Defer sort seed checks until adjust-order startup

.agents/skills/trellis-before-dev/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: trellis-before-dev
+description: "Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards."
+---
+
+Read the relevant development guidelines before starting your task.
+
+Execute these steps:
+
+1. **Discover packages and their spec layers**:
+   ```bash
+   python ./.trellis/scripts/get_context.py --mode packages
+   ```
+
+2. **Identify which specs apply** to your task based on:
+   - Which package you're modifying (e.g., `cli/`, `docs-site/`)
+   - What type of work (backend, frontend, unit-test, docs, etc.)
+
+3. **Read the spec index** for each relevant module:
+   ```bash
+   cat .trellis/spec/<package>/<layer>/index.md
+   ```
+   Follow the **"Pre-Development Checklist"** section in the index.
+
+4. **Read the specific guideline files** listed in the Pre-Development Checklist that are relevant to your task. The index is NOT the goal — it points you to the actual guideline files (e.g., `error-handling.md`, `conventions.md`, `mock-strategies.md`). Read those files to understand the coding standards and patterns.
+
+5. **Always read shared guides**:
+   ```bash
+   cat .trellis/spec/guides/index.md
+   ```
+
+6. Understand the coding standards and patterns you need to follow, then proceed with your development plan.
+
+This step is **mandatory** before writing any code.

.agents/skills/trellis-brainstorm/SKILL.md

@@ -0,0 +1,548 @@
+---
+name: trellis-brainstorm
+description: "Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task."
+---
+
+# Brainstorm - Requirements Discovery (AI Coding Enhanced)
+
+**CoreRule**: Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+
+Ask the questions one at a time.
+
+If a question can be answered by exploring the codebase, explore the codebase instead.
+
+---
+
+Guide AI through collaborative requirements discovery **before implementation**, optimized for AI coding workflows:
+
+* **Task-first** (capture ideas immediately)
+* **Action-before-asking** (reduce low-value questions)
+* **Research-first** for technical choices (avoid asking users to invent options)
+* **Diverge → Converge** (expand thinking, then lock MVP)
+
+---
+
+## When to Use
+
+Triggered from `start` (Trellis command) when the user describes a development task, especially when:
+
+* requirements are unclear or evolving
+* there are multiple valid implementation paths
+* trade-offs matter (UX, reliability, maintainability, cost, performance)
+* the user might not know the best options up front
+
+---
+
+## Core Principles (Non-negotiable)
+
+1. **Task-first (capture early)**
+   Always ensure a task exists at the start so the user's ideas are recorded immediately.
+
+2. **Action before asking**
+   If you can derive the answer from repo code, docs, configs, conventions, or quick research — do that first.
+
+3. **One question per message**
+   Never overwhelm the user with a list of questions. Ask one, update PRD, repeat.
+
+4. **Prefer concrete options**
+   For preference/decision questions, present 2–3 feasible, specific approaches with trade-offs.
+
+5. **Research-first for technical choices**
+   If the decision depends on industry conventions / similar tools / established patterns, do research first, then propose options.
+
+6. **Diverge → Converge**
+   After initial understanding, proactively consider future evolution, related scenarios, and failure/edge cases — then converge to an MVP with explicit out-of-scope.
+
+7. **No meta questions**
+   Do not ask "should I search?" or "can you paste the code so I can continue?"
+   If you need information: search/inspect. If blocked: ask the minimal blocking question.
+
+---
+
+## Step 0: Ensure Task Exists (ALWAYS)
+
+Before any Q&A, ensure a task exists. If none exists, create one immediately.
+
+* Use a **temporary working title** derived from the user's message.
+* It's OK if the title is imperfect — refine later in PRD.
+
+```bash
+TASK_DIR=$(python ./.trellis/scripts/task.py create "brainstorm: <short goal>" --slug <auto>)
+```
+
+Use a slug without a date prefix. `task.py create` adds the `MM-DD-`
+directory prefix automatically.
+
+Create/seed `prd.md` immediately with what you know:
+
+```markdown
+# brainstorm: <short goal>
+
+## Goal
+
+<one paragraph: what + why>
+
+## What I already know
+
+* <facts from user message>
+* <facts discovered from repo/docs>
+
+## Assumptions (temporary)
+
+* <assumptions to validate>
+
+## Open Questions
+
+* <ONLY Blocking / Preference questions; keep list short>
+
+## Requirements (evolving)
+
+* <start with what is known>
+
+## Acceptance Criteria (evolving)
+
+* [ ] <testable criterion>
+
+## Definition of Done (team quality bar)
+
+* Tests added/updated (unit/integration where appropriate)
+* Lint / typecheck / CI green
+* Docs/notes updated if behavior changes
+* Rollout/rollback considered if risky
+
+## Out of Scope (explicit)
+
+* <what we will not do in this task>
+
+## Technical Notes
+
+* <files inspected, constraints, links, references>
+* <research notes summary if applicable>
+```
+
+---
+
+## Step 1: Auto-Context (DO THIS BEFORE ASKING QUESTIONS)
+
+Before asking questions like "what does the code look like?", gather context yourself:
+
+### Repo inspection checklist
+
+* Identify likely modules/files impacted
+* Locate existing patterns (similar features, conventions, error handling style)
+* Check configs, scripts, existing command definitions
+* Note any constraints (runtime, dependency policy, build tooling)
+
+### Documentation checklist
+
+* Look for existing PRDs/specs/templates
+* Look for command usage examples, README, ADRs if any
+
+Write findings into PRD:
+
+* Add to `What I already know`
+* Add constraints/links to `Technical Notes`
+
+---
+
+## Step 2: Classify Complexity (still useful, not gating task creation)
+
+| Complexity   | Criteria                                               | Action                                      |
+| ------------ | ------------------------------------------------------ | ------------------------------------------- |
+| **Trivial**  | Single-line fix, typo, obvious change                  | Skip brainstorm, implement directly         |
+| **Simple**   | Clear goal, 1–2 files, scope well-defined              | Ask 1 confirm question, then implement      |
+| **Moderate** | Multiple files, some ambiguity                         | Light brainstorm (2–3 high-value questions) |
+| **Complex**  | Vague goal, architectural choices, multiple approaches | Full brainstorm                             |
+
+> Note: Task already exists from Step 0. Classification only affects depth of brainstorming.
+
+---
+
+## Step 3: Question Gate (Ask ONLY high-value questions)
+
+Before asking ANY question, run the following gate:
+
+### Gate A — Can I derive this without the user?
+
+If answer is available via:
+
+* repo inspection (code/config)
+* docs/specs/conventions
+* quick market/OSS research
+
+→ **Do not ask.** Fetch it, summarize, update PRD.
+
+### Gate B — Is this a meta/lazy question?
+
+Examples:
+
+* "Should I search?"
+* "Can you paste the code so I can proceed?"
+* "What does the code look like?" (when repo is available)
+
+→ **Do not ask.** Take action.
+
+### Gate C — What type of question is it?
+
+* **Blocking**: cannot proceed without user input
+* **Preference**: multiple valid choices, depends on product/UX/risk preference
+* **Derivable**: should be answered by inspection/research
+
+→ Only ask **Blocking** or **Preference**.
+
+---
+
+## Step 4: Research-first Mode (Mandatory for technical choices)
+
+### Trigger conditions (any → research-first)
+
+* The task involves selecting an approach, library, protocol, framework, template system, plugin mechanism, or CLI UX convention
+* The user asks for "best practice", "how others do it", "recommendation"
+* The user can't reasonably enumerate options
+
+### Delegate to `trellis-research` sub-agent (don't research inline)
+
+For each research topic, **spawn a `trellis-research` sub-agent via the Task tool** — don't do WebFetch / WebSearch / `gh api` inline in the main conversation.
+
+Why:
+- The sub-agent has its own context window → doesn't pollute brainstorm context with raw tool output
+- It persists findings to `{TASK_DIR}/research/<topic>.md` (the contract — see `workflow.md` Phase 1.2)
+- It returns only `{file path, one-line summary}` to the main agent
+- Independent topics can be **parallelized** — spawn multiple sub-agents in one tool call
+
+> **Codex exception**: on Codex CLI, do NOT dispatch `trellis-research` for research-first mode — do the research inline (WebFetch / WebSearch in the main session) and write findings to `{TASK_DIR}/research/<topic>.md` yourself. Reason: Codex `spawn_agent` runs sub-agents with `fork_turns="none"` (isolated context, no parent session inheritance), so the research sub-agent cannot resolve the active task path via `task.py current` and silently aborts without producing files. Inline research on Codex avoids this failure mode. The 3+ inline research calls limit (B rule in `workflow.md`) is relaxed for Codex specifically.
+
+Agent type: `trellis-research`
+Task description template: "Research <specific question>; persist findings to `{TASK_DIR}/research/<topic-slug>.md`."
+
+❌ Bad (what you must NOT do):
+```
+Main agent: WebFetch(url-A) → WebFetch(url-B) → Bash(gh api ...)
+          → WebSearch(q1) → WebSearch(q2) → ... (10+ inline calls)
+          → Write(research/topic.md)
+```
+→ Pollutes main context with raw HTML/JSON, burns tokens.
+
+✅ Good:
+```
+Main agent: Task(subagent_type="trellis-research",
+                 prompt="Research topic A; persist to research/topic-a.md")
+          + Task(subagent_type="trellis-research",
+                 prompt="Research topic B; persist to research/topic-b.md")
+          + Task(subagent_type="trellis-research",
+                 prompt="Research topic C; persist to research/topic-c.md")
+→ Reads research/topic-{a,b,c}.md after they finish.
+```
+
+### Research steps (to pass into each sub-agent prompt)
+
+Each `trellis-research` sub-agent should:
+
+1. Identify 2–4 comparable tools/patterns for its topic
+2. Summarize common conventions and why they exist
+3. Map conventions onto our repo constraints
+4. Write findings to `{TASK_DIR}/research/<topic>.md`
+
+Main agent then reads the persisted files and produces **2–3 feasible approaches** in PRD.
+
+### Research output format (PRD)
+
+The PRD itself should only reference the persisted research files, not duplicate their content. Add a `## Research References` section pointing at `research/*.md`.
+
+Optionally, add a convergence section with feasible approaches derived from the research:
+
+```markdown
+## Research References
+
+* [`research/<topic-a>.md`](research/<topic-a>.md) — <one-line takeaway>
+* [`research/<topic-b>.md`](research/<topic-b>.md) — <one-line takeaway>
+
+## Research Notes
+
+### What similar tools do
+
+* ...
+* ...
+
+### Constraints from our repo/project
+
+* ...
+
+### Feasible approaches here
+
+**Approach A: <name>** (Recommended)
+
+* How it works:
+* Pros:
+* Cons:
+
+**Approach B: <name>**
+
+* How it works:
+* Pros:
+* Cons:
+
+**Approach C: <name>** (optional)
+
+* ...
+```
+
+Then ask **one** preference question:
+
+* "Which approach do you prefer: A / B / C (or other)?"
+
+---
+
+## Step 5: Expansion Sweep (DIVERGE) — Required after initial understanding
+
+After you can summarize the goal, proactively broaden thinking before converging.
+
+### Expansion categories (keep to 1–2 bullets each)
+
+1. **Future evolution**
+
+   * What might this feature become in 1–3 months?
+   * What extension points are worth preserving now?
+
+2. **Related scenarios**
+
+   * What adjacent commands/flows should remain consistent with this?
+   * Are there parity expectations (create vs update, import vs export, etc.)?
+
+3. **Failure & edge cases**
+
+   * Conflicts, offline/network failure, retries, idempotency, compatibility, rollback
+   * Input validation, security boundaries, permission checks
+
+### Expansion message template (to user)
+
+```markdown
+I understand you want to implement: <current goal>.
+
+Before diving into design, let me quickly diverge to consider three categories (to avoid rework later):
+
+1. Future evolution: <1–2 bullets>
+2. Related scenarios: <1–2 bullets>
+3. Failure/edge cases: <1–2 bullets>
+
+For this MVP, which would you like to include (or none)?
+
+1. Current requirement only (minimal viable)
+2. Add <X> (reserve for future extension)
+3. Add <Y> (improve robustness/consistency)
+4. Other: describe your preference
+```
+
+Then update PRD:
+
+* What's in MVP → `Requirements`
+* What's excluded → `Out of Scope`
+
+---
+
+## Step 6: Q&A Loop (CONVERGE)
+
+### Rules
+
+* One question per message
+* Prefer multiple-choice when possible
+* After each user answer:
+
+  * Update PRD immediately
+  * Move answered items from `Open Questions` → `Requirements`
+  * Update `Acceptance Criteria` with testable checkboxes
+  * Clarify `Out of Scope`
+
+### Question priority (recommended)
+
+1. **MVP scope boundary** (what is included/excluded)
+2. **Preference decisions** (after presenting concrete options)
+3. **Failure/edge behavior** (only for MVP-critical paths)
+4. **Success metrics & Acceptance Criteria** (what proves it works)
+
+### Preferred question format (multiple choice)
+
+```markdown
+For <topic>, which approach do you prefer?
+
+1. **Option A** — <what it means + trade-off>
+2. **Option B** — <what it means + trade-off>
+3. **Option C** — <what it means + trade-off>
+4. **Other** — describe your preference
+```
+
+---
+
+## Step 7: Propose Approaches + Record Decisions (Complex tasks)
+
+After requirements are clear enough, propose 2–3 approaches (if not already done via research-first):
+
+```markdown
+Based on current information, here are 2–3 feasible approaches:
+
+**Approach A: <name>** (Recommended)
+
+* How:
+* Pros:
+* Cons:
+
+**Approach B: <name>**
+
+* How:
+* Pros:
+* Cons:
+
+Which direction do you prefer?
+```
+
+Record the outcome in PRD as an ADR-lite section:
+
+```markdown
+## Decision (ADR-lite)
+
+**Context**: Why this decision was needed
+**Decision**: Which approach was chosen
+**Consequences**: Trade-offs, risks, potential future improvements
+```
+
+---
+
+## Step 8: Final Confirmation + Implementation Plan
+
+When open questions are resolved, confirm complete requirements with a structured summary:
+
+### Final confirmation format
+
+```markdown
+Here's my understanding of the complete requirements:
+
+**Goal**: <one sentence>
+
+**Requirements**:
+
+* ...
+* ...
+
+**Acceptance Criteria**:
+
+* [ ] ...
+* [ ] ...
+
+**Definition of Done**:
+
+* ...
+
+**Out of Scope**:
+
+* ...
+
+**Technical Approach**:
+<brief summary + key decisions>
+
+**Implementation Plan (small PRs)**:
+
+* PR1: <scaffolding + tests + minimal plumbing>
+* PR2: <core behavior>
+* PR3: <edge cases + docs + cleanup>
+
+Does this look correct? If yes, I'll proceed with implementation.
+```
+
+### Subtask Decomposition (Complex Tasks)
+
+For complex tasks with multiple independent work items, create subtasks:
+
+```bash
+# Create child tasks
+CHILD1=$(python ./.trellis/scripts/task.py create "Child task 1" --slug child1 --parent "$TASK_DIR")
+CHILD2=$(python ./.trellis/scripts/task.py create "Child task 2" --slug child2 --parent "$TASK_DIR")
+
+# Or link existing tasks
+python ./.trellis/scripts/task.py add-subtask "$TASK_DIR" "$CHILD_DIR"
+```
+
+---
+
+## PRD Target Structure (final)
+
+`prd.md` should converge to:
+
+```markdown
+# <Task Title>
+
+## Goal
+
+<why + what>
+
+## Requirements
+
+* ...
+
+## Acceptance Criteria
+
+* [ ] ...
+
+## Definition of Done
+
+* ...
+
+## Technical Approach
+
+<key design + decisions>
+
+## Decision (ADR-lite)
+
+Context / Decision / Consequences
+
+## Out of Scope
+
+* ...
+
+## Technical Notes
+
+<constraints, references, files, research notes>
+```
+
+---
+
+## Anti-Patterns (Hard Avoid)
+
+* Asking user for code/context that can be derived from repo
+* Asking user to choose an approach before presenting concrete options
+* Meta questions about whether to research
+* Staying narrowly on the initial request without considering evolution/edges
+* Letting brainstorming drift without updating PRD
+
+---
+
+## Integration with Start Workflow
+
+After brainstorm completes (Step 8 confirmation approved), the flow continues to the Task Workflow's **Phase 2: Prepare for Implementation**:
+
+```text
+Brainstorm
+  Step 0: Create task directory + seed PRD
+  Step 1–7: Discover requirements, research, converge
+  Step 8: Final confirmation → user approves
+  ↓
+Task Workflow Phase 2 (Prepare for Implementation)
+  Code-Spec Depth Check (if applicable)
+  → Research codebase (based on confirmed PRD)
+  → Configure code-spec context (jsonl files)
+  → Activate task
+  ↓
+Task Workflow Phase 3 (Execute)
+  Implement → Check → Complete
+```
+
+The task directory and PRD already exist from brainstorm, so Phase 1 of the Task Workflow is skipped entirely.
+
+---
+
+## Related Commands
+
+| Command | When to Use |
+|---------|-------------|
+| ``start` (Trellis command)` | Entry point that triggers brainstorm |
+| ``finish-work` (Trellis command)` | After implementation is complete |
+| ``update-spec` (Trellis command)` | If new patterns emerge during work |

.agents/skills/trellis-break-loop/SKILL.md

@@ -0,0 +1,130 @@
+---
+name: trellis-break-loop
+description: "Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs."
+---
+
+# Break the Loop - Deep Bug Analysis
+
+When debug is complete, use this for deep analysis to break the "fix bug -> forget -> repeat" cycle.
+
+---
+
+## Analysis Framework
+
+Analyze the bug you just fixed from these 5 dimensions:
+
+### 1. Root Cause Category
+
+Which category does this bug belong to?
+
+| Category | Characteristics | Example |
+|----------|-----------------|---------|
+| **A. Missing Spec** | No documentation on how to do it | New feature without checklist |
+| **B. Cross-Layer Contract** | Interface between layers unclear | API returns different format than expected |
+| **C. Change Propagation Failure** | Changed one place, missed others | Changed function signature, missed call sites |
+| **D. Test Coverage Gap** | Unit test passes, integration fails | Works alone, breaks when combined |
+| **E. Implicit Assumption** | Code relies on undocumented assumption | Timestamp seconds vs milliseconds |
+
+### 2. Why Fixes Failed (if applicable)
+
+If you tried multiple fixes before succeeding, analyze each failure:
+
+- **Surface Fix**: Fixed symptom, not root cause
+- **Incomplete Scope**: Found root cause, didn't cover all cases
+- **Tool Limitation**: grep missed it, type check wasn't strict
+- **Mental Model**: Kept looking in same layer, didn't think cross-layer
+
+### 3. Prevention Mechanisms
+
+What mechanisms would prevent this from happening again?
+
+| Type | Description | Example |
+|------|-------------|---------|
+| **Documentation** | Write it down so people know | Update thinking guide |
+| **Architecture** | Make the error impossible structurally | Type-safe wrappers |
+| **Compile-time** | Strict type checking, no escape hatches | Signature change causes compile error |
+| **Runtime** | Monitoring, alerts, scans | Detect orphan entities |
+| **Test Coverage** | E2E tests, integration tests | Verify full flow |
+| **Code Review** | Checklist, PR template | "Did you check X?" |
+
+### 4. Systematic Expansion
+
+What broader problems does this bug reveal?
+
+- **Similar Issues**: Where else might this problem exist?
+- **Design Flaw**: Is there a fundamental architecture issue?
+- **Process Flaw**: Is there a development process improvement?
+- **Knowledge Gap**: Is the team missing some understanding?
+
+### 5. Knowledge Capture
+
+Solidify insights into the system:
+
+- [ ] Update `.trellis/spec/guides/` thinking guides
+- [ ] Update relevant `.trellis/spec/` docs
+- [ ] Create issue record (if applicable)
+- [ ] Create feature ticket for root fix
+- [ ] Update check guidelines if needed
+
+---
+
+## Output Format
+
+Please output analysis in this format:
+
+```markdown
+## Bug Analysis: [Short Description]
+
+### 1. Root Cause Category
+- **Category**: [A/B/C/D/E] - [Category Name]
+- **Specific Cause**: [Detailed description]
+
+### 2. Why Fixes Failed (if applicable)
+1. [First attempt]: [Why it failed]
+2. [Second attempt]: [Why it failed]
+...
+
+### 3. Prevention Mechanisms
+| Priority | Mechanism | Specific Action | Status |
+|----------|-----------|-----------------|--------|
+| P0 | ... | ... | TODO/DONE |
+
+### 4. Systematic Expansion
+- **Similar Issues**: [List places with similar problems]
+- **Design Improvement**: [Architecture-level suggestions]
+- **Process Improvement**: [Development process suggestions]
+
+### 5. Knowledge Capture
+- [ ] [Documents to update / tickets to create]
+```
+
+---
+
+## Core Philosophy
+
+> **The value of debugging is not in fixing the bug, but in making this class of bugs never happen again.**
+
+Three levels of insight:
+1. **Tactical**: How to fix THIS bug
+2. **Strategic**: How to prevent THIS CLASS of bugs
+3. **Philosophical**: How to expand thinking patterns
+
+30 minutes of analysis saves 30 hours of future debugging.
+
+---
+
+## After Analysis: Immediate Actions
+
+**IMPORTANT**: After completing the analysis above, you MUST immediately:
+
+1. **Update spec/guides** - Don't just list TODOs, actually update the relevant files:
+   - If it's a cross-platform issue → update `cross-platform-thinking-guide.md`
+   - If it's a cross-layer issue → update `cross-layer-thinking-guide.md`
+   - If it's a code reuse issue → update `code-reuse-thinking-guide.md`
+   - If it's domain-specific → update `backend/*.md` or `frontend/*.md`
+
+2. **Sync templates** - After updating `.trellis/spec/`, sync to `src/templates/markdown/spec/`
+
+3. **Commit the spec updates** - This is the primary output, not just the analysis text
+
+> **The analysis is worthless if it stays in chat. The value is in the updated specs.**

.agents/skills/trellis-check/SKILL.md

@@ -0,0 +1,92 @@
+---
+name: trellis-check
+description: "Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions."
+---
+
+# Code Quality Check
+
+Comprehensive quality verification for recently written code. Combines spec compliance, cross-layer safety, and pre-commit checks.
+
+---
+
+## Step 1: Identify What Changed
+
+```bash
+git diff --name-only HEAD
+git status
+```
+
+## Step 2: Read Applicable Specs
+
+```bash
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+For each changed package/layer, read the spec index and follow its **Quality Check** section:
+
+```bash
+cat .trellis/spec/<package>/<layer>/index.md
+```
+
+Read the specific guideline files referenced — the index is a pointer, not the goal.
+
+## Step 3: Run Project Checks
+
+Run the project's lint, type-check, and test commands. Fix any failures before proceeding.
+
+## Step 4: Review Against Checklist
+
+### Code Quality
+
+- [ ] Linter passes?
+- [ ] Type checker passes (if applicable)?
+- [ ] Tests pass?
+- [ ] No debug logging left in?
+- [ ] No suppressed warnings or type-safety bypasses?
+
+### Test Coverage
+
+- [ ] New function → unit test added?
+- [ ] Bug fix → regression test added?
+- [ ] Changed behavior → existing tests updated?
+
+### Spec Sync
+
+- [ ] Does `.trellis/spec/` need updates? (new patterns, conventions, lessons learned)
+
+> "If I fixed a bug or discovered something non-obvious, should I document it so future me won't hit the same issue?" → If YES, update the relevant spec doc.
+
+## Step 5: Cross-Layer Dimensions (if applicable)
+
+Skip this step if your change is confined to a single layer.
+
+### A. Data Flow (changes touch 3+ layers)
+
+- [ ] Read flow traces correctly: Storage → Service → API → UI
+- [ ] Write flow traces correctly: UI → API → Service → Storage
+- [ ] Types/schemas correctly passed between layers?
+- [ ] Errors properly propagated to caller?
+
+### B. Code Reuse (modifying constants, creating utilities)
+
+- [ ] Searched for existing similar code before creating new?
+  ```bash
+  grep -r "pattern" src/
+  ```
+- [ ] If 2+ places define same value → extracted to shared constant?
+- [ ] After batch modification, all occurrences updated?
+
+### C. Import/Dependency (creating new files)
+
+- [ ] Correct import paths (relative vs absolute)?
+- [ ] No circular dependencies?
+
+### D. Same-Layer Consistency
+
+- [ ] Other places using the same concept are consistent?
+
+---
+
+## Step 6: Report and Fix
+
+Report violations found and fix them directly. Re-run project checks after fixes.

.agents/skills/trellis-continue/SKILL.md

@@ -0,0 +1,60 @@
+---
+name: trellis-continue
+description: "Resume work on the current task. Loads the workflow Phase Index, figures out which phase/step to pick up at, then pulls the step-level detail via get_context.py --mode phase. Use when coming back to an in-progress task and you need to know what to do next."
+---
+
+# Continue Current Task
+
+Resume work on the current task — pick up at the right phase/step in `.trellis/workflow.md`.
+
+---
+
+## Step 1: Load Current Context
+
+```bash
+python ./.trellis/scripts/get_context.py
+```
+
+Confirms: current task, git state, recent commits.
+
+## Step 2: Load the Phase Index
+
+```bash
+python ./.trellis/scripts/get_context.py --mode phase
+```
+
+Shows the Phase Index (Plan / Execute / Finish) with routing + skill mapping.
+
+## Step 3: Decide Where You Are
+
+`get_context.py` shows the active task's `status` field. Route by `status` + artifact presence:
+
+- `status=planning` + no `prd.md` → **1.1** (load `trellis-brainstorm`)
+- `status=planning` + `prd.md` exists + `implement.jsonl` not curated (only the seed `_example` row) → **1.3**
+- `status=planning` + `prd.md` + curated `implement.jsonl` → **1.4** (run `task.py start` to enter Phase 2)
+- `status=in_progress` + implementation not started → **2.1**
+- `status=in_progress` + implementation done, not yet checked → **2.2**
+- `status=in_progress` + check passed → **3.1**
+- `status=completed` (rare; usually archived immediately) → archive flow
+
+Phase rules (full detail in `.trellis/workflow.md`):
+
+1. Run steps **in order** within a phase — `[required]` steps must not be skipped
+2. `[once]` steps are already done if the output exists (e.g., `prd.md` for 1.1; `implement.jsonl` with curated entries for 1.3) — skip them
+3. You may go back to an earlier phase if discoveries require it
+
+## Step 4: Load the Specific Step
+
+Once you know which step to resume at:
+
+```bash
+python ./.trellis/scripts/get_context.py --mode phase --step <X.X> --platform codex
+```
+
+Follow the loaded instructions. After each `[required]` step completes, move to the next.
+
+---
+
+## Reference
+
+Full workflow, skill routing table, and the DO-NOT-skip table live in `.trellis/workflow.md`. This command is only an entry point — the canonical guidance is there.

.agents/skills/trellis-finish-work/SKILL.md

@@ -0,0 +1,71 @@
+---
+name: trellis-finish-work
+description: "Wrap up the current session: verify quality gate passed, remind user to commit, archive completed tasks, and record session progress to the developer journal. Use when done coding and ready to end the session."
+---
+
+# Finish Work
+
+Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.
+
+## Step 1: Survey current state
+
+```bash
+python ./.trellis/scripts/get_context.py --mode record
+```
+
+This prints:
+
+- **My active tasks** — review whether any besides the current one are actually done (code merged, AC met) and should be archived this round.
+- **Git status** — quick visual on what's dirty.
+- **Recent commits** — you'll need their hashes in Step 4 for `--commit`.
+
+If `--mode record` surfaces other completed tasks not tied to the current session, surface them to the user with a one-shot confirmation: "These N tasks look done — archive them too in this round? [y/N]". Default is no; the current active task is always archived in Step 3 regardless.
+
+## Step 2: Sanity check — classify dirty paths
+
+Run:
+
+```bash
+git status --porcelain
+```
+
+Filter out paths under `.trellis/workspace/` and `.trellis/tasks/` — those are managed by `add_session.py` and `task.py archive` auto-commits and will appear dirty as part of this skill's own work.
+
+For each remaining dirty path, decide whether it belongs to **the current task** or to **other parallel work** (e.g., another terminal window editing the same repo). Heuristics:
+
+- Paths referenced in the current task's `prd.md` / `implement.jsonl` / `check.jsonl` → current task
+- Paths in code areas matching the task's stated scope, or that you remember editing this session → current task
+- Paths in unrelated areas you have no recollection of touching this session → other parallel work
+
+Then route:
+
+- **Any remaining path looks like current-task work** — bail out with:
+  > "Working tree has uncommitted code changes from this task: `<list>`. Return to workflow Phase 3.4 to commit them before running ``finish-work` (Trellis command)`."
+
+  Do NOT run `git commit` here. Do NOT prompt the user to commit. The user goes back to Phase 3.4 and the AI drives the batched commit there.
+- **All remaining paths look unrelated** (other parallel-window work) — report them once and continue to Step 3:
+  > "FYI, dirty files outside this task's scope — leaving them for the other window: `<list>`."
+- **Genuinely unsure** — ask the user once: "Are `<list>` this task's work I forgot to commit, or another window's? (commit / ignore)" — then route per their answer.
+
+## Step 3: Archive task(s)
+
+```bash
+python ./.trellis/scripts/task.py archive <task-name>
+```
+
+At minimum: the current active task (if any). Plus any extra tasks the user confirmed in Step 1. Each archive produces a `chore(task): archive ...` commit via the script's auto-commit.
+
+If there is no active task and the user did not confirm any cleanup archives, skip this step.
+
+## Step 4: Record session journal
+
+```bash
+python ./.trellis/scripts/add_session.py \
+  --title "Session Title" \
+  --commit "hash1,hash2" \
+  --summary "Brief summary"
+```
+
+Use the work-commit hashes produced in Phase 3.4 (visible in Step 1's `Recent commits` list, or via `git log --oneline`) for `--commit`. Do not include the archive commit hashes from Step 3. This produces a `chore: record journal` commit.
+
+Final git log order: `<work commits from 3.4>` → `chore(task): archive ...` (one or more) → `chore: record journal`.

.agents/skills/trellis-meta/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: trellis-meta
+description: "Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, or workflows generated by trellis init."
+---
+
+# Trellis Meta
+
+This skill is for local Trellis users who have already run `trellis init` in a project. After reading it, an AI should understand the Trellis architecture, operating model, and customization entry points inside that user project, then modify the generated `.trellis/` and platform directory files according to the user's request.
+
+The default operating scope is local files in the user project:
+
+- `.trellis/`: workflow, config, tasks, spec, workspace, scripts, and runtime state.
+- Platform directories: `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, `.kiro/`, `.gemini/`, `.qoder/`, `.codebuddy/`, `.github/`, `.factory/`, `.pi/`, `.kilocode/`, `.agent/`, `.windsurf/`, and similar directories.
+- Shared skill layer: `.agents/skills/`.
+
+Do not assume the user has the Trellis source repository. Do not default to modifying the global npm install directory or `node_modules`.
+
+## How To Use
+
+1. Read `references/local-architecture/overview.md` first to establish the local Trellis system model.
+2. If the request involves a specific AI tool, read `references/platform-files/platform-map.md` and the relevant platform file notes.
+3. If the user wants to change behavior, read `references/customize-local/overview.md`, then open the specific customization topic.
+4. Before editing, read the actual files in the user project and treat local content as authoritative.
+
+## References
+
+### Local Architecture
+
+- `references/local-architecture/overview.md`: The three-layer local Trellis architecture and customization principles.
+- `references/local-architecture/generated-files.md`: Files generated by `trellis init` and their customization boundaries.
+- `references/local-architecture/workflow.md`: Phases, routing, and workflow-state blocks in `.trellis/workflow.md`.
+- `references/local-architecture/task-system.md`: Task directories, active tasks, JSONL context, and task runtime.
+- `references/local-architecture/spec-system.md`: How `.trellis/spec/` is organized and injected.
+- `references/local-architecture/workspace-memory.md`: `.trellis/workspace/`, journals, and cross-session memory.
+- `references/local-architecture/context-injection.md`: Hooks, sub-agent preludes, and context injection paths.
+
+### Platform Files
+
+- `references/platform-files/overview.md`: How shared `.trellis/` files relate to platform directories.
+- `references/platform-files/platform-map.md`: Platform directories and paths for skills, agents, hooks, and extensions.
+- `references/platform-files/hooks-and-settings.md`: How settings/config files, hooks, plugins, and extensions connect to Trellis.
+- `references/platform-files/agents.md`: Local file responsibilities for `trellis-research`, `trellis-implement`, and `trellis-check`.
+- `references/platform-files/skills-and-commands.md`: Differences between skills, commands, prompts, and workflows, plus how to change them.
+
+### Local Customization
+
+- `references/customize-local/overview.md`: Choose the right local customization entry point for the user's request.
+- `references/customize-local/change-workflow.md`: Change phases, routing, next actions, and workflow-state.
+- `references/customize-local/change-task-lifecycle.md`: Change task creation, status, archive behavior, and hooks.
+- `references/customize-local/change-context-loading.md`: Change how tasks, specs, journals, and hook context are loaded.
+- `references/customize-local/change-hooks.md`: Change platform hooks, settings, and shell session bridges.
+- `references/customize-local/change-agents.md`: Change research, implement, and check agent behavior.
+- `references/customize-local/change-skills-or-commands.md`: Add or modify local skills, commands, prompts, and workflows.
+- `references/customize-local/change-spec-structure.md`: Adjust the project spec structure under `.trellis/spec/`.
+- `references/customize-local/add-project-local-conventions.md`: Put team rules into project-local specs or local skills.
+
+## Current Rules
+
+- `.trellis/workflow.md` is the local workflow source of truth.
+- `.trellis/config.yaml` is the project-level Trellis configuration and task hook configuration entry point.
+- `.trellis/spec/` stores the user's project-specific coding conventions and design constraints.
+- `.trellis/tasks/` stores task PRDs, technical notes, research files, and JSONL context.
+- `.trellis/workspace/` stores developer journals and cross-session memory.
+- Platform settings/config files decide which hooks, agents, skills, commands, prompts, and workflows actually run.
+- `.trellis/.template-hashes.json` and `.trellis/.runtime/` are management/runtime state files. Confirm necessity before editing them.
+
+## Do Not
+
+- Do not treat Trellis upstream source code as the default target for local customization.
+- Do not modify the global npm install directory or `node_modules/@mindfoldhq/trellis` to implement project needs.
+- Do not overwrite user-modified local files with default templates.
+- Do not put team-private project rules into the public `trellis-meta`; put project rules in `.trellis/spec/` or a project-local skill.
+- Do not describe removed historical mechanisms as current Trellis behavior.

.agents/skills/trellis-meta/references/customize-local/add-project-local-conventions.md

@@ -0,0 +1,83 @@
+# Add Project-Local Conventions
+
+Often the user does not need to change Trellis mechanics; they need local AI to understand their team's conventions. In that case, prefer `.trellis/spec/` or a project-local skill instead of editing `trellis-meta`.
+
+## Where To Put Things
+
+| Content type | Location |
+| --- | --- |
+| Rules code must follow | `.trellis/spec/<layer>/` |
+| Cross-layer thinking methods | `.trellis/spec/guides/` |
+| AI capability for a project-specific flow | Platform-local skill |
+| One-off task material | `.trellis/tasks/<task>/` |
+| Session summary | `.trellis/workspace/<developer>/journal-N.md` |
+
+## Create A Project-Local Skill
+
+If the user wants AI to know "how this project customizes Trellis," create a local skill:
+
+```text
+.claude/skills/trellis-local/
+└── SKILL.md
+```
+
+Example:
+
+```md
+---
+name: trellis-local
+description: "Project-local Trellis customizations for this repository. Use when changing this project's Trellis workflow, hooks, local agents, or team-specific conventions."
+---
+
+# Trellis Local
+
+## Local Scope
+
+This skill documents this repository's Trellis customizations only.
+
+## Custom Workflow Rules
+
+- ...
+
+## Local Hook Changes
+
+- ...
+
+## Local Agent Changes
+
+- ...
+```
+
+For multi-platform projects, place equivalent versions in other platform skill directories, or use `.agents/skills/` for platforms that support the shared layer.
+
+## Write To `.trellis/spec/`
+
+If the content is a coding convention, write it to spec. Examples:
+
+```text
+.trellis/spec/backend/error-handling.md
+.trellis/spec/frontend/components.md
+.trellis/spec/guides/cross-platform-thinking-guide.md
+```
+
+After writing it, update the corresponding `index.md` so AI can find the new rule from the entry point.
+
+## Make The Current Task Use New Conventions
+
+After writing a spec, add it to the current task context:
+
+```bash
+python ./.trellis/scripts/task.py add-context <task> implement ".trellis/spec/backend/error-handling.md" "Error handling conventions"
+python ./.trellis/scripts/task.py add-context <task> check ".trellis/spec/backend/error-handling.md" "Review error handling"
+```
+
+## Do Not Store Project-Private Rules In `trellis-meta`
+
+`trellis-meta` is a public skill for understanding Trellis architecture and local customization entry points. Put project-private content in:
+
+- `.trellis/spec/`
+- a project-local skill
+- the current task
+- workspace journal
+
+This prevents future updates to Trellis's built-in `trellis-meta` from overwriting the team's own conventions.

.agents/skills/trellis-meta/references/customize-local/change-agents.md

@@ -0,0 +1,54 @@
+# Change Local Agents
+
+When the user wants to change `trellis-research`, `trellis-implement`, or `trellis-check` behavior, edit platform agent files in the user project.
+
+## Read These Files First
+
+1. Target platform agent directory
+2. `.trellis/workflow.md` Phase 2 / research routing
+3. Current task `prd.md`
+4. Current task `implement.jsonl` / `check.jsonl`
+5. Relevant hook or agent prelude
+
+## Common Paths
+
+| Platform | Path |
+| --- | --- |
+| Claude Code | `.claude/agents/trellis-*.md` |
+| Cursor | `.cursor/agents/trellis-*.md` |
+| OpenCode | `.opencode/agents/trellis-*.md` |
+| Codex | `.codex/agents/trellis-*.toml` |
+| Kiro | `.kiro/agents/trellis-*.json` |
+| Gemini CLI | `.gemini/agents/trellis-*.md` |
+| Qoder | `.qoder/agents/trellis-*.md` |
+| CodeBuddy | `.codebuddy/agents/trellis-*.md` |
+| Factory Droid | `.factory/droids/trellis-*.md` |
+| Pi Agent | `.pi/agents/trellis-*.md` |
+
+Use the actual paths in the user project as authoritative.
+
+## Common Needs
+
+| Need | Which agent to edit |
+| --- | --- |
+| Research must write files, not only reply in chat | `trellis-research` |
+| Certain local specs must be read before implementation | `trellis-implement` + `implement.jsonl` configuration rules |
+| Specific commands must run during checking | `trellis-check` |
+| Agent must not modify certain directories | The corresponding agent's write boundary instructions |
+| Agent output format must be fixed | The corresponding agent's final/reporting instructions |
+
+## Modification Principles
+
+1. **Preserve role boundaries**: research investigates and persists; implement writes implementation; check reviews and fixes.
+2. **Do not hard-code project specs into agents**: long-term specs belong in `.trellis/spec/`; agents are responsible for reading them.
+3. **Make read order explicit**: active task -> PRD -> info -> JSONL -> spec/research.
+4. **Make write boundaries explicit**: which directories may be written and which may not.
+5. **Synchronize across platforms**: when the user configured multiple platforms, decide whether to change only the current platform or all platform agents.
+
+## Agent Pull Platforms
+
+If an agent file contains a prelude for "read task/context after startup," do not remove those steps when editing. Otherwise the agent will work only from chat context and bypass Trellis's core mechanism.
+
+## Hook Push Platforms
+
+If context is injected by a hook, the agent file should still retain responsibility boundaries. Do not remove PRD/spec requirements from the agent just because a hook injects context.

.agents/skills/trellis-meta/references/customize-local/change-context-loading.md

@@ -0,0 +1,81 @@
+# Change Local Context Loading
+
+Context loading determines when AI reads workflow, task, spec, research, workspace, and git status. Read this page when the user says "AI does not know the current task," "the agent did not read specs," or "there is too much/too little context."
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. `.trellis/scripts/get_context.py`
+3. `.trellis/scripts/common/session_context.py`
+4. `.trellis/scripts/common/task_context.py`
+5. `.trellis/scripts/common/active_task.py`
+6. Current platform hooks or agent files
+7. The current task's `implement.jsonl` / `check.jsonl`
+
+## Context Sources
+
+| Source | Purpose |
+| --- | --- |
+| `.trellis/workflow.md` | Workflow and next-action hints. |
+| `.trellis/tasks/<task>/prd.md` | Current task requirements. |
+| `.trellis/tasks/<task>/implement.jsonl` | Spec/research to read before implementation. |
+| `.trellis/tasks/<task>/check.jsonl` | Spec/research to read during checking. |
+| `.trellis/spec/` | Project specs. |
+| `.trellis/workspace/` | Session records. |
+| git status | Current working tree changes. |
+
+## Common Needs And Edit Points
+
+| Need | Edit point |
+| --- | --- |
+| Inject more/less information in new sessions | `session_context.py` or the platform `session-start` hook. |
+| Change hints on each user input | `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The `inject-workflow-state` hook is parser-only and reads the block verbatim. |
+| Agent did not read specs | Task JSONL, agent prelude, `inject-subagent-context` hook. |
+| Active task is lost | `active_task.py` and platform session identity propagation. |
+| Change JSONL validation rules | `task_context.py`. |
+
+## JSONL Rules
+
+`implement.jsonl` / `check.jsonl` are the key context loading interface:
+
+```jsonl
+{"file": ".trellis/spec/backend/index.md", "reason": "Backend conventions"}
+{"file": ".trellis/tasks/04-28-x/research/api.md", "reason": "API research"}
+```
+
+Include only spec/research files. Do not put code files that will be modified into these manifests; agents read code files themselves during implementation.
+
+## Change Session Context
+
+If the user wants every new session to see more project state, edit:
+
+- `.trellis/scripts/common/session_context.py`
+- the corresponding platform `session-start` hook
+
+Context cannot grow without bound. Prefer injecting indexes and paths so the AI can read detailed files on demand.
+
+## Change Sub-Agent Context
+
+First determine which mode the platform uses:
+
+- hook push: edit the `inject-subagent-context` hook.
+- agent pull: edit the read steps in the corresponding `trellis-implement` / `trellis-check` agent file.
+
+In both modes, make sure the agent ultimately reads:
+
+1. active task
+2. `prd.md`
+3. `info.md` if present
+4. the corresponding JSONL
+5. spec/research referenced by the JSONL
+
+## Troubleshooting Order
+
+```bash
+python ./.trellis/scripts/task.py current --source
+python ./.trellis/scripts/task.py list-context <task>
+python ./.trellis/scripts/task.py validate <task>
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+Confirm the task and JSONL are correct before editing hooks/agents.

.agents/skills/trellis-meta/references/customize-local/change-hooks.md

@@ -0,0 +1,57 @@
+# Change Local Hooks
+
+Hooks are the automation layer that connects a platform to Trellis. When the user wants to change "when context is injected," "how shell commands inherit a session," or "which files are read before an agent starts," hooks are usually the edit point.
+
+## Read These Files First
+
+1. Target platform settings/config, such as `.claude/settings.json`, `.codex/hooks.json`, `.cursor/hooks.json`
+2. Target platform hooks directory
+3. `.trellis/scripts/common/active_task.py`
+4. `.trellis/scripts/common/session_context.py`
+5. `.trellis/workflow.md`
+
+## Common Hook Types
+
+| Hook | Purpose |
+| --- | --- |
+| session-start | Injects a Trellis overview when a session starts, clears, or compacts. |
+| workflow-state | Injects a state hint on each user input. |
+| sub-agent context | Injects PRD/spec/research before an agent starts. |
+| shell session bridge | Lets `task.py` commands in shell see the same session identity. |
+
+## Modification Steps
+
+1. Find the hook registration in settings/config.
+2. Confirm the registered script path exists.
+3. Read the hook script and identify inputs, outputs, and called `.trellis/scripts/`.
+4. Modify hook behavior.
+5. If the hook depends on workflow content, synchronize `.trellis/workflow.md`.
+
+## Example: Change New-Session Injection Content
+
+First find the session-start hook:
+
+```text
+.claude/settings.json
+.claude/hooks/session-start.py
+```
+
+If the hook ultimately calls `.trellis/scripts/get_context.py` or `session_context.py`, editing the local script is usually more robust than hard-coding content in the hook.
+
+## Example: Agent Did Not Read JSONL
+
+First confirm:
+
+```bash
+python ./.trellis/scripts/task.py current --source
+python ./.trellis/scripts/task.py validate <task>
+```
+
+If the task and JSONL are correct, determine whether the platform uses hook push or agent pull. For hook push, edit `inject-subagent-context`; for agent pull, edit the agent file.
+
+## Notes
+
+- Settings handle registration, hook scripts handle behavior; inspect both together.
+- Different platforms support different hook events. Do not directly copy another platform's settings.
+- Hooks should read project-local `.trellis/`; they should not depend on Trellis upstream source paths.
+- Hook failures should produce visible errors so AI does not silently lose context.

.agents/skills/trellis-meta/references/customize-local/change-skills-or-commands.md

@@ -0,0 +1,78 @@
+# Change Local Skills, Commands, Prompts, And Workflows
+
+When the user wants to change AI entry points, auto-trigger rules, or explicit command behavior, edit skills, commands, prompts, or workflows in local platform directories.
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. Target platform skill/command/prompt/workflow directory
+3. Related agent or hook files
+4. Whether project rules already exist in `.trellis/spec/`
+
+## Which Entry Type To Choose
+
+| Goal | Recommendation |
+| --- | --- |
+| AI should automatically know a capability | Add or modify a skill. |
+| User wants to trigger manually with a command | Add or modify a command/prompt/workflow. |
+| Team project conventions | Prefer `.trellis/spec/` or a project-local skill. |
+| Change Trellis flow semantics | Synchronize `.trellis/workflow.md`. |
+
+## Modify A Skill
+
+A skill is usually:
+
+```text
+<skill-name>/
+├── SKILL.md
+└── references/
+```
+
+`SKILL.md` should be short and responsible for triggering/routing. Put long content in `references/` so AI can read it on demand.
+
+The frontmatter description should specify when to use the skill. Example:
+
+```yaml
+description: "Use when customizing this project's deployment workflow and release checklist."
+```
+
+Do not write vague descriptions such as "helpful project skill"; they can trigger incorrectly.
+
+## Modify A Command/Prompt/Workflow
+
+Explicit entry points should state:
+
+- How the user triggers it.
+- Which `.trellis/` files to read.
+- Which scripts to run.
+- How to report after completion.
+
+If a command only repeats workflow rules, prefer making it reference/read `.trellis/workflow.md` instead of maintaining a second copy of the flow.
+
+## Common Paths
+
+| Platform | Entry directories |
+| --- | --- |
+| Claude Code | `.claude/skills/`, `.claude/commands/` |
+| Cursor | `.cursor/skills/`, `.cursor/commands/` |
+| OpenCode | `.opencode/skills/`, `.opencode/commands/` |
+| Codex | `.agents/skills/`, `.codex/skills/` |
+| GitHub Copilot | `.github/skills/`, `.github/prompts/` |
+| Kilo / Antigravity / Windsurf | workflows + skills |
+
+## Add A Project-Local Skill
+
+If the user wants to document team-private customizations, create a project-local skill, for example:
+
+```text
+.claude/skills/project-trellis-local/
+└── SKILL.md
+```
+
+For multi-platform projects, add equivalent versions in each platform skill directory, or use `.agents/skills/` on platforms that support the shared layer.
+
+## Notes
+
+- Do not mix every platform's syntax into one file.
+- Do not change only one platform entry point while claiming all platforms are supported.
+- Do not hide long-term engineering conventions inside a command; write them to `.trellis/spec/`.

.agents/skills/trellis-meta/references/customize-local/change-spec-structure.md

@@ -0,0 +1,83 @@
+# Change Local Spec Structure
+
+When the user wants to change the engineering conventions AI follows, add new spec layers, or adjust monorepo package mapping, edit `.trellis/spec/` and `.trellis/config.yaml`.
+
+## Read These Files First
+
+1. `.trellis/config.yaml`
+2. `.trellis/spec/`
+3. `.trellis/workflow.md` Phase 1.3 and Phase 3.3
+4. Current task `implement.jsonl` / `check.jsonl`
+
+## Common Needs
+
+| Need | Edit location |
+| --- | --- |
+| Add backend/frontend/docs/test spec layer | `.trellis/spec/<layer>/` or `.trellis/spec/<package>/<layer>/` |
+| Add shared thinking guides | `.trellis/spec/guides/` |
+| Adjust monorepo packages | `packages` in `.trellis/config.yaml` |
+| Change default package | `default_package` in `.trellis/config.yaml` |
+| Control spec scanning scope | `spec_scope` in `.trellis/config.yaml` |
+| Make a task read a new spec | Task `implement.jsonl` / `check.jsonl` |
+
+## Add A Spec Layer
+
+Single-repository example:
+
+```text
+.trellis/spec/security/
+├── index.md
+└── auth.md
+```
+
+Monorepo example:
+
+```text
+.trellis/spec/webapp/security/
+├── index.md
+└── auth.md
+```
+
+`index.md` should include:
+
+- What code this layer applies to.
+- Pre-Development Checklist.
+- Quality Check.
+- Links to specific guideline files.
+
+## Update Context
+
+Adding a spec does not mean every task automatically reads it. The current task must reference it in JSONL:
+
+```bash
+python ./.trellis/scripts/task.py add-context <task> implement ".trellis/spec/webapp/security/index.md" "Security conventions"
+python ./.trellis/scripts/task.py add-context <task> check ".trellis/spec/webapp/security/index.md" "Security review rules"
+```
+
+## Change Monorepo Packages
+
+Example `.trellis/config.yaml`:
+
+```yaml
+packages:
+  webapp:
+    path: apps/web
+  api:
+    path: apps/api
+default_package: webapp
+```
+
+After editing, run:
+
+```bash
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+Use this output to confirm AI can see the correct packages and spec layers.
+
+## Notes
+
+- Specs are user project conventions and can be changed according to project needs.
+- Do not put temporary task information into specs; put temporary information in the task.
+- Do not put long-term conventions only in agents or commands; preserve them in specs.
+- After changing spec structure, check whether existing task JSONL files still point to files that exist.

.agents/skills/trellis-meta/references/customize-local/change-task-lifecycle.md

@@ -0,0 +1,90 @@
+# Change Local Task Lifecycle
+
+Task lifecycle includes creation, start, context configuration, finish, archive, parent/child tasks, and lifecycle hooks. The default customization targets are `.trellis/tasks/`, `.trellis/config.yaml`, and `.trellis/scripts/`.
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. `.trellis/config.yaml`
+3. `.trellis/scripts/task.py`
+4. `.trellis/scripts/common/task_store.py`
+5. `.trellis/scripts/common/task_utils.py`
+6. The current task's `.trellis/tasks/<task>/task.json`
+
+## Common Needs And Edit Points
+
+| Need | Edit point |
+| --- | --- |
+| Automatically sync an external system after task creation | `hooks.after_create` in `.trellis/config.yaml`. |
+| Automatically update status after task start | `hooks.after_start` in `.trellis/config.yaml`. |
+| Run a script after task finish | `hooks.after_finish` in `.trellis/config.yaml`. |
+| Clean external resources after archive | `hooks.after_archive` in `.trellis/config.yaml`. |
+| Change default task fields | `.trellis/scripts/common/task_store.py`. |
+| Change task parsing/search | `.trellis/scripts/common/task_utils.py`. |
+| Change active task behavior | `.trellis/scripts/common/active_task.py`. |
+
+## lifecycle hooks
+
+`.trellis/config.yaml` supports:
+
+```yaml
+hooks:
+  after_create:
+    - "python .trellis/scripts/hooks/my_sync.py create"
+  after_start:
+    - "python .trellis/scripts/hooks/my_sync.py start"
+  after_finish:
+    - "python .trellis/scripts/hooks/my_sync.py finish"
+  after_archive:
+    - "python .trellis/scripts/hooks/my_sync.py archive"
+```
+
+Hook commands receive the `TASK_JSON_PATH` environment variable, pointing to the current task's `task.json`. Hook failures should usually warn, but not block the main task operation.
+
+## Change Task Fields
+
+If the user wants to add project-local fields, prefer putting them under `meta` in `task.json` to avoid breaking existing scripts' assumptions about standard fields.
+
+Example:
+
+```json
+"meta": {
+  "linearIssue": "ENG-123",
+  "risk": "high"
+}
+```
+
+If standard fields really need to change, inspect every local script that reads `task.json`.
+
+## Change Active Task
+
+Active task is session-level state stored in `.trellis/.runtime/sessions/`. Do not fall back to a global `.current-task` model. If the user wants to change active task behavior, edit:
+
+- `.trellis/scripts/common/active_task.py`
+- platform hooks or shell session bridges
+- active task descriptions in `.trellis/workflow.md`
+
+### `task.py create` Sets the Active Pointer
+
+`cmd_create` in `.trellis/scripts/common/task_store.py` calls `set_active_task` best-effort right after writing the new task directory. The behavior:
+
+- When the calling shell carries session identity (`TRELLIS_CONTEXT_ID` env var, or any platform-specific session env that `resolve_context_key` recognizes — see `active_task.py:_ENV_SESSION_KEYS`), the per-session pointer at `.trellis/.runtime/sessions/<context_key>.json` is rewritten to point at the new task. The task's `status=planning` and `[workflow-state:planning]` fires on the very next `UserPromptSubmit`.
+- When session identity is unavailable (raw CLI invocation outside an AI session, or a platform that doesn't propagate identity to shell), the task directory is still created and `status=planning` is still written, but the active pointer is left untouched. The user can attach the task later with `task.py start <dir>` once they're back in an AI session.
+
+This makes `[workflow-state:planning]` the live breadcrumb during the brainstorm and JSONL curation work that follows `task.py create`. The pre-R7 behavior left the breadcrumb stuck on `no_task` until `task.py start`, so the planning block was effectively dead text.
+
+If you fork `task.py` to add a new creation path (e.g. an external import that bypasses `cmd_create`), audit whether your path also calls `set_active_task`. Without that call, your created tasks will not surface as active. The full status writer table is in `.trellis/spec/cli/backend/workflow-state-contract.md`.
+
+## Modification Steps
+
+1. Confirm the current task with `python ./.trellis/scripts/task.py current --source`.
+2. Read the current task's `task.json` and confirm status and fields.
+3. For configuration needs, edit `.trellis/config.yaml` first.
+4. For script behavior needs, then edit `.trellis/scripts/`.
+5. If the AI flow changed, synchronize `.trellis/workflow.md`.
+
+## Do Not
+
+- Do not directly edit `.trellis/.runtime/sessions/` to "fix" business state.
+- Do not hard-code project-private fields into scripts; prefer `meta`.
+- Do not default to asking the user to fork Trellis CLI.

.agents/skills/trellis-meta/references/customize-local/change-workflow.md

@@ -0,0 +1,64 @@
+# Change Local Workflow
+
+When the user wants to change Trellis phases, next-action hints, whether to create tasks, whether to use sub-agents, or when to check/wrap up, edit `.trellis/workflow.md` first.
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. Entry files for the current platform, such as skills/commands/prompts/workflows
+3. The current task's `task.json` and `prd.md`
+
+## Common Needs And Edit Points
+
+| Need | Edit point |
+| --- | --- |
+| Change phase names or phase order | `Phase Index` and the corresponding Phase sections. |
+| Change whether to create a task when there is no task | `[workflow-state:no_task]` state block. |
+| Change the next step during planning | Phase 1 and `[workflow-state:planning]`. |
+| Change whether an agent is required during in_progress | Phase 2 and `[workflow-state:in_progress]`. |
+| Change wrap-up after completion | Phase 3 and `[workflow-state:completed]`. |
+| Change which skill a user intent triggers | `Skill Routing` table. |
+
+## Modification Steps
+
+1. Find the relevant section in `.trellis/workflow.md`.
+2. When changing rules, keep explicit trigger conditions and next actions.
+3. If adding or renaming a skill/agent, synchronize the corresponding files in platform directories.
+4. Workflow-state changes only need an edit to the `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The hook is parser-only — it reads whatever you put in the block. Keep the opening and closing tags' STATUS strings identical (`[workflow-state:foo]…[/workflow-state:foo]`); mismatched STATUS pairs are silently dropped.
+5. Make the AI reread `.trellis/workflow.md`; do not keep using rules from the old conversation.
+
+## Example: Relax Task Creation Requirements
+
+To change when task creation can be skipped, usually edit `[workflow-state:no_task]`:
+
+```md
+[workflow-state:no_task]
+Task is not required when the answer is a one-reply explanation, no files are changed, and no research is needed.
+[/workflow-state:no_task]
+```
+
+If the formal Phase 1 flow also needs to change, synchronize the Phase 1 section.
+
+## Example: One Platform Does Not Use Sub-Agents
+
+If the user wants only one platform to avoid sub-agents, first confirm whether that platform has a separate group in the workflow. Then change Phase 2 routing for that platform group instead of deleting all `trellis-implement` / `trellis-check` instructions across platforms.
+
+## `/trellis:continue` Route Table
+
+`/trellis:continue` resumes a task by deciding which phase step to load next. The decision combines `task.json.status` with the presence of artifacts inside the task directory. The mapping is fixed in the command itself; forks that add custom statuses must extend both the workflow.md tag block and this table.
+
+| `status` | Artifact state | Resume at |
+| --- | --- | --- |
+| `planning` | `prd.md` missing | Phase 1.1 (load `trellis-brainstorm`) |
+| `planning` | `prd.md` exists, `implement.jsonl` only has the seed `_example` row | Phase 1.3 (curate JSONL context) |
+| `planning` | `prd.md` exists, `implement.jsonl` curated | Phase 1.4 (run `task.py start`) |
+| `in_progress` | no implementation in conversation history | Phase 2.1 (`trellis-implement`) |
+| `in_progress` | implementation done, no `trellis-check` run | Phase 2.2 (`trellis-check`) |
+| `in_progress` | check passed | Phase 3.1 (verify quality + spec update) |
+| `completed` | task is still in active tree | Phase 3.5 (run `/trellis:finish-work` to archive) |
+
+When you add a custom status (e.g. `in-review`), add a `[workflow-state:in-review]` block in `.trellis/workflow.md` for the per-turn breadcrumb AND extend this route table — usually by editing the `/trellis:continue` command file (`.{platform}/commands/trellis/continue.md` or equivalent) to add a row that decides where to resume from. Without the route entry, `/trellis:continue` will fall through to a default branch and the user will not land on the step you intended.
+
+## Notes
+
+`.trellis/workflow.md` is the local project workflow, not an immutable template. The user can adapt it to team habits. After editing it, platform entry files may still contain old descriptions, so inspect them too.

.agents/skills/trellis-meta/references/customize-local/overview.md

@@ -0,0 +1,55 @@
+# Local Customization Overview
+
+This directory is for local AI working in a user project where Trellis was installed through npm and `trellis init` has already been run. The AI should modify generated `.trellis/` and platform directories inside the project, not Trellis CLI upstream source code.
+
+## First Determine What The User Actually Wants To Change
+
+| User wording | Read first |
+| --- | --- |
+| "Change the Trellis flow / phases / next prompt" | `change-workflow.md` |
+| "Change task creation, status, archive, or hooks" | `change-task-lifecycle.md` |
+| "AI did not read context / change injected content" | `change-context-loading.md` |
+| "A platform hook is not behaving as expected" | `change-hooks.md` |
+| "Change implement/check/research agent behavior" | `change-agents.md` |
+| "Add a skill/command/workflow/prompt" | `change-skills-or-commands.md` |
+| "Adjust the project spec structure" | `change-spec-structure.md` |
+| "Add team conventions and local notes" | `add-project-local-conventions.md` |
+
+## General Operation Order
+
+1. **Confirm platform and directories**: inspect which directories exist, such as `.claude/`, `.codex/`, `.cursor/`.
+2. **Confirm the current active task**: run `python ./.trellis/scripts/task.py current --source`.
+3. **Read the local source of truth**: prefer `.trellis/workflow.md`, `.trellis/config.yaml`, and relevant platform files.
+4. **Modify narrowly**: edit only files related to the user's request.
+5. **Synchronize semantics**: if a shared flow changes, check whether platform entry points also need changes; if a platform entry changes, check whether `.trellis/workflow.md` still agrees.
+
+## Local File Priority
+
+| Layer | Files |
+| --- | --- |
+| Workflow | `.trellis/workflow.md` |
+| Project configuration | `.trellis/config.yaml` |
+| Task material | `.trellis/tasks/<task>/` |
+| Project specs | `.trellis/spec/` |
+| Runtime scripts | `.trellis/scripts/` |
+| Platform integration | `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, and similar directories |
+| Shared skill | `.agents/skills/` |
+
+## Things Not To Do By Default
+
+- Do not edit the global npm install directory.
+- Do not edit `node_modules/@mindfoldhq/trellis`.
+- Do not assume the user has the Trellis GitHub repository.
+- Do not overwrite local files already modified by the user with default templates.
+- Do not put team project rules into public `trellis-meta`; project rules belong in `.trellis/spec/` or a local skill.
+
+## When To Inspect Upstream Source
+
+Switch to an upstream source-code perspective only when the user explicitly expresses one of these goals:
+
+- "I want to open a PR to Trellis"
+- "I want to change npm package publish contents"
+- "I want to fork Trellis"
+- "I want to modify the generation logic for `trellis init/update`"
+
+Otherwise, default to modifying local Trellis files inside the user project.

.agents/skills/trellis-meta/references/local-architecture/context-injection.md

@@ -0,0 +1,68 @@
+# Local Context Injection System
+
+Trellis context injection aims to make AI read the right files at the right time instead of relying on model memory. In a user project, injection is implemented by `.trellis/` scripts together with platform hooks, agents, and skills.
+
+## Injected Context Types
+
+| Type | Source | Purpose |
+| --- | --- | --- |
+| session context | `.trellis/scripts/get_context.py` | Current developer, git status, active task, active tasks, journal, packages. |
+| workflow context | `.trellis/workflow.md` | Current Trellis flow and next action. |
+| spec context | `.trellis/spec/` + task JSONL | Specs that must be followed during implementation/checking. |
+| task context | `.trellis/tasks/<task>/prd.md`, `info.md`, `research/` | Current task requirements, design, and research. |
+| platform context | Platform hooks/settings/agents | Lets different AI tools read the files above through their own mechanisms. |
+
+## session-start
+
+Platforms with session-start support inject a Trellis overview when a session starts, clears, compacts, or receives a similar event. Injected content usually includes:
+
+- workflow summary.
+- current task status.
+- active tasks.
+- spec index paths.
+- developer identity and git status.
+
+If the user feels the AI does not know the current task in a new session, first check whether the platform's session-start hook or equivalent mechanism is installed and running.
+
+## workflow-state
+
+workflow-state is a lightweight hint injected around each user turn. Based on current task status, it selects a block from `.trellis/workflow.md`, such as `no_task`, `planning`, `in_progress`, or `completed`.
+
+If the user wants to change "what the AI should do next in a given state," edit the corresponding state block in `.trellis/workflow.md` first.
+
+## sub-agent context
+
+Implement and check agents need task context. Trellis has two loading modes:
+
+1. **hook push**: a platform hook injects `prd.md` and the files referenced by `implement.jsonl` / `check.jsonl` before the agent starts.
+2. **agent pull**: the agent definition instructs the agent to read the active task, PRD, and JSONL context after startup.
+
+In both modes, JSONL files in the task directory are the key interface.
+
+## JSONL Reading Rules
+
+`implement.jsonl` and `check.jsonl` contain one JSON object per line:
+
+```jsonl
+{"file": ".trellis/spec/backend/index.md", "reason": "Backend rules"}
+```
+
+Readers should skip seed rows without a `file` field. When configuring JSONL, the AI should include only spec/research files, not pre-register code files that will be modified.
+
+## Active Task And Context Key
+
+Active task state lives in `.trellis/.runtime/sessions/` and is isolated per session. Hooks try to resolve the context key from platform events, environment variables, transcript paths, or `TRELLIS_CONTEXT_ID`.
+
+If shell commands cannot see the same context key, `task.py current --source` may report no active task. In that case, check whether the platform passes session identity into the shell instead of hand-writing a global current-task file.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Change session-start injected content | The platform's `session-start` hook or plugin file. |
+| Change per-turn workflow-state rules | `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The platform workflow-state hook parses these blocks verbatim and embeds no fallback text. |
+| Change how sub-agents read context | Platform agent definitions, the `inject-subagent-context` hook, or agent preludes. |
+| Change JSONL validation/display | `.trellis/scripts/common/task_context.py`. |
+| Change active task resolution | `.trellis/scripts/common/active_task.py`. |
+
+When modifying context injection, verify two things: new sessions can see the correct task, and sub-agents can see the correct PRD/spec/research.

.agents/skills/trellis-meta/references/local-architecture/generated-files.md

@@ -0,0 +1,80 @@
+# Local Files Generated After Init
+
+`trellis init` writes the Trellis runtime into the user project. Later, `trellis update` tries to update Trellis-managed template files, but it uses `.trellis/.template-hashes.json` to determine which files have already been modified by the user.
+
+This page only describes files that are visible and editable inside the user project.
+
+## `.trellis/`
+
+```text
+.trellis/
+├── workflow.md
+├── config.yaml
+├── .developer
+├── .version
+├── .template-hashes.json
+├── .runtime/
+├── scripts/
+├── spec/
+├── tasks/
+└── workspace/
+```
+
+| Path | Usually editable? | Notes |
+| --- | --- | --- |
+| `.trellis/workflow.md` | Yes | Local workflow documentation and AI routing rules. |
+| `.trellis/config.yaml` | Yes | Project configuration, hooks, packages, journal line limits, and related settings. |
+| `.trellis/spec/` | Yes | Project specs, intended to be updated regularly by users and AI. |
+| `.trellis/tasks/` | Yes | Task material and research artifacts, maintained by the task workflow. |
+| `.trellis/workspace/` | Yes | Session records, usually written by `add_session.py`. |
+| `.trellis/scripts/` | Carefully | Local runtime. It can be customized, but only after understanding the call chain. |
+| `.trellis/.runtime/` | No | Runtime state, usually written automatically by hooks/scripts. |
+| `.trellis/.developer` | Carefully | Current developer identity. |
+| `.trellis/.version` | No | Trellis version record used by update/migration logic. |
+| `.trellis/.template-hashes.json` | No | Template hash record. Do not hand-write business rules here. |
+
+## Platform Directories
+
+Different platforms generate different directories. Common categories:
+
+| Category | Example paths | Purpose |
+| --- | --- | --- |
+| hooks | `.claude/hooks/`, `.codex/hooks/`, `.cursor/hooks/` | Inject session context, workflow-state, and sub-agent context. |
+| settings | `.claude/settings.json`, `.codex/hooks.json`, `.qoder/settings.json` | Tell the platform when to run hooks or plugins. |
+| agents | `.claude/agents/`, `.codex/agents/`, `.kiro/agents/` | Define agents such as `trellis-research`, `trellis-implement`, and `trellis-check`. |
+| skills | `.claude/skills/`, `.agents/skills/`, `.qoder/skills/` | Skills that auto-trigger or can be read by AI. |
+| commands/prompts/workflows | `.cursor/commands/`, `.github/prompts/`, `.windsurf/workflows/` | Explicit user-invoked command or workflow entry points. |
+
+When modifying a platform directory, also confirm whether `.trellis/workflow.md` still describes the same flow.
+
+## Meaning Of Template Hashes
+
+`.trellis/.template-hashes.json` records the content hash from the last time Trellis wrote a template file. `trellis update` uses it to distinguish three cases:
+
+| Case | Update behavior |
+| --- | --- |
+| File was not modified by the user | It can be updated automatically. |
+| File was modified by the user | Prompt the user to overwrite, keep, or generate `.new`. |
+| File is no longer a current template | It may be deleted, renamed, or preserved according to migration rules. |
+
+When an AI customizes local Trellis files, it does not need to maintain hashes manually. It is normal for Trellis update to recognize the result as "modified by the user."
+
+## Local Customization Boundaries
+
+Editable by default:
+
+- `.trellis/workflow.md`
+- `.trellis/config.yaml`
+- `.trellis/spec/**`
+- `.trellis/scripts/**`
+- Platform hooks, settings, agents, skills, commands, prompts, and workflows
+
+Do not edit by default:
+
+- Global npm install directory
+- `node_modules/@mindfoldhq/trellis`
+- Trellis GitHub repository source code
+- Concrete state files under `.trellis/.runtime/**`
+- Hash contents inside `.trellis/.template-hashes.json`
+
+Switch to the Trellis CLI source-code perspective only when the user explicitly wants to contribute upstream.

.agents/skills/trellis-meta/references/local-architecture/overview.md

@@ -0,0 +1,51 @@
+# Local Trellis Architecture Overview
+
+`trellis-meta` is for user projects that have already run `trellis init`. The user's machine usually has only the npm-installed `trellis` command plus the Trellis files generated inside the project; it may not have the Trellis CLI source code.
+
+Therefore, when an AI uses this skill, the default customization target is local files inside the user project:
+
+- `.trellis/`: workflow, tasks, specs, memory, scripts, and runtime state.
+- Platform directories: `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, `.kiro/`, `.gemini/`, `.qoder/`, `.codebuddy/`, `.github/`, `.factory/`, `.pi/`, `.kilocode/`, `.agent/`, `.windsurf/`, and similar directories.
+- Shared skill layer: `.agents/skills/`.
+
+Do not default to guiding the user to fork the Trellis CLI repository. Treat upstream source code as the operating target only when the user explicitly says they want to change Trellis upstream source, publish an npm package, or contribute a PR.
+
+## Local System Model
+
+Trellis provides three layers inside a user project:
+
+1. **Workflow layer**: `.trellis/workflow.md` defines phases, routing, next actions, and prompt blocks.
+2. **Persistence layer**: `.trellis/tasks/`, `.trellis/spec/`, and `.trellis/workspace/` store tasks, specs, and session memory.
+3. **Platform integration layer**: hooks, settings, agents, skills, commands, prompts, and workflows in platform directories connect the Trellis workflow to different AI tools.
+
+All three layers live inside the user project, so an AI can read and modify them directly.
+
+## Core Paths
+
+| Path | Purpose |
+| --- | --- |
+| `.trellis/workflow.md` | Workflow phases, skill routing, and workflow-state prompt blocks. |
+| `.trellis/config.yaml` | Project configuration, task lifecycle hooks, monorepo package configuration, and journal configuration. |
+| `.trellis/spec/` | The user's project-specific coding conventions and thinking guides. |
+| `.trellis/tasks/` | Each task's PRD, technical notes, research files, and JSONL context. |
+| `.trellis/workspace/` | Per-developer journals and cross-session memory. |
+| `.trellis/scripts/` | Local Python runtime used by commands, hooks, and context injection. |
+| `.trellis/.runtime/` | Session-level runtime state, such as the current task pointer. |
+| `.trellis/.template-hashes.json` | Template hashes for Trellis-managed files, used by update to determine whether local files were modified by the user. |
+
+## AI Customization Principles
+
+1. **Find the local source of truth first**: Do not edit from memory. Read `.trellis/workflow.md`, `.trellis/config.yaml`, the relevant platform directory, and related task files first.
+2. **Edit the user project, not the npm package cache**: Modify generated files inside the project, not `node_modules` or the global npm install directory.
+3. **Keep platform files aligned with `.trellis/`**: If workflow routing changes, also check whether platform skills or commands still describe the same flow.
+4. **Put project-specific rules in `.trellis/spec/` or a local skill**: Do not put team conventions into `trellis-meta`.
+5. **Preserve user changes**: If a file was already modified locally, work from the current content instead of overwriting it with a default template.
+
+## How To Use This Directory
+
+- To understand which files exist after init, read `generated-files.md`.
+- To change phases, routing, or next actions, read `workflow.md`.
+- To change the task model, JSONL context, or active task behavior, read `task-system.md`.
+- To change coding convention injection, read `spec-system.md`.
+- To understand journals and cross-session memory, read `workspace-memory.md`.
+- To change hooks or sub-agent context loading, read `context-injection.md`.

.agents/skills/trellis-meta/references/local-architecture/spec-system.md

@@ -0,0 +1,102 @@
+# Local Spec System
+
+`.trellis/spec/` is the user's project-specific engineering spec library. Trellis is not about making AI memorize conventions; it injects relevant specs or requires the AI to read them at the right time.
+
+## Directory Model
+
+A common single-repository structure:
+
+```text
+.trellis/spec/
+├── backend/
+│   ├── index.md
+│   └── ...
+├── frontend/
+│   ├── index.md
+│   └── ...
+└── guides/
+    ├── index.md
+    └── ...
+```
+
+A common monorepo structure:
+
+```text
+.trellis/spec/
+├── cli/
+│   ├── backend/
+│   │   ├── index.md
+│   │   └── ...
+│   └── unit-test/
+│       ├── index.md
+│       └── ...
+├── docs-site/
+│   └── docs/
+│       ├── index.md
+│       └── ...
+└── guides/
+    ├── index.md
+    └── ...
+```
+
+`index.md` is the entry point for each layer. It should list the Pre-Development Checklist and Quality Check. Specific guidelines live in other Markdown files in the same directory.
+
+## Package Configuration
+
+`.trellis/config.yaml` can declare packages:
+
+```yaml
+packages:
+  cli:
+    path: packages/cli
+  docs-site:
+    path: docs-site
+    type: submodule
+default_package: cli
+```
+
+The AI can run:
+
+```bash
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+This command lists packages and spec layers for the current project. Use this output as the reference when configuring context JSONL.
+
+## How Specs Enter Tasks
+
+Before a task enters implementation, Phase 1.3 should write relevant specs into `implement.jsonl` / `check.jsonl`:
+
+```jsonl
+{"file": ".trellis/spec/cli/backend/index.md", "reason": "CLI backend conventions"}
+{"file": ".trellis/spec/cli/unit-test/conventions.md", "reason": "Test expectations"}
+```
+
+Sub-agents or platform preludes read these JSONL files and load the referenced specs. On platforms without sub-agent support, the AI should read the relevant specs directly according to the workflow.
+
+## What Specs Should Contain
+
+Specs should contain executable engineering conventions for the project, not generic best practices:
+
+- Where files should live.
+- How error handling should be expressed.
+- Input/output contracts for APIs, hooks, and commands.
+- Patterns that are forbidden.
+- Cases that require tests.
+- Project-specific pitfalls and how to avoid them.
+
+When the AI learns a new rule during implementation or debugging, it should update `.trellis/spec/` rather than only summarizing it in chat.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Add a new spec layer | `.trellis/spec/<package>/<layer>/index.md` and corresponding guideline files. |
+| Change monorepo spec mapping | `packages` / `default_package` / `spec_scope` in `.trellis/config.yaml`. |
+| Change which specs AI reads before implementation | The task's `implement.jsonl`. |
+| Change which specs AI reads during checking | The task's `check.jsonl`. |
+| Change when specs should be updated | Phase 3.3 in `.trellis/workflow.md` and the `trellis-update-spec` skill. |
+
+## Boundaries
+
+`.trellis/spec/` is the user's project specification, not a permanent copy of Trellis built-in templates. The AI should encourage the user to update it according to the actual project code instead of treating Trellis default templates as immutable documents.

.agents/skills/trellis-meta/references/local-architecture/task-system.md

@@ -0,0 +1,101 @@
+# Local Task System
+
+The Trellis task system is stored entirely under `.trellis/tasks/` in the user project. Each task is a directory containing requirements, context, research, state, and relationship information.
+
+## Task Directory Structure
+
+```text
+.trellis/tasks/
+├── 04-28-example-task/
+│   ├── task.json
+│   ├── prd.md
+│   ├── info.md
+│   ├── implement.jsonl
+│   ├── check.jsonl
+│   └── research/
+└── archive/
+    └── 2026-04/
+```
+
+| File | Purpose |
+| --- | --- |
+| `task.json` | Task metadata: status, assignee, priority, branch, parent/child tasks, and similar fields. |
+| `prd.md` | Requirements document; the most important business context during implementation. |
+| `info.md` | Optional technical design. |
+| `implement.jsonl` | List of spec/research files the implement agent must read first. |
+| `check.jsonl` | List of spec/research files the check agent must read first. |
+| `research/` | Research artifacts. Complex findings should not live only in chat. |
+
+## `task.json`
+
+`task.json` records task status and metadata. Common fields:
+
+| Field | Meaning |
+| --- | --- |
+| `id` / `name` / `title` | Task identity and title. |
+| `status` | Status such as `planning`, `in_progress`, `review`, or `completed`. |
+| `priority` | `P0`, `P1`, `P2`, `P3`. |
+| `creator` / `assignee` | Creator and assignee. |
+| `package` | Target package in a monorepo; may be empty. |
+| `branch` / `base_branch` | Working branch and PR target branch. |
+| `children` / `parent` | Parent/child task relationships. |
+| `commit` / `pr_url` | Commit and PR information after completion. |
+| `meta` | Extension fields. |
+
+The AI should not treat phase numbers as task status. Task progress is mainly determined by `status`, `prd.md`, whether JSONL context is configured, and the phase descriptions in `workflow.md`.
+
+## Active Task
+
+The user sees a "current task," but Trellis stores active task state per session.
+
+```text
+.trellis/.runtime/sessions/<context-key>.json
+```
+
+`task.py start` writes the task path into the runtime session file for the current session. `task.py current --source` shows the current task and where it came from. Different AI windows can point to different tasks without overwriting each other.
+
+If the platform or shell environment has no stable session identity, `task.py start` may be unable to set the active task. The AI should read the error, inspect the platform hook/session environment, and not fall back to a shared global pointer.
+
+## JSONL Context
+
+`implement.jsonl` and `check.jsonl` are context manifests for sub-agents to read first.
+
+Format:
+
+```jsonl
+{"file": ".trellis/spec/cli/backend/index.md", "reason": "Backend conventions"}
+{"file": ".trellis/tasks/04-28-example/research/api.md", "reason": "API research"}
+```
+
+Rules:
+
+- Include spec and research files.
+- Do not include code files that are about to be modified.
+- Do not treat temporary conclusions in chat as the only context.
+- Seed rows have no `file` field; they only prompt the AI to fill in real entries.
+
+## Common Commands
+
+```bash
+python ./.trellis/scripts/task.py create "<title>" --slug <slug>
+python ./.trellis/scripts/task.py start <task>
+python ./.trellis/scripts/task.py current --source
+python ./.trellis/scripts/task.py add-context <task> implement <file> <reason>
+python ./.trellis/scripts/task.py validate <task>
+python ./.trellis/scripts/task.py finish
+python ./.trellis/scripts/task.py archive <task>
+```
+
+When modifying the task system, the AI should prefer script commands to maintain structure. Edit JSON/Markdown directly only when scripts do not cover the need.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Change the default task template | `.trellis/scripts/common/task_store.py` and task creation instructions. |
+| Change status semantics | `.trellis/workflow.md`, workflow-state hook logic, and task usage conventions. |
+| Add task lifecycle actions | `hooks.after_*` in `.trellis/config.yaml`. |
+| Change context rules | Phase 1.3 in `.trellis/workflow.md` and related platform agent/hook instructions. |
+| Change archive policy | `.trellis/scripts/common/task_store.py` / `task_utils.py`. |
+
+These are local files in the user project. Do not default to editing Trellis CLI source code unless the user wants to contribute upstream.

.agents/skills/trellis-meta/references/local-architecture/workflow.md

@@ -0,0 +1,75 @@
+# Local Workflow System
+
+`.trellis/workflow.md` is the Trellis workflow source of truth inside the user project. An AI does not need Trellis source code to understand how the current project should move tasks forward; this file is enough.
+
+## File Responsibilities
+
+`.trellis/workflow.md` has three responsibilities:
+
+1. **Explain workflow phases**: Plan, Execute, Finish.
+2. **Define skill routing**: which skill or agent the AI should use when the user expresses a certain intent.
+3. **Provide workflow-state prompt blocks**: hooks can inject the prompt block for the current state into the conversation.
+
+## Current Phase Model
+
+```text
+Phase 1: Plan    -> clarify what to build, produce prd.md and required research
+Phase 2: Execute -> implement against the PRD and specs, then check
+Phase 3: Finish  -> final verification, preserve lessons, and wrap up
+```
+
+Each phase contains numbered steps, such as `1.3 Configure context`. These numbers are not runtime fields in `task.json`; they are workflow structure for AI and humans to read.
+
+## Skill Routing
+
+`workflow.md` separates routing by platform capability:
+
+- Platforms with sub-agent support: dispatch `trellis-implement` by default for implementation and `trellis-check` for checking.
+- Platforms without sub-agent support: the main session reads skills such as `trellis-before-dev`, then executes directly.
+
+When changing local AI behavior, update the routing descriptions in `workflow.md` first, then check whether the corresponding platform skill, command, or agent files need to stay in sync.
+
+## Workflow-State Prompt Blocks
+
+The bottom of `workflow.md` can contain state blocks like this:
+
+```text
+[workflow-state:no_task]
+...
+[/workflow-state:no_task]
+```
+
+Hooks choose the right block based on current task status and inject it into the conversation. Common states include:
+
+| State | Meaning |
+| --- | --- |
+| `no_task` | The current session has no active task. |
+| `planning` | The task is still in requirements, research, or context configuration. |
+| `in_progress` | The task has entered implementation and checking. |
+| `completed` | The task is complete and waiting for wrap-up or archive. |
+
+If the user wants to change policies such as "whether to create a task when there is no task," "when task creation may be skipped," or "whether sub-agents are required," edit these state blocks and the routing table above them.
+
+## Local Modification Patterns
+
+Common changes:
+
+| Goal | Edit point |
+| --- | --- |
+| Add a phase | Update the Phase Index, phase body, routing, and state blocks. |
+| Change task creation policy | Update the `no_task` state block and Phase 1 description. |
+| Change the default implementation/check path | Update Phase 2 and skill routing. |
+| Change the wrap-up flow | Update Phase 3 and `finish-work` related descriptions. Note the current split: Phase 3.4 = AI-driven code commits (batched, user-confirmed), Phase 3.5 = `/finish-work` (archive + record session). `/finish-work` refuses to run if the working tree is dirty. |
+| Change platform differences | Update routing descriptions grouped by platform. |
+
+After editing, make the AI reread `.trellis/workflow.md`; do not assume the flow from the old conversation is still valid.
+
+## Relationship To Platform Files
+
+`workflow.md` is the semantic center of the local workflow, but each platform can also have its own entry files:
+
+- skills, such as `trellis-brainstorm` and `trellis-check`.
+- commands/prompts/workflows, such as continue and finish-work.
+- hooks, such as session-start or workflow-state injection.
+
+If only `workflow.md` changes, platform entry files may still contain old language. When the user wants to change "what the AI actually does," also inspect the relevant platform directory.

.agents/skills/trellis-meta/references/local-architecture/workspace-memory.md

@@ -0,0 +1,71 @@
+# Local Workspace Memory System
+
+`.trellis/workspace/` stores cross-session memory. Its purpose is to let AI and humans understand what happened before across different windows and different days.
+
+## Directory Structure
+
+```text
+.trellis/workspace/
+├── index.md
+└── <developer>/
+    ├── index.md
+    ├── journal-1.md
+    └── journal-2.md
+```
+
+| File | Purpose |
+| --- | --- |
+| `.trellis/.developer` | Current developer identity. |
+| `.trellis/workspace/index.md` | Global workspace overview. |
+| `.trellis/workspace/<developer>/index.md` | Session index for a developer. |
+| `.trellis/workspace/<developer>/journal-N.md` | Session journal. |
+
+## Developer Identity
+
+Run this the first time:
+
+```bash
+python ./.trellis/scripts/init_developer.py <name>
+```
+
+This creates `.trellis/.developer` and the corresponding workspace directory. The AI should not change developer identity casually; if the identity is wrong, first confirm who is using the current project.
+
+## Journal
+
+`journal-N.md` records completed or partially completed work from each session. By default, each journal holds about 2000 lines; after that it rotates to the next file.
+
+Common command for recording a session:
+
+```bash
+python ./.trellis/scripts/add_session.py \
+  --title "Session title" \
+  --summary "What changed" \
+  --commit "abc1234"
+```
+
+Planning or review work without a commit can also be recorded by using `--no-commit` or an empty commit value.
+
+## Relationship Between Workspace Memory And Tasks
+
+| System | What it stores |
+| --- | --- |
+| `.trellis/tasks/` | Requirements, design, research, and state for a specific task. |
+| `.trellis/workspace/` | Work records across tasks and sessions. |
+| `.trellis/spec/` | Engineering knowledge preserved as long-term conventions. |
+
+If information is only useful for the current task, put it in the task directory.  
+If information describes what happened in the current session, put it in the workspace journal.  
+If information should be followed every time code is written in the future, put it in spec.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Change maximum journal lines | `max_journal_lines` in `.trellis/config.yaml`. |
+| Change session auto-commit message | `session_commit_message` in `.trellis/config.yaml`. |
+| Change session content format | `.trellis/scripts/add_session.py`. |
+| Change how workspace is displayed in context | `.trellis/scripts/common/session_context.py`. |
+
+## AI Usage Rules
+
+The AI should not treat workspace as the only source of truth. When resuming a task, read the current task first, then use workspace for background. After a task is complete, record important process notes in workspace; if long-term rules emerged, update spec.

.agents/skills/trellis-meta/references/platform-files/agents.md

@@ -0,0 +1,79 @@
+# Agents
+
+Trellis agent files define specialized roles. Common Trellis agents in a user project are:
+
+- `trellis-research`
+- `trellis-implement`
+- `trellis-check`
+
+File locations and formats differ by platform, but responsibility boundaries should stay consistent.
+
+## Agent Responsibilities
+
+| Agent | Responsibility |
+| --- | --- |
+| `trellis-research` | Investigate the question and write findings into the current task's `research/`. |
+| `trellis-implement` | Implement against `prd.md`, `info.md`, `implement.jsonl`, and related spec/research. |
+| `trellis-check` | Review changes, fix discovered issues, and run necessary checks. |
+
+Agent files should not become generic chat prompts. They should define input sources, write boundaries, whether code may be changed, and how results are reported.
+
+## Common Paths
+
+| Platform | Agent path |
+| --- | --- |
+| Claude Code | `.claude/agents/trellis-*.md` |
+| Cursor | `.cursor/agents/trellis-*.md` |
+| OpenCode | `.opencode/agents/trellis-*.md` |
+| Codex | `.codex/agents/trellis-*.toml` |
+| Kiro | `.kiro/agents/trellis-*.json` |
+| Gemini CLI | `.gemini/agents/trellis-*.md` |
+| Qoder | `.qoder/agents/trellis-*.md` |
+| CodeBuddy | `.codebuddy/agents/trellis-*.md` |
+| Factory Droid | `.factory/droids/trellis-*.md` |
+| Pi Agent | `.pi/agents/trellis-*.md` |
+
+GitHub Copilot agent/prompt support is provided by a combination of directories such as `.github/agents/`, `.github/prompts/`, and `.github/skills/`; inspect the files actually generated in the user project.
+
+Main-session workflow platforms such as Kilo, Antigravity, and Windsurf may not have Trellis sub-agent files. They usually rely on workflows/skills to guide the main session.
+
+## Two Context Loading Modes
+
+### hook push
+
+The platform hook injects task context before the agent starts. The agent file itself can focus more on responsibilities and boundaries.
+
+Common on platforms that support agent hooks.
+
+### agent pull
+
+The agent file instructs the agent to read after startup:
+
+- `python ./.trellis/scripts/task.py current --source`
+- current task `prd.md`
+- `info.md`
+- `implement.jsonl` or `check.jsonl`
+- spec/research files referenced by JSONL
+
+This mode fits platforms whose hooks cannot reliably rewrite sub-agent prompts.
+
+## Local Change Scenarios
+
+| User need | Edit location |
+| --- | --- |
+| Implement agent must follow extra restrictions | The platform's `trellis-implement` agent file. |
+| Check agent must run project-specific commands | `trellis-check` agent file, and `.trellis/spec/` if needed. |
+| Research agent must output a fixed format | `trellis-research` agent file. |
+| Agent cannot read task context | Agent prelude or `inject-subagent-context` hook. |
+| Add a project-specific agent | Platform agent directory + related workflow/command/skill entry point. |
+
+## Modification Principles
+
+1. **Keep responsibilities single-purpose**. Do not mix research, implement, and check responsibilities into one agent.
+2. **Specify the read order**. Agents must know to start from the active task and then find the PRD and JSONL.
+3. **Specify write boundaries**. Research usually only writes `research/`; implement can write code; check can fix issues.
+4. **Keep semantics synchronized in multi-platform projects**. If the user configured Claude, Codex, and Cursor together, decide whether changes to one platform's agent also need to be applied to others.
+
+## Do Not Default To Editing Upstream Templates
+
+Local AI should default to modifying platform agent files inside the user project. Discuss upstream template source only when the user explicitly wants to contribute the change back to Trellis.

.agents/skills/trellis-meta/references/platform-files/hooks-and-settings.md

@@ -0,0 +1,69 @@
+# Hooks And Settings
+
+Hooks/settings are the entry layer that connects a platform to Trellis. They decide which scripts, plugins, or extensions a platform runs for which events.
+
+## Settings Responsibilities
+
+settings/config files usually register:
+
+- session-start hook: injects a Trellis overview when a new session starts or context resets.
+- workflow-state hook: parses `[workflow-state:STATUS]` blocks from `.trellis/workflow.md` and emits the body matching the current task `status` on each user input. Parser-only; the script does not embed fallback content.
+- sub-agent context hook: injects task context when implementation/check/research agents start.
+- shell/session bridge: lets shell commands see the same Trellis session identity.
+- platform plugin or extension entry points.
+
+Common files:
+
+| Platform | settings/config |
+| --- | --- |
+| Claude Code | `.claude/settings.json` |
+| Cursor | `.cursor/hooks.json` |
+| Codex | `.codex/hooks.json`, `.codex/config.toml` |
+| OpenCode | `.opencode/package.json`, `.opencode/plugins/*` |
+| Kiro | `.kiro/hooks/` + platform config |
+| Gemini CLI | `.gemini/settings.json` |
+| Qoder | `.qoder/settings.json` |
+| CodeBuddy | `.codebuddy/settings.json` |
+| GitHub Copilot | `.github/copilot/hooks.json` |
+| Factory Droid | `.factory/settings.json` |
+| Pi Agent | `.pi/settings.json`, `.pi/extensions/trellis/` |
+
+Whether these files exist in a project depends on which `trellis init --<platform>` flags the user ran.
+
+## Hook Script Types
+
+| Script | Purpose |
+| --- | --- |
+| `session-start.py` | Generates session-start context. |
+| `inject-workflow-state.py` | Parses `[workflow-state:STATUS]` blocks in `.trellis/workflow.md` and emits the body matching the current task status. Falls back to `Refer to workflow.md for current step.` when no matching block exists. |
+| `inject-subagent-context.py` | Injects PRD, JSONL context, and related spec/research into sub-agents. |
+| `inject-shell-session-context.py` | Lets shell commands inherit Trellis session identity. |
+
+Not every platform has every hook. Do not copy files from another platform just because a platform lacks a hook; first confirm whether that platform supports the corresponding event.
+
+## Local Change Scenarios
+
+| User need | Edit location |
+| --- | --- |
+| AI should see more/less context in a new session | Platform `session-start` hook. |
+| Per-turn hint policy should change | `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The hook parses workflow.md verbatim — no script edit required. |
+| Sub-agent cannot read PRD/spec | `inject-subagent-context` hook or agent prelude. |
+| `task.py current` in shell has no active task | Shell/session bridge hook or platform environment variable configuration. |
+| Disable an automatic injection | The corresponding hook registration in settings/config. |
+
+## Modification Principles
+
+1. **Settings wire things up; hooks define behavior**. If only the hook changes, the platform may never call it. If only settings change, behavior may not change.
+2. **Confirm platform event names first**. Different platforms use different names for SessionStart, UserPromptSubmit, AgentSpawn, shell execution, and similar events.
+3. **Hooks read local `.trellis/`, not upstream source**. `.trellis/scripts/` and `.trellis/workflow.md` in the user project are the default targets.
+4. **Errors must be visible**. Hook failures should tell the user what was not injected instead of silently leaving the AI without context.
+
+## Troubleshooting Path
+
+If the user says "AI did not read Trellis state":
+
+1. Check whether the platform settings register the hook.
+2. Check whether the hook file exists.
+3. Manually run the `.trellis/scripts/get_context.py` or `task.py current --source` command that the hook depends on.
+4. Check whether active task state exists in `.trellis/.runtime/sessions/`.
+5. Check whether the platform shell passes session identity.

.agents/skills/trellis-meta/references/platform-files/overview.md

@@ -0,0 +1,59 @@
+# Platform Files Overview
+
+Trellis connects the same local architecture to different AI tools. `.trellis/` stores the shared runtime; platform directories store adapter files that define how each AI tool enters Trellis.
+
+When a local AI modifies Trellis, it should distinguish two file categories first:
+
+- **Shared files**: `.trellis/workflow.md`, `.trellis/tasks/`, `.trellis/spec/`, `.trellis/scripts/`.
+- **Platform files**: `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, `.kiro/`, `.gemini/`, `.qoder/`, `.codebuddy/`, `.github/`, `.factory/`, `.pi/`, `.kilocode/`, `.agent/`, `.windsurf/`, and similar directories.
+
+Platform files do not store business state. They let the corresponding AI tool read Trellis state, call Trellis scripts, and load Trellis skills/agents/hooks.
+
+## Platform File Categories
+
+| Category | Common paths | Purpose |
+| --- | --- | --- |
+| settings/config | `.claude/settings.json`, `.codex/hooks.json`, `.qoder/settings.json` | Register hooks, plugins, extensions, or platform behavior. |
+| hooks/plugins/extensions | `.claude/hooks/`, `.opencode/plugins/`, `.pi/extensions/` | Inject context at session start, user input, agent startup, shell execution, and similar events. |
+| agents | `.claude/agents/`, `.codex/agents/`, `.kiro/agents/` | Define `trellis-research`, `trellis-implement`, and `trellis-check`. |
+| skills | `.claude/skills/`, `.agents/skills/`, `.qoder/skills/` | Capability descriptions that auto-trigger or can be read on demand. |
+| commands/prompts/workflows | `.cursor/commands/`, `.github/prompts/`, `.windsurf/workflows/` | Entry points explicitly invoked by the user. |
+
+## Three Platform Integration Modes
+
+### 1. Hook / Extension Driven
+
+These platforms can trigger scripts or plugins on specific events and actively inject Trellis context into AI.
+
+Common capabilities:
+
+- session-start injection of a `.trellis/` overview.
+- workflow-state hints for each user turn.
+- PRD/spec/research injection when sub-agents start.
+- Shell commands inheriting session identity.
+
+To change "when the AI knows what," inspect hooks/plugins/extensions and settings first.
+
+### 2. Agent Prelude / Pull-Based
+
+Some platforms cannot reliably let hooks rewrite sub-agent prompts, so the agent file itself instructs the agent to read the active task, PRD, and JSONL context after startup.
+
+To change how sub-agents load context, inspect the agent files themselves.
+
+### 3. Main-Session Workflow
+
+Some platforms do not have Trellis sub-agent or hook capabilities. They rely on workflows/skills/commands to guide the main-session AI to read files, run scripts, and move tasks forward.
+
+To change behavior, inspect platform workflows/skills/commands and `.trellis/workflow.md`.
+
+## Local Modification Order
+
+When the user asks to customize behavior for a platform, the AI should inspect files in this order:
+
+1. Read `.trellis/workflow.md` to confirm the shared flow.
+2. Read the target platform's settings/config to see which hooks/agents/skills/commands are registered.
+3. Read the target platform's agents/skills/commands/hooks.
+4. Modify the local file closest to the user's need.
+5. If the change affects the shared flow, synchronize `.trellis/workflow.md` or `.trellis/spec/`.
+
+Do not modify only platform files and forget the shared workflow. Do not modify only `.trellis/workflow.md` and forget that platform entry points may still contain old descriptions.

.agents/skills/trellis-meta/references/platform-files/platform-map.md

@@ -0,0 +1,74 @@
+# Platform File Map
+
+This page lists common Trellis file locations in a user project by platform. Whether a platform directory exists in an actual project depends on which `trellis init --<platform>` commands the user ran.
+
+## Matrix
+
+| Platform | CLI flag | Main directory | Skill directory | Agent directory | Hooks/extensions |
+| --- | --- | --- | --- | --- | --- |
+| Claude Code | `--claude` | `.claude/` | `.claude/skills/` | `.claude/agents/` | `.claude/hooks/` + `.claude/settings.json` |
+| Cursor | `--cursor` | `.cursor/` | `.cursor/skills/` | `.cursor/agents/` | `.cursor/hooks.json` + `.cursor/hooks/` |
+| OpenCode | `--opencode` | `.opencode/` | `.opencode/skills/` | `.opencode/agents/` | `.opencode/plugins/` |
+| Codex | `--codex` | `.codex/` | `.agents/skills/` | `.codex/agents/` | `.codex/hooks/` + `.codex/hooks.json` |
+| Kilo | `--kilo` | `.kilocode/` | `.kilocode/skills/` | Usually none | `.kilocode/workflows/` |
+| Kiro | `--kiro` | `.kiro/` | `.kiro/skills/` | `.kiro/agents/` | `.kiro/hooks/` |
+| Gemini CLI | `--gemini` | `.gemini/` | `.agents/skills/` | `.gemini/agents/` | `.gemini/settings.json` + `.gemini/hooks/` |
+| Antigravity | `--antigravity` | `.agent/` | `.agent/skills/` | Usually none | `.agent/workflows/` |
+| Windsurf | `--windsurf` | `.windsurf/` | `.windsurf/skills/` | Usually none | `.windsurf/workflows/` |
+| Qoder | `--qoder` | `.qoder/` | `.qoder/skills/` | `.qoder/agents/` | `.qoder/hooks/` + `.qoder/settings.json` |
+| CodeBuddy | `--codebuddy` | `.codebuddy/` | `.codebuddy/skills/` | `.codebuddy/agents/` | `.codebuddy/hooks/` + `.codebuddy/settings.json` |
+| GitHub Copilot | `--copilot` | `.github/` | `.github/skills/` | `.github/agents/` | `.github/copilot/hooks/` + prompts |
+| Factory Droid | `--droid` | `.factory/` | `.factory/skills/` | `.factory/droids/` | `.factory/hooks/` + settings |
+| Pi Agent | `--pi` | `.pi/` | `.pi/skills/` | `.pi/agents/` | `.pi/extensions/trellis/` + `.pi/settings.json` |
+
+## Capability Groups
+
+### Trellis Sub-Agent Support
+
+These platforms usually have `trellis-research`, `trellis-implement`, and `trellis-check` files:
+
+- Claude Code
+- Cursor
+- OpenCode
+- Codex
+- Kiro
+- Gemini CLI
+- Qoder
+- CodeBuddy
+- GitHub Copilot
+- Factory Droid
+- Pi Agent
+
+When changing implementation/check/research behavior, look for the corresponding platform agent files first.
+
+### Main-Session Workflow Platforms
+
+These platforms rely more on workflows/skills to guide the main session:
+
+- Kilo
+- Antigravity
+- Windsurf
+
+When changing behavior, inspect workflows and skills first. Do not assume Trellis sub-agents exist.
+
+### Shared `.agents/skills/`
+
+Codex writes the shared `.agents/skills/` layer. Some tools that support agentskills.io can also read this directory. If the user wants multiple compatible tools to share one skill, consider `.agents/skills/` first, but do not assume every platform reads it.
+
+## Decision Rules When Modifying Platform Files
+
+1. User specified a platform: modify only that platform directory unless shared workflow/spec files must also change.
+2. User says "all platforms should do this": synchronize equivalent entry points platform by platform; do not modify only one directory.
+3. User only says "my AI": inspect the configuration directories that actually exist in the project and infer the current AI platform.
+4. User wants project rules: prefer `.trellis/spec/` or a project-local skill.
+5. User wants Trellis behavior: edit `.trellis/workflow.md` plus platform hooks/agents/skills/commands.
+
+## When Paths Differ
+
+Platform ecosystems change, and user projects may already be customized. If this table disagrees with local files, use the actual settings/config in the user project as authoritative:
+
+- Check the hook that settings registers.
+- Check the script that a command/prompt/workflow points to.
+- Judge behavior by the read rules currently written in the agent file.
+
+Do not delete a custom file just because it is not listed in this path table.

.agents/skills/trellis-meta/references/platform-files/skills-and-commands.md

@@ -0,0 +1,83 @@
+# Skills, Commands, Prompts, And Workflows
+
+Skills and commands are textual entry points for user interaction with Trellis. Different platforms use different names, but their core purpose is the same: tell the AI how to enter the Trellis flow when the user expresses a certain intent.
+
+## Conceptual Differences
+
+| Type | Trigger mode | Best for |
+| --- | --- | --- |
+| skill | AI auto-match or explicit user mention | Long-term capabilities, workflow rules, modification guides. |
+| command | Explicit user invocation | Clear operation entry points such as continue and finish-work. |
+| prompt | Explicit user invocation or platform selection | Similar to command, but in a platform prompt format. |
+| workflow | Explicit user selection or platform auto-match | Guides the main session when no sub-agent/hook exists. |
+
+Trellis workflow skills usually share one semantic set: brainstorm, before-dev, check, update-spec, break-loop. Multi-file built-in skills such as `trellis-meta` use layered references.
+
+## Common Paths
+
+| Platform | Common entries |
+| --- | --- |
+| Claude Code | `.claude/skills/`, `.claude/commands/` |
+| Cursor | `.cursor/skills/`, `.cursor/commands/` |
+| OpenCode | `.opencode/skills/`, `.opencode/commands/` |
+| Codex | `.agents/skills/`, `.codex/skills/` |
+| Kilo | `.kilocode/skills/`, `.kilocode/workflows/` |
+| Kiro | `.kiro/skills/` |
+| Gemini CLI | `.agents/skills/`, `.gemini/commands/` |
+| Antigravity | `.agent/skills/`, `.agent/workflows/` |
+| Windsurf | `.windsurf/skills/`, `.windsurf/workflows/` |
+| Qoder | `.qoder/skills/`, `.qoder/commands/` |
+| CodeBuddy | `.codebuddy/skills/`, `.codebuddy/commands/` |
+| GitHub Copilot | `.github/skills/`, `.github/prompts/` |
+| Factory Droid | `.factory/skills/`, `.factory/commands/` |
+| Pi Agent | `.pi/skills/` |
+
+In a user project, use the files actually generated by init as authoritative.
+
+## Skill Structure
+
+A common skill is a directory:
+
+```text
+trellis-meta/
+├── SKILL.md
+└── references/
+```
+
+`SKILL.md` should tell the AI:
+
+- When to use this skill.
+- Which reference to read first for the current task.
+- What not to do.
+
+References hold longer explanations so the entry file does not contain everything.
+
+## Command/Prompt/Workflow Structure
+
+Commands, prompts, and workflows are usually single files. Their content should include:
+
+- When to use it.
+- Which `.trellis/` files to read.
+- Which scripts to run.
+- How to report after completion.
+
+They should not store task state; task state belongs in `.trellis/tasks/` and `.trellis/.runtime/`.
+
+## Local Change Scenarios
+
+| User need | Edit location |
+| --- | --- |
+| Change AI auto-trigger rules | The corresponding skill's frontmatter description. |
+| Change user command behavior | The corresponding command/prompt/workflow file. |
+| Add a project-local skill | Platform skill directory, or shared `.agents/skills/`. |
+| Let multiple platforms share one capability | Write equivalent skills in each platform skill directory, or use the `.agents/skills/` shared layer on platforms that support it. |
+| Change finish/continue entry points | Platform commands/prompts/workflows. |
+
+## Modification Principles
+
+1. **Keep entry files short; references carry long content**. This matters especially for multi-file skills like `trellis-meta`.
+2. **Make trigger descriptions specific**. A description that is too broad can mis-trigger; one that is too narrow may not trigger.
+3. **Keep the same semantics consistent across platforms**. File formats can differ, but behavior descriptions should match.
+4. **Put project-specific capabilities in local skills**. Do not put team-private flows into public `trellis-meta`.
+
+If the user only wants local AI to know one more project rule, usually create a project-local skill or update `.trellis/spec/` instead of changing a Trellis built-in workflow skill.

.agents/skills/trellis-spec-bootstarp/SKILL.md

@@ -0,0 +1,41 @@
+---
+name: trellis-spec-bootstarp
+description: "Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder text."
+---
+
+# Trellis Spec Bootstarp
+
+Use this skill to create or refresh `.trellis/spec/` guidelines from the real codebase. One capable agent owns the full loop: analyze the repository, choose the spec boundaries, write the docs, and verify the result. The workflow does not depend on a specific host, CLI, or agent brand.
+
+## Workflow
+
+1. Confirm Trellis is initialized and inspect the current `.trellis/spec/` tree.
+2. Analyze the repository architecture with the best available tools: GitNexus, ABCoder, language tooling, and direct source reads.
+3. Decompose the spec work by package and layer only when that reflects the actual codebase.
+4. Fill or reshape the spec files with concrete patterns, file paths, examples, and anti-patterns from the project.
+5. Verify that the final specs are internally consistent and contain no template placeholders.
+
+## Reference Routing
+
+| Need | Read |
+|------|------|
+| Repository architecture analysis | [references/repository-analysis.md](references/repository-analysis.md) |
+| Spec work decomposition and task planning | [references/spec-task-planning.md](references/spec-task-planning.md) |
+| Writing high-signal Trellis spec files | [references/spec-writing.md](references/spec-writing.md) |
+| GitNexus and ABCoder MCP setup | [references/mcp-setup.md](references/mcp-setup.md) |
+
+## Operating Rules
+
+- Treat templates as starting points, not contracts. Delete, rename, split, or add spec files when the repository calls for it.
+- Prefer source-backed rules over generic advice. Every important recommendation should point at a real file or repeated local pattern.
+- Keep execution single-owner by default. Optional helper agents are an implementation detail, not a requirement or user-visible dependency.
+- Do not write platform-specific instructions unless the target project already standardizes on that platform.
+- Do not leave placeholder text, empty headings, or copied boilerplate in `.trellis/spec/`.
+
+## Done Criteria
+
+- `.trellis/spec/` describes the project as it exists now.
+- Each relevant package or layer has practical coding guidance with real examples.
+- Non-applicable template sections are removed.
+- `index.md` files match the final spec file set.
+- Any required setup or analysis assumptions are documented in the relevant spec or task notes.

.agents/skills/trellis-spec-bootstarp/references/mcp-setup.md

@@ -0,0 +1,90 @@
+# MCP Setup
+
+GitNexus and ABCoder are recommended when bootstrapping Trellis specs because they expose architecture and AST context to the agent. They are tool choices, not platform requirements. Configure them through whatever MCP mechanism your agent host provides.
+
+## GitNexus
+
+GitNexus builds a code knowledge graph from the repository. Use it for module boundaries, execution flows, dependency relationships, blast radius, and graph queries.
+
+### Install and Index
+
+```bash
+# Run from the repository root.
+npx gitnexus analyze
+
+# Check index status.
+npx gitnexus status
+
+# Re-index after code changes when the analysis is stale.
+npx gitnexus analyze
+```
+
+The index is written to `.gitnexus/`. Keep embeddings only if the project already uses them; otherwise a normal index is enough for spec bootstrapping.
+
+### MCP Server Command
+
+Use this server command in the host's MCP configuration:
+
+```bash
+npx -y gitnexus mcp
+```
+
+### Useful Tools
+
+| Tool | Purpose |
+|------|---------|
+| `gitnexus_query` | Find execution flows and functional areas by concept |
+| `gitnexus_context` | Inspect callers, callees, references, and process participation for a symbol |
+| `gitnexus_impact` | Understand blast radius before changing a symbol |
+| `gitnexus_detect_changes` | Check changed symbols and affected flows before finishing |
+| `gitnexus_cypher` | Run direct graph queries |
+| `gitnexus_list_repos` | List indexed repositories |
+
+## ABCoder
+
+ABCoder parses code into UniAST and gives precise package, file, and node-level structure. Use it for signatures, type shapes, implementations, dependencies, and reverse references.
+
+### Install
+
+```bash
+go install github.com/cloudwego/abcoder@latest
+abcoder --help
+```
+
+### Parse Repositories
+
+```bash
+abcoder parse /absolute/path/to/package \
+  --lang typescript \
+  --name package-name \
+  --output ~/abcoder-asts
+```
+
+For monorepos, parse each package with a stable `--name` so task notes can reference the same repository names.
+
+### MCP Server Command
+
+Use this server command in the host's MCP configuration:
+
+```bash
+abcoder mcp ~/abcoder-asts
+```
+
+### Useful Tools
+
+| Tool | Layer | Purpose |
+|------|-------|---------|
+| `list_repos` | 1 | List parsed repositories |
+| `get_repo_structure` | 2 | Inspect packages and files |
+| `get_package_structure` | 3 | Inspect nodes within a package |
+| `get_file_structure` | 3 | Inspect functions, classes, types, and signatures in a file |
+| `get_ast_node` | 4 | Retrieve code, dependencies, references, and implementations |
+
+## Verification
+
+After configuration, verify from the agent host that both MCP servers are visible. Then run one simple query against each server before starting the spec writing pass.
+
+```bash
+ls .gitnexus/meta.json
+ls ~/abcoder-asts/*.json
+```

.agents/skills/trellis-spec-bootstarp/references/repository-analysis.md

@@ -0,0 +1,59 @@
+# Repository Analysis
+
+The goal is to discover the project's real architecture before writing rules. Do not start from generic spec templates and fill blanks. Start from the code, then let the spec structure follow.
+
+## Analysis Order
+
+1. Read the existing `.trellis/spec/` tree and note which files are templates, outdated, or already project-specific.
+2. Inspect package manifests, build scripts, workspace config, and top-level documentation to identify packages and runtime layers.
+3. Use GitNexus for execution flows, module clusters, dependency hubs, and impact-sensitive areas.
+4. Use ABCoder or language-native tooling for exact signatures, types, class boundaries, and implementation examples.
+5. Read representative source and test files directly before turning any finding into a spec rule.
+
+## What To Capture
+
+| Area | Questions |
+|------|-----------|
+| Package boundaries | What does each package own? What imports cross boundaries? |
+| Runtime layers | Which code is CLI, backend, frontend, worker, shared library, test-only, or tooling? |
+| Core abstractions | Which types, services, stores, commands, routes, or adapters define the system shape? |
+| Data flow | Where does user input enter, how is it validated, and where does state persist? |
+| Error handling | How are failures represented, logged, surfaced, and tested? |
+| Configuration | Where do defaults, environment config, generated files, and templates live? |
+| Tests | Which test styles are trusted examples for new work? |
+
+## GitNexus Usage
+
+Start broad, then inspect specific symbols:
+
+```text
+gitnexus_query({query: "CLI command execution flow"})
+gitnexus_query({query: "template generation and migration"})
+gitnexus_context({name: "SymbolName"})
+gitnexus_cypher({query: "MATCH (n)-[r]->(m) RETURN n.name, type(r), m.name LIMIT 30"})
+```
+
+Use GitNexus results to find important files and flows. Do not quote graph output as the final authority until you have checked the relevant source files.
+
+## ABCoder Usage
+
+Use ABCoder when the spec needs exact code shapes:
+
+```text
+list_repos()
+get_repo_structure({repo_name: "package-name"})
+get_file_structure({repo_name: "package-name", file_path: "src/example.ts"})
+get_ast_node({repo_name: "package-name", node_ids: [{mod_path: "...", pkg_path: "...", name: "SymbolName"}]})
+```
+
+ABCoder is most valuable for documenting constructor patterns, function signatures, type contracts, and reference chains.
+
+## Analysis Notes
+
+Keep short notes while analyzing. The notes should include:
+
+- Package or layer name.
+- Files that define the local pattern.
+- Rules the spec should teach.
+- Anti-patterns found in old code, comments, tests, or migration paths.
+- Spec files that should be created, deleted, renamed, or merged.

.agents/skills/trellis-spec-bootstarp/references/spec-task-planning.md

@@ -0,0 +1,61 @@
+# Spec Task Planning
+
+Use a single agent as the default execution model. The agent may create Trellis tasks for traceability, but the skill should not require a specific platform, CLI, or parallel worker model.
+
+## Decomposition
+
+Create spec work units around real ownership boundaries:
+
+- One package when a package has its own conventions.
+- One layer when the same package has distinct frontend, backend, CLI, worker, or shared-library rules.
+- One cross-cutting guide when a pattern spans packages and is not owned by one layer.
+
+Avoid artificial decomposition. A small library usually needs one focused spec pass, not several tasks.
+
+## Task Shape
+
+When a Trellis task is useful, write a concise PRD with these sections:
+
+```markdown
+# Fill <package-or-layer> Trellis Specs
+
+## Goal
+Write project-specific `.trellis/spec/` guidance for <scope>.
+
+## Scope
+- Spec directory:
+- Source directories to inspect:
+- Tests to inspect:
+- Out of scope:
+
+## Architecture Context
+Summarize the concrete findings from repository analysis.
+
+## Files To Create Or Update
+- `.trellis/spec/.../index.md`
+- `.trellis/spec/.../<topic>.md`
+
+## Rules
+- Adapt the spec file set to the real codebase.
+- Use real source examples with file paths.
+- Remove template-only sections that do not apply.
+- Do not modify product source code unless the task explicitly asks for it.
+
+## Acceptance Criteria
+- [ ] Specs contain concrete examples and anti-patterns from the repository.
+- [ ] No placeholder text remains.
+- [ ] Index files match the final spec files.
+- [ ] Claims are backed by source files, tests, or project docs.
+```
+
+## Optional Helper Agents
+
+If the host supports subagents, helpers can inspect independent packages or run verification. They are optional. The main agent still owns integration and final quality.
+
+Helper tasks must have clear ownership:
+
+- Read-only research tasks may inspect any source needed for the assigned scope.
+- Write tasks should own disjoint spec directories.
+- Verification tasks should check placeholder removal, broken links, and consistency.
+
+Do not encode helper-agent names, vendor-specific commands, or platform-specific routing in the skill. Put only the required work and acceptance criteria in the task.

.agents/skills/trellis-spec-bootstarp/references/spec-writing.md

@@ -0,0 +1,70 @@
+# Spec Writing
+
+Trellis specs are coding guidance for future agents. They should explain how to work in this repository, not how a generic project might be organized.
+
+## Write From Evidence
+
+Each important rule should be backed by one of these:
+
+- A source file that demonstrates the preferred pattern.
+- A test file that shows expected behavior.
+- A project document that defines the convention.
+- A repeated pattern across multiple files.
+
+Use short snippets only when they make the rule clearer. Prefer linking to the file path and naming the symbol or behavior.
+
+## File Structure
+
+Keep the spec tree aligned with the project:
+
+- Keep `index.md` as the navigation file for the spec directory.
+- Split topics when developers would look for them independently.
+- Merge topics when separate files would repeat the same rule.
+- Delete template files that do not apply.
+- Add new files for important local patterns the template missed.
+
+## Content Standards
+
+Good spec sections include:
+
+- When the rule applies.
+- The local pattern to follow.
+- The source or test files that prove the pattern.
+- Common mistakes or anti-patterns.
+- Verification commands or checks when they are specific and reliable.
+
+Avoid:
+
+- Placeholder prose.
+- Generic framework advice.
+- Tool instructions that only work in one agent host.
+- Long copied code blocks.
+- Rules based on a single accidental implementation detail.
+
+## Example Shape
+
+```markdown
+## Command Handlers
+
+Command handlers should keep argument parsing, validation, and side effects separate. The local pattern is:
+
+- Parse CLI flags at the command boundary.
+- Convert raw inputs into typed task options before invoking core logic.
+- Keep filesystem writes in the command or service layer, not in template helpers.
+
+Reference files:
+- `packages/cli/src/commands/example.ts`
+- `packages/cli/test/commands/example.test.ts`
+
+Avoid passing raw `process.argv` or unvalidated config objects into shared helpers.
+```
+
+## Final Pass
+
+Before finishing:
+
+```bash
+grep -R "To be filled\\|TODO: fill\\|placeholder" .trellis/spec
+```
+
+Also check links, index files, and whether any spec still describes a template rather than this repository.

.agents/skills/trellis-start/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: trellis-start
+description: "Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/. Classifies incoming tasks and routes to brainstorm, direct edit, or task workflow. Use when beginning a new coding session, resuming work, starting a new task, or re-establishing project context."
+---
+
+# Start Session
+
+Initialize a Trellis-managed development session. This platform has no session-start hook, so manually load the equivalent context by following these steps (each one mirrors a section the hook would otherwise inject).
+
+---
+
+## Step 1: Current state
+Identity, git status, current task, active tasks, journal location.
+
+```bash
+python ./.trellis/scripts/get_context.py
+```
+
+If this output includes a line beginning `Trellis update available:`, copy the full line verbatim when summarizing session context. Do not shorten operational command hints.
+
+## Step 2: Workflow overview
+Phase Index + skill routing table + DO-NOT-skip rules.
+
+```bash
+python ./.trellis/scripts/get_context.py --mode phase
+```
+
+Full guide in `.trellis/workflow.md` (read on demand).
+
+## Step 3: Guideline indexes
+Discover packages + spec layers, then read each relevant index file.
+
+```bash
+python ./.trellis/scripts/get_context.py --mode packages
+cat .trellis/spec/guides/index.md
+cat .trellis/spec/<package>/<layer>/index.md   # for each relevant layer
+```
+
+Index files list the specific guideline docs to read when you actually start coding.
+
+## Step 4: Decide next action
+From Step 1 you know the current task. Check the task directory:
+
+- **Active task + `prd.md` exists** → Phase 2 step 2.1. Load the step detail:
+  ```bash
+  python ./.trellis/scripts/get_context.py --mode phase --step 2.1 --platform codex
+  ```
+- **Active task + no `prd.md`** → Phase 1.1. Load the `trellis-brainstorm` skill.
+- **No active task** → when the user describes multi-step work, load the `trellis-brainstorm` skill to clarify requirements, then create a task via `task.py create`. For simple one-off questions or trivial edits, skip this and just answer directly — no task needed.
+
+---
+
+## Skill routing (quick reference)
+
+| User intent | Skill |
+|---|---|
+| New feature / unclear requirements | `trellis-brainstorm` |
+| About to write code | `trellis-before-dev` |
+| Done coding / quality check | `trellis-check` |
+| Stuck / fixed same bug multiple times | `trellis-break-loop` |
+| Learned something worth capturing | `trellis-update-spec` |
+
+Full rules + anti-rationalization table in `.trellis/workflow.md`.

.agents/skills/trellis-update-spec/SKILL.md

@@ -0,0 +1,356 @@
+---
+name: trellis-update-spec
+description: "Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions."
+---
+
+# Update Code-Spec - Capture Executable Contracts
+
+When you learn something valuable (from debugging, implementing, or discussion), use this to update the relevant code-spec documents.
+
+**Timing**: After completing a task, fixing a bug, or discovering a new pattern
+
+---
+
+## Code-Spec First Rule (CRITICAL)
+
+In this project, "spec" for implementation work means **code-spec**:
+- Executable contracts (not principle-only text)
+- Concrete signatures, payload fields, env keys, and boundary behavior
+- Testable validation/error behavior
+
+If the change touches infra or cross-layer contracts, code-spec depth is mandatory.
+
+### Mandatory Triggers
+
+Apply code-spec depth when the change includes any of:
+- New/changed command or API signature
+- Cross-layer request/response contract change
+- Database schema/migration change
+- Infra integration (storage, queue, cache, secrets, env wiring)
+
+### Mandatory Output (7 Sections)
+
+For triggered tasks, include all sections below:
+1. Scope / Trigger
+2. Signatures (command/API/DB)
+3. Contracts (request/response/env)
+4. Validation & Error Matrix
+5. Good/Base/Bad Cases
+6. Tests Required (with assertion points)
+7. Wrong vs Correct (at least one pair)
+
+---
+
+## When to Update Code-Specs
+
+| Trigger | Example | Target Spec |
+|---------|---------|-------------|
+| **Implemented a feature** | Added a new integration or module | Relevant spec file |
+| **Made a design decision** | Chose extensibility pattern over simplicity | Relevant spec + "Design Decisions" section |
+| **Fixed a bug** | Found a subtle issue with error handling | Relevant spec (e.g., error-handling docs) |
+| **Discovered a pattern** | Found a better way to structure code | Relevant spec file |
+| **Hit a gotcha** | Learned that X must be done before Y | Relevant spec + "Common Mistakes" section |
+| **Established a convention** | Team agreed on naming pattern | Quality guidelines |
+| **New thinking trigger** | "Don't forget to check X before doing Y" | `guides/*.md` (as a checklist item) |
+
+**Key Insight**: Code-spec updates are NOT just for problems. Every feature implementation contains design decisions and contracts that future AI/developers need to execute safely.
+
+---
+
+## Spec Structure Overview
+
+```
+.trellis/spec/
+├── <layer>/           # Per-layer coding standards (e.g., backend/, frontend/, api/)
+│   ├── index.md       # Overview and links
+│   └── *.md           # Topic-specific guidelines
+└── guides/            # Thinking checklists (NOT coding specs!)
+    ├── index.md       # Guide index
+    └── *.md           # Topic-specific guides
+```
+
+### CRITICAL: Code-Spec vs Guide - Know the Difference
+
+| Type | Location | Purpose | Content Style |
+|------|----------|---------|---------------|
+| **Code-Spec** | `<layer>/*.md` | Tell AI "how to implement safely" | Signatures, contracts, matrices, cases, test points |
+| **Guide** | `guides/*.md` | Help AI "what to think about" | Checklists, questions, pointers to specs |
+
+**Decision Rule**: Ask yourself:
+
+- "This is **how to write** the code" → Put in a spec layer directory
+- "This is **what to consider** before writing" → Put in `guides/`
+
+**Example**:
+
+| Learning | Wrong Location | Correct Location |
+|----------|----------------|------------------|
+| "Use API X not API Y for this task" | ❌ `guides/` (too specific for a thinking guide) | ✅ Relevant spec file (concrete convention) |
+| "Remember to check X when doing Y" | ❌ Spec file (too abstract for a spec) | ✅ `guides/` (thinking checklist) |
+
+**Guides should be short checklists that point to specs**, not duplicate the detailed rules.
+
+---
+
+## Update Process
+
+### Step 1: Identify What You Learned
+
+Answer these questions:
+
+1. **What did you learn?** (Be specific)
+2. **Why is it important?** (What problem does it prevent?)
+3. **Where does it belong?** (Which spec file?)
+
+### Step 2: Classify the Update Type
+
+| Type | Description | Action |
+|------|-------------|--------|
+| **Design Decision** | Why we chose approach X over Y | Add to "Design Decisions" section |
+| **Project Convention** | How we do X in this project | Add to relevant section with examples |
+| **New Pattern** | A reusable approach discovered | Add to "Patterns" section |
+| **Forbidden Pattern** | Something that causes problems | Add to "Anti-patterns" or "Don't" section |
+| **Common Mistake** | Easy-to-make error | Add to "Common Mistakes" section |
+| **Convention** | Agreed-upon standard | Add to relevant section |
+| **Gotcha** | Non-obvious behavior | Add warning callout |
+
+### Step 3: Read the Target Code-Spec
+
+Before editing, read the current code-spec to:
+- Understand existing structure
+- Avoid duplicating content
+- Find the right section for your update
+
+```bash
+cat .trellis/spec/<category>/<file>.md
+```
+
+### Step 4: Make the Update
+
+Follow these principles:
+
+1. **Be Specific**: Include concrete examples, not just abstract rules
+2. **Explain Why**: State the problem this prevents
+3. **Show Contracts**: Add signatures, payload fields, and error behavior
+4. **Show Code**: Add code snippets for key patterns
+5. **Keep it Short**: One concept per section
+
+### Step 5: Update the Index (if needed)
+
+If you added a new section or the code-spec status changed, update the category's `index.md`.
+
+---
+
+## Update Templates
+
+### Mandatory Template for Infra/Cross-Layer Work
+
+```markdown
+## Scenario: <name>
+
+### 1. Scope / Trigger
+- Trigger: <why this requires code-spec depth>
+
+### 2. Signatures
+- Backend command/API/DB signature(s)
+
+### 3. Contracts
+- Request fields (name, type, constraints)
+- Response fields (name, type, constraints)
+- Environment keys (required/optional)
+
+### 4. Validation & Error Matrix
+- <condition> -> <error>
+
+### 5. Good/Base/Bad Cases
+- Good: ...
+- Base: ...
+- Bad: ...
+
+### 6. Tests Required
+- Unit/Integration/E2E with assertion points
+
+### 7. Wrong vs Correct
+#### Wrong
+...
+#### Correct
+...
+```
+
+### Adding a Design Decision
+
+```markdown
+### Design Decision: [Decision Name]
+
+**Context**: What problem were we solving?
+
+**Options Considered**:
+1. Option A - brief description
+2. Option B - brief description
+
+**Decision**: We chose Option X because...
+
+**Example**:
+\`\`\`typescript
+// How it's implemented
+code example
+\`\`\`
+
+**Extensibility**: How to extend this in the future...
+```
+
+### Adding a Project Convention
+
+```markdown
+### Convention: [Convention Name]
+
+**What**: Brief description of the convention.
+
+**Why**: Why we do it this way in this project.
+
+**Example**:
+\`\`\`typescript
+// How to follow this convention
+code example
+\`\`\`
+
+**Related**: Links to related conventions or specs.
+```
+
+### Adding a New Pattern
+
+```markdown
+### Pattern Name
+
+**Problem**: What problem does this solve?
+
+**Solution**: Brief description of the approach.
+
+**Example**:
+\`\`\`
+// Good
+code example
+
+// Bad
+code example
+\`\`\`
+
+**Why**: Explanation of why this works better.
+```
+
+### Adding a Forbidden Pattern
+
+```markdown
+### Don't: Pattern Name
+
+**Problem**:
+\`\`\`
+// Don't do this
+bad code example
+\`\`\`
+
+**Why it's bad**: Explanation of the issue.
+
+**Instead**:
+\`\`\`
+// Do this instead
+good code example
+\`\`\`
+```
+
+### Adding a Common Mistake
+
+```markdown
+### Common Mistake: Description
+
+**Symptom**: What goes wrong
+
+**Cause**: Why this happens
+
+**Fix**: How to correct it
+
+**Prevention**: How to avoid it in the future
+```
+
+### Adding a Gotcha
+
+```markdown
+> **Warning**: Brief description of the non-obvious behavior.
+>
+> Details about when this happens and how to handle it.
+```
+
+---
+
+## Interactive Mode
+
+If you're unsure what to update, answer these prompts:
+
+1. **What did you just finish?**
+   - [ ] Fixed a bug
+   - [ ] Implemented a feature
+   - [ ] Refactored code
+   - [ ] Had a discussion about approach
+
+2. **What did you learn or decide?**
+   - Design decision (why X over Y)
+   - Project convention (how we do X)
+   - Non-obvious behavior (gotcha)
+   - Better approach (pattern)
+
+3. **Would future AI/developers need to know this?**
+   - To understand how the code works → Yes, update spec
+   - To maintain or extend the feature → Yes, update spec
+   - To avoid repeating mistakes → Yes, update spec
+   - Purely one-off implementation detail → Maybe skip
+
+4. **Which area does it relate to?**
+   - [ ] Backend code
+   - [ ] Frontend code
+   - [ ] Cross-layer data flow
+   - [ ] Code organization/reuse
+   - [ ] Quality/testing
+
+---
+
+## Quality Checklist
+
+Before finishing your code-spec update:
+
+- [ ] Is the content specific and actionable?
+- [ ] Did you include a code example?
+- [ ] Did you explain WHY, not just WHAT?
+- [ ] Did you include executable signatures/contracts?
+- [ ] Did you include validation and error matrix?
+- [ ] Did you include Good/Base/Bad cases?
+- [ ] Did you include required tests with assertion points?
+- [ ] Is it in the right code-spec file?
+- [ ] Does it duplicate existing content?
+- [ ] Would a new team member understand it?
+
+---
+
+## Relationship to Other Commands
+
+```
+Development Flow:
+  Learn something → `update-spec` (Trellis command) → Knowledge captured
+       ↑                                  ↓
+  `break-loop` (Trellis command) ←──────────────────── Future sessions benefit
+  (deep bug analysis)
+```
+
+- ``break-loop` (Trellis command)` - Analyzes bugs deeply, often reveals spec updates needed
+- ``update-spec` (Trellis command)` - Actually makes the updates
+- ``finish-work` (Trellis command)` - Reminds you to check if specs need updates
+
+---
+
+## Core Philosophy
+
+> **Code-specs are living documents. Every debugging session, every "aha moment" is an opportunity to make the implementation contract clearer.**
+
+The goal is **institutional memory**:
+- What one person learns, everyone benefits from
+- What AI learns in one session, persists to future sessions
+- Mistakes become documented guardrails

.claude/agents/trellis-check.md

@@ -0,0 +1,109 @@
+---
+name: trellis-check
+description: |
+  Code quality check expert. Reviews code changes against specs and self-fixes issues.
+tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
+---
+# Check Agent
+
+You are the Check Agent in the Trellis workflow.
+
+## Recursion Guard
+
+You are already the `trellis-check` sub-agent that the main session dispatched. Do the review and fixes directly.
+
+- Do NOT spawn another `trellis-check` or `trellis-implement` sub-agent.
+- If SessionStart context, workflow-state breadcrumbs, or workflow.md say to dispatch `trellis-implement` / `trellis-check`, treat that as a main-session instruction that is already satisfied by your current role.
+- Only the main session may dispatch Trellis implement/check agents. If more implementation work is needed, report that recommendation instead of spawning.
+
+## Trellis Context Loading Protocol
+
+Look for the `<!-- trellis-hook-injected -->` marker in your input above.
+
+- **If the marker is present**: prd / spec / research files have already been auto-loaded for you above. Proceed with the check work directly.
+- **If the marker is absent**: hook injection didn't fire (Windows + Claude Code, `--continue` resume, fork distribution, hooks disabled, etc.). Find the active task path from your dispatch prompt's first line `Active task: <path>`, then Read `<task-path>/prd.md` and the spec files listed in `<task-path>/check.jsonl` yourself before doing the work.
+
+## Context
+
+Before checking, read:
+- `.trellis/spec/` - Development guidelines
+- Pre-commit checklist for quality standards
+
+## Core Responsibilities
+
+1. **Get code changes** - Use git diff to get uncommitted code
+2. **Check against specs** - Verify code follows guidelines
+3. **Self-fix** - Fix issues yourself, not just report them
+4. **Run verification** - typecheck and lint
+
+## Important
+
+**Fix issues yourself**, don't just report them.
+
+You have write and edit tools, you can modify code directly.
+
+---
+
+## Workflow
+
+### Step 1: Get Changes
+
+```bash
+git diff --name-only  # List changed files
+git diff              # View specific changes
+```
+
+### Step 2: Check Against Specs
+
+Read relevant specs in `.trellis/spec/` to check code:
+
+- Does it follow directory structure conventions
+- Does it follow naming conventions
+- Does it follow code patterns
+- Are there missing types
+- Are there potential bugs
+
+### Step 3: Self-Fix
+
+After finding issues:
+
+1. Fix the issue directly (use edit tool)
+2. Record what was fixed
+3. Continue checking other issues
+
+### Step 4: Run Verification
+
+Run project's lint and typecheck commands to verify changes.
+
+If failed, fix issues and re-run.
+
+---
+
+## Report Format
+
+```markdown
+## Self-Check Complete
+
+### Files Checked
+
+- src/components/Feature.tsx
+- src/hooks/useFeature.ts
+
+### Issues Found and Fixed
+
+1. `<file>:<line>` - <what was fixed>
+2. `<file>:<line>` - <what was fixed>
+
+### Issues Not Fixed
+
+(If there are issues that cannot be self-fixed, list them here with reasons)
+
+### Verification Results
+
+- TypeCheck: Passed
+- Lint: Passed
+
+### Summary
+
+Checked X files, found Y issues, all fixed.
+```

.claude/agents/trellis-implement.md

@@ -0,0 +1,109 @@
+---
+name: trellis-implement
+description: |
+  Code implementation expert. Understands specs and requirements, then implements features. No git commit allowed.
+tools: Read, Write, Edit, Bash, Glob, Grep, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa
+---
+# Implement Agent
+
+You are the Implement Agent in the Trellis workflow.
+
+## Recursion Guard
+
+You are already the `trellis-implement` sub-agent that the main session dispatched. Do the implementation work directly.
+
+- Do NOT spawn another `trellis-implement` or `trellis-check` sub-agent.
+- If SessionStart context, workflow-state breadcrumbs, or workflow.md say to dispatch `trellis-implement` / `trellis-check`, treat that as a main-session instruction that is already satisfied by your current role.
+- Only the main session may dispatch Trellis implement/check agents. If more parallel work is needed, report that recommendation instead of spawning.
+
+## Trellis Context Loading Protocol
+
+Look for the `<!-- trellis-hook-injected -->` marker in your input above.
+
+- **If the marker is present**: prd / spec / research files have already been auto-loaded for you above. Proceed with the implementation work directly.
+- **If the marker is absent**: hook injection didn't fire (Windows + Claude Code, `--continue` resume, fork distribution, hooks disabled, etc.). Find the active task path from your dispatch prompt's first line `Active task: <path>`, then Read `<task-path>/prd.md`, `<task-path>/info.md` (if it exists), and the spec files listed in `<task-path>/implement.jsonl` yourself before doing the work.
+
+## Context
+
+Before implementing, read:
+- `.trellis/workflow.md` - Project workflow
+- `.trellis/spec/` - Development guidelines
+- Task `prd.md` - Requirements document
+- Task `info.md` - Technical design (if exists)
+
+## Core Responsibilities
+
+1. **Understand specs** - Read relevant spec files in `.trellis/spec/`
+2. **Understand requirements** - Read prd.md and info.md
+3. **Implement features** - Write code following specs and design
+4. **Self-check** - Ensure code quality
+5. **Report results** - Report completion status
+
+## Forbidden Operations
+
+**Do NOT execute these git commands:**
+
+- `git commit`
+- `git push`
+- `git merge`
+
+---
+
+## Workflow
+
+### 1. Understand Specs
+
+Read relevant specs based on task type:
+
+- Spec layers: `.trellis/spec/<package>/<layer>/`
+- Shared guides: `.trellis/spec/guides/`
+
+### 2. Understand Requirements
+
+Read the task's prd.md and info.md:
+
+- What are the core requirements
+- Key points of technical design
+- Which files to modify/create
+
+### 3. Implement Features
+
+- Write code following specs and technical design
+- Follow existing code patterns
+- Only do what's required, no over-engineering
+
+### 4. Verify
+
+Run project's lint and typecheck commands to verify changes.
+
+---
+
+## Report Format
+
+```markdown
+## Implementation Complete
+
+### Files Modified
+
+- `src/components/Feature.tsx` - New component
+- `src/hooks/useFeature.ts` - New hook
+
+### Implementation Summary
+
+1. Created Feature component...
+2. Added useFeature hook...
+
+### Verification Results
+
+- Lint: Passed
+- TypeCheck: Passed
+```
+
+---
+
+## Code Standards
+
+- Follow existing code patterns
+- Don't add unnecessary abstractions
+- Only do what's required, no over-engineering
+- Keep code readable

.claude/agents/trellis-research.md

@@ -0,0 +1,137 @@
+---
+name: trellis-research
+description: |
+  Code and tech search expert. Finds files, patterns, and tech solutions, and PERSISTS every finding to the current task's research/ directory. No code modifications outside that directory.
+tools: Read, Write, Glob, Grep, Bash, mcp__exa__web_search_exa, mcp__exa__get_code_context_exa, Skill, mcp__chrome-devtools__*
+---
+# Research Agent
+
+You are the Research Agent in the Trellis workflow.
+
+## Core Principle
+
+**You do one thing: find, explain, and PERSIST information.**
+
+Conversations get compacted; files don't. Every research output MUST end up as a file under `{TASK_DIR}/research/`. Returning findings only through the chat reply is a failure — the caller cannot read them next session.
+
+---
+
+## Core Responsibilities
+
+1. **Internal Search** — locate files/components, understand code logic, discover patterns (Glob, Grep, Read)
+2. **External Search** — library docs, API references, best practices (web search)
+3. **Persist** — write each research topic to `{TASK_DIR}/research/<topic>.md`
+4. **Report** — return file paths + one-line summaries to the main agent (not full content)
+
+---
+
+## Workflow
+
+### Step 1: Resolve Current Task
+
+Run `python ./.trellis/scripts/task.py current --source` → active task path. If no active task is set, ask the user where to write output; do NOT guess.
+
+Ensure `{TASK_DIR}/research/` exists:
+
+```bash
+mkdir -p <TASK_DIR>/research
+```
+
+### Step 2: Understand Search Request
+
+Classify: internal / external / mixed. Determine scope (global / specific directory) and expected shape (file list / pattern notes / tech comparison).
+
+### Step 3: Execute Search
+
+Run independent searches in parallel (Glob + Grep + web) for efficiency.
+
+### Step 4: Persist Each Topic
+
+For each distinct research topic, Write a markdown file at `{TASK_DIR}/research/<topic-slug>.md`. Use the File Format below.
+
+### Step 5: Report to Main Agent
+
+Reply with ONLY:
+
+- List of files written (paths relative to repo root)
+- One-line summary per file
+- Any critical caveats that the main agent needs to know right now
+
+Do NOT paste full research content into the reply. The files are the contract.
+
+---
+
+## Scope Limits (Strict)
+
+### Write ALLOWED
+
+- `{TASK_DIR}/research/*.md` — your own output
+- Creating `{TASK_DIR}/research/` if it doesn't exist (via `mkdir -p`)
+
+### Write FORBIDDEN
+
+- Code files (`src/`, `lib/`, …)
+- Spec files (`.trellis/spec/`) — main agent should use `update-spec` skill instead
+- `.trellis/scripts/`, `.trellis/workflow.md`, platform config (`.claude/`, `.cursor/`, etc.)
+- Other task directories
+- Any git operation (commit / push / branch / merge)
+
+If the user asks you to edit code, decline and suggest spawning `implement` instead.
+
+---
+
+## File Format
+
+Each `{TASK_DIR}/research/<topic>.md` should follow:
+
+```markdown
+# Research: <topic>
+
+- **Query**: <original query>
+- **Scope**: <internal / external / mixed>
+- **Date**: <YYYY-MM-DD>
+
+## Findings
+
+### Files Found
+
+| File Path | Description |
+|---|---|
+| `src/services/xxx.ts` | Main implementation |
+| `src/types/xxx.ts` | Type definitions |
+
+### Code Patterns
+
+<describe patterns, cite file:line>
+
+### External References
+
+- [Library X docs](url) — <why relevant, version constraints>
+
+### Related Specs
+
+- `.trellis/spec/xxx.md` — <description>
+
+## Caveats / Not Found
+
+<anything incomplete or uncertain>
+```
+
+---
+
+## Guidelines
+
+### DO
+
+- Provide specific file paths and line numbers
+- Quote actual code snippets
+- Persist every topic to its own file
+- Return file paths in your reply, not the full content
+- Mark "not found" explicitly when searches come up empty
+
+### DON'T
+
+- Don't write code or modify files outside `{TASK_DIR}/research/`
+- Don't guess uncertain info
+- Don't paste full research text into the reply (files are the deliverable)
+- Don't propose improvements or critique implementation (that's not your role)

.claude/commands/trellis/continue.md

@@ -0,0 +1,55 @@
+# Continue Current Task
+
+Resume work on the current task — pick up at the right phase/step in `.trellis/workflow.md`.
+
+---
+
+## Step 1: Load Current Context
+
+```bash
+python ./.trellis/scripts/get_context.py
+```
+
+Confirms: current task, git state, recent commits.
+
+## Step 2: Load the Phase Index
+
+```bash
+python ./.trellis/scripts/get_context.py --mode phase
+```
+
+Shows the Phase Index (Plan / Execute / Finish) with routing + skill mapping.
+
+## Step 3: Decide Where You Are
+
+`get_context.py` shows the active task's `status` field. Route by `status` + artifact presence:
+
+- `status=planning` + no `prd.md` → **1.1** (load `trellis-brainstorm`)
+- `status=planning` + `prd.md` exists + `implement.jsonl` not curated (only the seed `_example` row) → **1.3**
+- `status=planning` + `prd.md` + curated `implement.jsonl` → **1.4** (run `task.py start` to enter Phase 2)
+- `status=in_progress` + implementation not started → **2.1**
+- `status=in_progress` + implementation done, not yet checked → **2.2**
+- `status=in_progress` + check passed → **3.1**
+- `status=completed` (rare; usually archived immediately) → archive flow
+
+Phase rules (full detail in `.trellis/workflow.md`):
+
+1. Run steps **in order** within a phase — `[required]` steps must not be skipped
+2. `[once]` steps are already done if the output exists (e.g., `prd.md` for 1.1; `implement.jsonl` with curated entries for 1.3) — skip them
+3. You may go back to an earlier phase if discoveries require it
+
+## Step 4: Load the Specific Step
+
+Once you know which step to resume at:
+
+```bash
+python ./.trellis/scripts/get_context.py --mode phase --step <X.X> --platform claude
+```
+
+Follow the loaded instructions. After each `[required]` step completes, move to the next.
+
+---
+
+## Reference
+
+Full workflow, skill routing table, and the DO-NOT-skip table live in `.trellis/workflow.md`. This command is only an entry point — the canonical guidance is there.

.claude/commands/trellis/finish-work.md

@@ -0,0 +1,66 @@
+# Finish Work
+
+Wrap up the current session: archive the active task (and any other completed-but-unarchived tasks the user wants to clean up) and record the session journal. Code commits are NOT done here — those happen in workflow Phase 3.4 before you invoke this command.
+
+## Step 1: Survey current state
+
+```bash
+python ./.trellis/scripts/get_context.py --mode record
+```
+
+This prints:
+
+- **My active tasks** — review whether any besides the current one are actually done (code merged, AC met) and should be archived this round.
+- **Git status** — quick visual on what's dirty.
+- **Recent commits** — you'll need their hashes in Step 4 for `--commit`.
+
+If `--mode record` surfaces other completed tasks not tied to the current session, surface them to the user with a one-shot confirmation: "These N tasks look done — archive them too in this round? [y/N]". Default is no; the current active task is always archived in Step 3 regardless.
+
+## Step 2: Sanity check — classify dirty paths
+
+Run:
+
+```bash
+git status --porcelain
+```
+
+Filter out paths under `.trellis/workspace/` and `.trellis/tasks/` — those are managed by `add_session.py` and `task.py archive` auto-commits and will appear dirty as part of this skill's own work.
+
+For each remaining dirty path, decide whether it belongs to **the current task** or to **other parallel work** (e.g., another terminal window editing the same repo). Heuristics:
+
+- Paths referenced in the current task's `prd.md` / `implement.jsonl` / `check.jsonl` → current task
+- Paths in code areas matching the task's stated scope, or that you remember editing this session → current task
+- Paths in unrelated areas you have no recollection of touching this session → other parallel work
+
+Then route:
+
+- **Any remaining path looks like current-task work** — bail out with:
+  > "Working tree has uncommitted code changes from this task: `<list>`. Return to workflow Phase 3.4 to commit them before running `/trellis:finish-work`."
+
+  Do NOT run `git commit` here. Do NOT prompt the user to commit. The user goes back to Phase 3.4 and the AI drives the batched commit there.
+- **All remaining paths look unrelated** (other parallel-window work) — report them once and continue to Step 3:
+  > "FYI, dirty files outside this task's scope — leaving them for the other window: `<list>`."
+- **Genuinely unsure** — ask the user once: "Are `<list>` this task's work I forgot to commit, or another window's? (commit / ignore)" — then route per their answer.
+
+## Step 3: Archive task(s)
+
+```bash
+python ./.trellis/scripts/task.py archive <task-name>
+```
+
+At minimum: the current active task (if any). Plus any extra tasks the user confirmed in Step 1. Each archive produces a `chore(task): archive ...` commit via the script's auto-commit.
+
+If there is no active task and the user did not confirm any cleanup archives, skip this step.
+
+## Step 4: Record session journal
+
+```bash
+python ./.trellis/scripts/add_session.py \
+  --title "Session Title" \
+  --commit "hash1,hash2" \
+  --summary "Brief summary"
+```
+
+Use the work-commit hashes produced in Phase 3.4 (visible in Step 1's `Recent commits` list, or via `git log --oneline`) for `--commit`. Do not include the archive commit hashes from Step 3. This produces a `chore: record journal` commit.
+
+Final git log order: `<work commits from 3.4>` → `chore(task): archive ...` (one or more) → `chore: record journal`.

.claude/hooks/inject-subagent-context.py

@@ -0,0 +1,749 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Multi-Platform Sub-Agent Context Injection Hook
+
+Injects task-specific context when sub-agents (implement, check, research) are spawned.
+
+Core Design Philosophy:
+- Hook is responsible for injecting all context, subagent works autonomously with complete info
+- Each agent has a dedicated jsonl file defining its context
+- No resume needed, no segmentation, behavior controlled by code not prompt
+
+Trigger: PreToolUse (before Task tool call)
+
+Context Source: Trellis active task resolver points to task directory
+- implement.jsonl - Implement agent dedicated context
+- check.jsonl     - Check agent dedicated context
+- prd.md          - Requirements document
+- info.md         - Technical design
+- codex-review-output.txt - Code Review results
+"""
+from __future__ import annotations
+
+# IMPORTANT: Suppress all warnings FIRST
+import warnings
+warnings.filterwarnings("ignore")
+
+import json
+import os
+import sys
+from pathlib import Path
+from typing import Any
+
+# IMPORTANT: Force stdout to use UTF-8 on Windows
+# This fixes UnicodeEncodeError when outputting non-ASCII characters
+if sys.platform.startswith("win"):
+    import io as _io
+    if hasattr(sys.stdout, "reconfigure"):
+        sys.stdout.reconfigure(encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+    elif hasattr(sys.stdout, "detach"):
+        sys.stdout = _io.TextIOWrapper(sys.stdout.detach(), encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+
+
+# =============================================================================
+# Path Constants (change here to rename directories)
+# =============================================================================
+
+DIR_WORKFLOW = ".trellis"
+DIR_SPEC = "spec"
+FILE_TASK_JSON = "task.json"
+
+# =============================================================================
+# Subagent Constants (change here to rename subagent types)
+# =============================================================================
+
+AGENT_IMPLEMENT = "trellis-implement"
+AGENT_CHECK = "trellis-check"
+AGENT_RESEARCH = "trellis-research"
+
+# Agents that require a task directory
+AGENTS_REQUIRE_TASK = (AGENT_IMPLEMENT, AGENT_CHECK)
+# All supported agents
+AGENTS_ALL = (AGENT_IMPLEMENT, AGENT_CHECK, AGENT_RESEARCH)
+
+
+def find_repo_root(start_path: str) -> str | None:
+    """
+    Find git repo root from start_path upwards
+
+    Returns:
+        Repo root path, or None if not found
+    """
+    current = Path(start_path).resolve()
+    while current != current.parent:
+        if (current / ".git").exists():
+            return str(current)
+        current = current.parent
+    return None
+
+
+def _detect_platform(input_data: dict) -> str | None:
+    if isinstance(input_data.get("cursor_version"), str):
+        return "cursor"
+    env_map = {
+        "CLAUDE_PROJECT_DIR": "claude",
+        "CURSOR_PROJECT_DIR": "cursor",
+        "CODEBUDDY_PROJECT_DIR": "codebuddy",
+        "FACTORY_PROJECT_DIR": "droid",
+        "GEMINI_PROJECT_DIR": "gemini",
+        "QODER_PROJECT_DIR": "qoder",
+        "KIRO_PROJECT_DIR": "kiro",
+        "COPILOT_PROJECT_DIR": "copilot",
+    }
+    for env_name, platform in env_map.items():
+        if os.environ.get(env_name):
+            return platform
+    script_parts = set(Path(sys.argv[0]).parts)
+    if ".claude" in script_parts:
+        return "claude"
+    if ".cursor" in script_parts:
+        return "cursor"
+    if ".gemini" in script_parts:
+        return "gemini"
+    if ".qoder" in script_parts:
+        return "qoder"
+    if ".codebuddy" in script_parts:
+        return "codebuddy"
+    if ".factory" in script_parts:
+        return "droid"
+    if ".kiro" in script_parts:
+        return "kiro"
+    return None
+
+
+def get_current_task(repo_root: str, input_data: dict) -> str | None:
+    """Resolve current task directory through the unified active task resolver."""
+    scripts_dir = Path(repo_root) / DIR_WORKFLOW / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    try:
+        from common.active_task import resolve_active_task  # type: ignore[import-not-found]
+    except Exception:
+        return None
+
+    active = resolve_active_task(
+        Path(repo_root),
+        input_data,
+        platform=_detect_platform(input_data),
+    )
+    return active.task_path
+
+
+def read_file_content(base_path: str, file_path: str) -> str | None:
+    """Read file content, return None if file doesn't exist"""
+    full_path = os.path.join(base_path, file_path)
+    if os.path.exists(full_path) and os.path.isfile(full_path):
+        try:
+            with open(full_path, "r", encoding="utf-8") as f:
+                return f.read()
+        except Exception:
+            return None
+    return None
+
+
+def read_directory_contents(
+    base_path: str, dir_path: str, max_files: int = 20
+) -> list[tuple[str, str]]:
+    """
+    Read all .md files in a directory
+
+    Args:
+        base_path: Base path (usually repo_root)
+        dir_path: Directory relative path
+        max_files: Max files to read (prevent huge directories)
+
+    Returns:
+        [(file_path, content), ...]
+    """
+    full_path = os.path.join(base_path, dir_path)
+    if not os.path.exists(full_path) or not os.path.isdir(full_path):
+        return []
+
+    results = []
+    try:
+        # Only read .md files, sorted by filename
+        md_files = sorted(
+            [
+                f
+                for f in os.listdir(full_path)
+                if f.endswith(".md") and os.path.isfile(os.path.join(full_path, f))
+            ]
+        )
+
+        for filename in md_files[:max_files]:
+            file_full_path = os.path.join(full_path, filename)
+            relative_path = os.path.join(dir_path, filename)
+            try:
+                with open(file_full_path, "r", encoding="utf-8") as f:
+                    content = f.read()
+                    results.append((relative_path, content))
+            except Exception:
+                continue
+    except Exception:
+        pass
+
+    return results
+
+
+def read_jsonl_entries(base_path: str, jsonl_path: str) -> list[tuple[str, str]]:
+    """
+    Read all file/directory contents referenced in jsonl file
+
+    Schema:
+        {"file": "path/to/file.md", "reason": "..."}
+        {"file": "path/to/dir/", "type": "directory", "reason": "..."}
+        {"_example": "..."}          # seed row — skipped (no `file` field)
+
+    Rows without a ``file`` field (e.g. the self-describing seed line written
+    by ``task.py create`` before the agent has curated entries) are skipped
+    silently. If the resulting entry list is empty, a stderr warning is
+    emitted so the operator can debug missing context.
+
+    Returns:
+        [(path, content), ...]
+    """
+    full_path = os.path.join(base_path, jsonl_path)
+    if not os.path.exists(full_path):
+        print(
+            f"[inject-subagent-context] WARN: {jsonl_path} not found — "
+            f"sub-agent will receive only prd.md",
+            file=sys.stderr,
+        )
+        return []
+
+    results = []
+    saw_real_entry = False
+    try:
+        with open(full_path, "r", encoding="utf-8") as f:
+            for line in f:
+                line = line.strip()
+                if not line:
+                    continue
+                try:
+                    item = json.loads(line)
+                    file_path = item.get("file") or item.get("path")
+                    entry_type = item.get("type", "file")
+
+                    if not file_path:
+                        # Seed / comment row — skip silently
+                        continue
+
+                    saw_real_entry = True
+                    if entry_type == "directory":
+                        # Read all .md files in directory
+                        dir_contents = read_directory_contents(base_path, file_path)
+                        results.extend(dir_contents)
+                    else:
+                        # Read single file
+                        content = read_file_content(base_path, file_path)
+                        if content:
+                            results.append((file_path, content))
+                except json.JSONDecodeError:
+                    continue
+    except Exception:
+        pass
+
+    if not saw_real_entry:
+        print(
+            f"[inject-subagent-context] WARN: {jsonl_path} has no curated "
+            f"entries (only seed / empty) — sub-agent will receive only "
+            f"prd.md. See workflow.md Phase 1.3 for curation guidance.",
+            file=sys.stderr,
+        )
+
+    return results
+
+
+
+
+def get_agent_context(repo_root: str, task_dir: str, agent_type: str) -> str:
+    """
+    Get context from {agent_type}.jsonl for the specified agent.
+    Only reads implement.jsonl or check.jsonl (the two JSONL files the task system creates).
+    """
+    context_parts = []
+
+    agent_jsonl = f"{task_dir}/{agent_type}.jsonl"
+    for file_path, content in read_jsonl_entries(repo_root, agent_jsonl):
+        context_parts.append(f"=== {file_path} ===\n{content}")
+
+    return "\n\n".join(context_parts)
+
+
+def get_implement_context(repo_root: str, task_dir: str) -> str:
+    """
+    Complete context for Implement Agent
+
+    Read order:
+    1. All files in implement.jsonl (dev specs)
+    2. prd.md (requirements)
+    3. info.md (technical design)
+    """
+    context_parts = []
+
+    # 1. Read implement.jsonl
+    base_context = get_agent_context(repo_root, task_dir, "implement")
+    if base_context:
+        context_parts.append(base_context)
+
+    # 2. Requirements document
+    prd_content = read_file_content(repo_root, f"{task_dir}/prd.md")
+    if prd_content:
+        context_parts.append(f"=== {task_dir}/prd.md (Requirements) ===\n{prd_content}")
+
+    # 3. Technical design
+    info_content = read_file_content(repo_root, f"{task_dir}/info.md")
+    if info_content:
+        context_parts.append(
+            f"=== {task_dir}/info.md (Technical Design) ===\n{info_content}"
+        )
+
+    return "\n\n".join(context_parts)
+
+
+def get_check_context(repo_root: str, task_dir: str) -> str:
+    """
+    Context for Check Agent: check.jsonl + prd.md
+    """
+    context_parts = []
+
+    for file_path, content in read_jsonl_entries(repo_root, f"{task_dir}/check.jsonl"):
+        context_parts.append(f"=== {file_path} ===\n{content}")
+
+    prd_content = read_file_content(repo_root, f"{task_dir}/prd.md")
+    if prd_content:
+        context_parts.append(f"=== {task_dir}/prd.md (Requirements) ===\n{prd_content}")
+
+    return "\n\n".join(context_parts)
+
+
+def get_finish_context(repo_root: str, task_dir: str) -> str:
+    """
+    Context for Finish phase: reuses check.jsonl + prd.md
+    (Finish is a final check, same context source.)
+    """
+    return get_check_context(repo_root, task_dir)
+
+
+
+def build_implement_prompt(original_prompt: str, context: str) -> str:
+    """Build complete prompt for Implement"""
+    return f"""<!-- trellis-hook-injected -->
+# Implement Agent Task
+
+You are the Implement Agent in the Multi-Agent Pipeline.
+
+## Your Context
+
+All the information you need has been prepared for you:
+
+{context}
+
+---
+
+## Your Task
+
+{original_prompt}
+
+---
+
+## Workflow
+
+1. **Understand specs** - All dev specs are injected above, understand them
+2. **Understand requirements** - Read requirements document and technical design
+3. **Implement feature** - Implement following specs and design
+4. **Self-check** - Ensure code quality against check specs
+
+## Important Constraints
+
+- Do NOT execute git commit, only code modifications
+- Follow all dev specs injected above
+- Report list of modified/created files when done"""
+
+
+def build_check_prompt(original_prompt: str, context: str) -> str:
+    """Build complete prompt for Check"""
+    return f"""<!-- trellis-hook-injected -->
+# Check Agent Task
+
+You are the Check Agent in the Multi-Agent Pipeline (code and cross-layer checker).
+
+## Your Context
+
+All check specs and dev specs you need:
+
+{context}
+
+---
+
+## Your Task
+
+{original_prompt}
+
+---
+
+## Workflow
+
+1. **Get changes** - Run `git diff --name-only` and `git diff` to get code changes
+2. **Check against specs** - Check item by item against specs above
+3. **Self-fix** - Fix issues directly, don't just report
+4. **Run verification** - Run project's lint and typecheck commands
+
+## Important Constraints
+
+- Fix issues yourself, don't just report
+- Must execute complete checklist in check specs
+- Pay special attention to impact radius analysis (L1-L5)"""
+
+
+def build_finish_prompt(original_prompt: str, context: str) -> str:
+    """Build complete prompt for Finish (final check before PR)"""
+    return f"""<!-- trellis-hook-injected -->
+# Finish Agent Task
+
+You are performing the final check before creating a PR.
+
+## Your Context
+
+Finish checklist and requirements:
+
+{context}
+
+---
+
+## Your Task
+
+{original_prompt}
+
+---
+
+## Workflow
+
+1. **Review changes** - Run `git diff --name-only` to see all changed files
+2. **Verify requirements** - Check each requirement in prd.md is implemented
+3. **Spec sync** - Analyze whether changes introduce new patterns, contracts, or conventions
+   - If new pattern/convention found: read target spec file → update it → update index.md if needed
+   - If infra/cross-layer change: follow the 7-section mandatory template from update-spec.md
+   - If pure code fix with no new patterns: skip this step
+4. **Run final checks** - Execute lint and typecheck
+5. **Confirm ready** - Ensure code is ready for PR
+
+## Important Constraints
+
+- You MAY update spec files when gaps are detected (use update-spec.md as guide)
+- MUST read the target spec file BEFORE editing (avoid duplicating existing content)
+- Do NOT update specs for trivial changes (typos, formatting, obvious fixes)
+- If critical CODE issues found, report them clearly (fix specs, not code)
+- Verify all acceptance criteria in prd.md are met"""
+
+
+
+def get_research_context(repo_root: str, task_dir: str | None) -> str:
+    """
+    Context for Research Agent — project structure overview for spec directories.
+
+    `task_dir` kept for signature parity with get_implement_context / get_check_context
+    so the dispatcher can call them uniformly.
+    """
+    _ = task_dir
+    context_parts = []
+
+    # 1. Project structure overview (dynamically discover spec directories)
+    spec_path = f"{DIR_WORKFLOW}/{DIR_SPEC}"
+    spec_root = Path(repo_root) / DIR_WORKFLOW / DIR_SPEC
+
+    # Build spec tree dynamically
+    tree_lines = [f"{spec_path}/"]
+    if spec_root.is_dir():
+        pkg_dirs = sorted(d for d in spec_root.iterdir() if d.is_dir())
+        for i, pkg_dir in enumerate(pkg_dirs):
+            is_last = i == len(pkg_dirs) - 1
+            prefix = "└── " if is_last else "├── "
+            layers = sorted(d.name for d in pkg_dir.iterdir() if d.is_dir())
+            layer_info = f" ({', '.join(layers)})" if layers else ""
+            tree_lines.append(f"{prefix}{pkg_dir.name}/{layer_info}")
+
+    spec_tree = "\n".join(tree_lines)
+
+    project_structure = f"""## Project Spec Directory Structure
+
+```
+{spec_tree}
+```
+
+To get structured package info, run: `python ./{DIR_WORKFLOW}/scripts/get_context.py --mode packages`
+
+## Search Tips
+
+- Spec files: `{spec_path}/**/*.md`
+- Code search: Use Glob and Grep tools
+- Tech solutions: Use mcp__exa__web_search_exa or mcp__exa__get_code_context_exa"""
+
+    context_parts.append(project_structure)
+
+    return "\n\n".join(context_parts)
+
+
+def build_research_prompt(original_prompt: str, context: str) -> str:
+    """Build complete prompt for Research"""
+    return f"""# Research Agent Task
+
+You are the Research Agent in the Multi-Agent Pipeline (search researcher).
+
+## Core Principle
+
+**You do one thing: find and explain information.**
+
+You are a documenter, not a reviewer.
+
+## Project Info
+
+{context}
+
+---
+
+## Your Task
+
+{original_prompt}
+
+---
+
+## Workflow
+
+1. **Understand query** - Determine search type (internal/external) and scope
+2. **Plan search** - List search steps for complex queries
+3. **Execute search** - Execute multiple independent searches in parallel
+4. **Organize results** - Output structured report
+
+## Search Tools
+
+| Tool | Purpose |
+|------|---------|
+| Glob | Search by filename pattern |
+| Grep | Search by content |
+| Read | Read file content |
+| mcp__exa__web_search_exa | External web search |
+| mcp__exa__get_code_context_exa | External code/doc search |
+
+## Strict Boundaries
+
+**Only allowed**: Describe what exists, where it is, how it works
+
+**Forbidden** (unless explicitly asked):
+- Suggest improvements
+- Criticize implementation
+- Recommend refactoring
+- Modify any files
+
+## Report Format
+
+Provide structured search results including:
+- List of files found (with paths)
+- Code pattern analysis (if applicable)
+- Related spec documents
+- External references (if any)"""
+
+
+def _string_value(value: Any) -> str:
+    if isinstance(value, str):
+        stripped = value.strip()
+        return stripped
+    return ""
+
+
+def _extract_subagent_name(value: Any) -> str:
+    """Extract a sub-agent name from common platform encodings.
+
+    Cursor's native Task args encode custom sub-agents as a protobuf oneof,
+    which can appear in hook JSON as either ``{"custom": {"name": "..."}}``
+    or ``{"type": {"case": "custom", "value": {"name": "..."}}}``.
+    """
+    direct = _string_value(value)
+    if direct:
+        return direct
+
+    if not isinstance(value, dict):
+        return ""
+
+    for key in ("name", "subagent_type_name", "subagentTypeName"):
+        direct = _string_value(value.get(key))
+        if direct:
+            return direct
+
+    custom = value.get("custom")
+    if isinstance(custom, dict):
+        custom_name = _string_value(custom.get("name"))
+        if custom_name:
+            return custom_name
+
+    oneof = value.get("type")
+    if isinstance(oneof, dict):
+        case_name = _string_value(oneof.get("case"))
+        if case_name == "custom":
+            nested_value = oneof.get("value")
+            if isinstance(nested_value, dict):
+                custom_name = _string_value(nested_value.get("name"))
+                if custom_name:
+                    return custom_name
+        if case_name:
+            return case_name
+
+    case_name = _string_value(value.get("case"))
+    if case_name == "custom":
+        nested_value = value.get("value")
+        if isinstance(nested_value, dict):
+            custom_name = _string_value(nested_value.get("name"))
+            if custom_name:
+                return custom_name
+    if case_name:
+        return case_name
+
+    for agent_name in AGENTS_ALL:
+        if agent_name in value:
+            return agent_name
+
+    return ""
+
+
+def _extract_subagent_type(tool_input: dict) -> str:
+    for key in (
+        "subagent_type",
+        "subagentType",
+        "subagent_type_name",
+        "subagentTypeName",
+        "agent_type",
+        "agentType",
+        "name",
+    ):
+        agent_name = _extract_subagent_name(tool_input.get(key))
+        if agent_name:
+            return agent_name
+    return ""
+
+
+def _parse_hook_input(input_data: dict) -> tuple[str, str, dict]:
+    """Parse hook input across different platform formats.
+
+    Returns (subagent_type, original_prompt, tool_input).
+    Handles:
+    - Claude Code / Qoder / CodeBuddy / Droid: tool_name=Task|Agent, tool_input.subagent_type
+    - Cursor: tool_name=Task|Subagent, tool_input.subagent_type
+    - Copilot CLI: toolName=task (camelCase key, lowercase value)
+    - Gemini CLI: tool_name IS the agent name (BeforeTool matcher already filtered)
+    - Kiro: agentSpawn hook, agent_name field at top level
+    """
+    tool_input = input_data.get("tool_input", {})
+
+    # Standard format: Task/Agent tool with subagent_type
+    tool_name = input_data.get("tool_name", "") or input_data.get("toolName", "")
+    if tool_name.lower() in ("task", "agent", "subagent"):
+        return (
+            _extract_subagent_type(tool_input),
+            tool_input.get("prompt", ""),
+            tool_input,
+        )
+
+    # Kiro: agentSpawn hook passes agent_name at top level
+    agent_name = input_data.get("agent_name", "")
+    if agent_name:
+        return agent_name, tool_input.get("prompt", input_data.get("prompt", "")), tool_input
+
+    # Gemini CLI: BeforeTool where tool_name IS the agent name
+    # (matcher already ensured it's one of our agents)
+    if tool_name in AGENTS_ALL:
+        return tool_name, tool_input.get("prompt", ""), tool_input
+
+    # Copilot CLI: toolName field (camelCase), value might be the agent name
+    tool_name_camel = input_data.get("toolName", "")
+    if tool_name_camel in AGENTS_ALL:
+        return tool_name_camel, input_data.get("toolArgs", ""), tool_input
+
+    return "", "", tool_input
+
+
+def main():
+    if os.environ.get("TRELLIS_HOOKS") == "0" or os.environ.get("TRELLIS_DISABLE_HOOKS") == "1":
+        sys.exit(0)
+
+    try:
+        input_data = json.load(sys.stdin)
+    except json.JSONDecodeError:
+        sys.exit(0)
+
+    subagent_type, original_prompt, tool_input = _parse_hook_input(input_data)
+    cwd = input_data.get("cwd", os.getcwd())
+
+    # Only handle subagent types we care about
+    if subagent_type not in AGENTS_ALL:
+        sys.exit(0)
+
+    # Find repo root
+    repo_root = find_repo_root(cwd)
+    if not repo_root:
+        sys.exit(0)
+
+    # Get current task directory (research doesn't require it)
+    task_dir = get_current_task(repo_root, input_data)
+
+    # implement/check need task directory
+    if subagent_type in AGENTS_REQUIRE_TASK:
+        if not task_dir:
+            sys.exit(0)
+        # Check if task directory exists
+        task_dir_full = os.path.join(repo_root, task_dir)
+        if not os.path.exists(task_dir_full):
+            sys.exit(0)
+
+    # Check for [finish] marker in prompt (check agent with finish context)
+    is_finish_phase = "[finish]" in original_prompt.lower()
+
+    # Get context and build prompt based on subagent type
+    if subagent_type == AGENT_IMPLEMENT:
+        assert task_dir is not None  # validated above
+        context = get_implement_context(repo_root, task_dir)
+        new_prompt = build_implement_prompt(original_prompt, context)
+    elif subagent_type == AGENT_CHECK:
+        assert task_dir is not None  # validated above
+        if is_finish_phase:
+            # Finish phase: use finish context (lighter, focused on final verification)
+            context = get_finish_context(repo_root, task_dir)
+            new_prompt = build_finish_prompt(original_prompt, context)
+        else:
+            # Regular check phase: use check context (full specs for self-fix loop)
+            context = get_check_context(repo_root, task_dir)
+            new_prompt = build_check_prompt(original_prompt, context)
+    elif subagent_type == AGENT_RESEARCH:
+        # Research can work without task directory
+        context = get_research_context(repo_root, task_dir)
+        new_prompt = build_research_prompt(original_prompt, context)
+    else:
+        sys.exit(0)
+
+    if not context:
+        sys.exit(0)
+
+    # Return updated input — use a multi-format output that covers all platforms.
+    # Most platforms ignore unrecognized fields, so we include multiple formats.
+    # The platform picks whichever fields it understands.
+    updated = {**tool_input, "prompt": new_prompt}
+    output = {
+        # Claude Code / Qoder / CodeBuddy / Droid format
+        "hookSpecificOutput": {
+            "hookEventName": "PreToolUse",
+            "permissionDecision": "allow",
+            "updatedInput": updated,
+        },
+        # Cursor format
+        "permission": "allow",
+        "updated_input": updated,
+        # Gemini format
+        "updatedInput": updated,
+    }
+
+    print(json.dumps(output, ensure_ascii=False))
+    sys.exit(0)
+
+
+if __name__ == "__main__":
+    main()

.claude/hooks/inject-workflow-state.py

@@ -0,0 +1,387 @@
+#!/usr/bin/env python3
+"""Trellis per-turn breadcrumb hook (UserPromptSubmit / BeforeAgent equivalent).
+
+Runs on every user prompt. Resolves the active task through Trellis'
+session-aware active task resolver and emits a short <workflow-state>
+block reminding the main AI what task is active and its expected flow.
+
+The emitted ``hookEventName`` field is platform-aware: most hosts expect
+``UserPromptSubmit`` (Claude Code naming, also accepted by Cursor / Qoder /
+CodeBuddy / Droid / Codex / Copilot wiring), but Gemini CLI 0.40.x renamed
+its per-turn event to ``BeforeAgent`` and its schema validator rejects the
+legacy name. ``_detect_platform`` picks the right value at runtime.
+Breadcrumb text is pulled exclusively from workflow.md
+[workflow-state:STATUS] tag blocks — workflow.md is the single source of
+truth. There are no fallback dicts in this script: when workflow.md is
+missing or a tag is absent, the breadcrumb degrades to a generic
+"Refer to workflow.md for current step." line so users see (and fix)
+the broken state instead of the hook silently masking it.
+
+Shared across all hook-capable platforms (Claude, Cursor, Codex, Qoder,
+CodeBuddy, Droid, Gemini, Copilot). Kiro is not wired (no per-turn
+hook entry point). Written to each platform's hooks directory via
+writeSharedHooks() at init time.
+
+Silent exit 0 cases (no output):
+  - No .trellis/ directory found (not a Trellis project)
+  - task.json malformed or missing status
+"""
+from __future__ import annotations
+
+import json
+import os
+import re
+import sys
+from pathlib import Path
+
+# Force UTF-8 on stdin/stdout/stderr on Windows. Default codepage there is
+# cp936 / cp1252 / etc. — non-ASCII content (Chinese task names, prd snippets)
+# both in stdin (hook payload from host CLI) and stdout (our emitted blocks)
+# raises UnicodeDecodeError / UnicodeEncodeError. Equivalent to `python -X utf8`
+# but applied per-stream so we don't depend on host CLI's command wiring.
+if sys.platform.startswith("win"):
+    import io as _io
+    for _stream_name in ("stdin", "stdout", "stderr"):
+        _stream = getattr(sys, _stream_name, None)
+        if _stream is None:
+            continue
+        if hasattr(_stream, "reconfigure"):
+            try:
+                _stream.reconfigure(encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+            except Exception:
+                pass
+        elif hasattr(_stream, "detach"):
+            try:
+                setattr(sys, _stream_name, _io.TextIOWrapper(_stream.detach(), encoding="utf-8", errors="replace"))
+            except Exception:
+                pass
+from typing import Optional
+
+
+CODEX_SUB_AGENT_NOTICE = """<sub-agent-notice>
+SUB-AGENT NOTICE - READ FIRST IF SPAWNED VIA spawn_agent
+
+If your parent session spawned you via spawn_agent with an explicit task
+message above this hook output, that message is your only job.
+- Execute the parent message exactly as written, then return.
+- Ignore all Trellis workflow guidance below this notice.
+- Do NOT call task.py start, task.py add-context, or task.py archive.
+- Do NOT call wait_agent or spawn_agent.
+- Do NOT modify .trellis/tasks/* or any other file unless the parent message
+  explicitly asks for that.
+
+If you are the main interactive Codex session and the user is typing at the
+terminal with no parent agent, use the workflow guidance below normally.
+</sub-agent-notice>"""
+
+
+# Bootstrap notice for Codex while the session has no active task. Replaces the
+# heavyweight SessionStart context injection — instead of pushing 9.5 KB of
+# workflow text up front, we just nudge the AI to read the `trellis-start` skill once.
+# The nudge keeps showing up while status == "no_task" (cheap text, AI won't
+# re-read after the first time). Once a task is created the breadcrumb status
+# flips and this notice stops appearing automatically. Sub-agents are warded
+# off by the <sub-agent-notice> above plus the explicit exemption below.
+CODEX_NO_TASK_BOOTSTRAP_NOTICE = """<trellis-bootstrap>
+You are running in a Trellis-managed Codex session and there is no active task yet.
+If you have not already loaded Trellis context this session, read the `trellis-start` skill once:
+
+  $trellis-start
+
+(equivalent to reading `.agents/skills/trellis-start/SKILL.md` and following its Steps 1-3)
+
+The skill walks you through workflow.md, dev profile, git status, active tasks, and spec
+indexes. Then route the user's request per the <workflow-state> A/B/C rules below.
+
+Sub-agent exemption: if you are a sub-agent (spawned via spawn_agent with a parent task
+message), DO NOT read `$trellis-start`. Execute the parent message directly as instructed by the
+<sub-agent-notice> above.
+</trellis-bootstrap>"""
+
+
+# ---------------------------------------------------------------------------
+# CWD-robust Trellis root discovery (fixes hook-path-robustness for this hook)
+# ---------------------------------------------------------------------------
+
+def find_trellis_root(start: Path) -> Optional[Path]:
+    """Walk up from start to find directory containing .trellis/.
+
+    Handles CWD drift: subdirectory launches, monorepo packages, etc.
+    Returns None if no .trellis/ found (silent no-op).
+    """
+    cur = start.resolve()
+    while cur != cur.parent:
+        if (cur / ".trellis").is_dir():
+            return cur
+        cur = cur.parent
+    return None
+
+
+# ---------------------------------------------------------------------------
+# Active task discovery
+# ---------------------------------------------------------------------------
+
+def _detect_platform(input_data: dict) -> str | None:
+    if isinstance(input_data.get("cursor_version"), str):
+        return "cursor"
+    env_map = {
+        "CLAUDE_PROJECT_DIR": "claude",
+        "CURSOR_PROJECT_DIR": "cursor",
+        "CODEBUDDY_PROJECT_DIR": "codebuddy",
+        "FACTORY_PROJECT_DIR": "droid",
+        "GEMINI_PROJECT_DIR": "gemini",
+        "QODER_PROJECT_DIR": "qoder",
+        "KIRO_PROJECT_DIR": "kiro",
+        "COPILOT_PROJECT_DIR": "copilot",
+    }
+    for env_name, platform in env_map.items():
+        if os.environ.get(env_name):
+            return platform
+    script_parts = set(Path(sys.argv[0]).parts)
+    if ".claude" in script_parts:
+        return "claude"
+    if ".cursor" in script_parts:
+        return "cursor"
+    if ".codex" in script_parts:
+        return "codex"
+    if ".gemini" in script_parts:
+        return "gemini"
+    if ".qoder" in script_parts:
+        return "qoder"
+    if ".codebuddy" in script_parts:
+        return "codebuddy"
+    if ".factory" in script_parts:
+        return "droid"
+    if ".kiro" in script_parts:
+        return "kiro"
+    return None
+
+
+def _resolve_active_task(root: Path, input_data: dict):
+    scripts_dir = root / ".trellis" / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    from common.active_task import resolve_active_task  # type: ignore[import-not-found]
+
+    return resolve_active_task(root, input_data, platform=_detect_platform(input_data))
+
+
+def get_active_task(root: Path, input_data: dict) -> Optional[tuple[str, str, str]]:
+    """Return (task_id, status, source) from the current active task."""
+    active = _resolve_active_task(root, input_data)
+    if not active.task_path:
+        return None
+
+    task_dir = Path(active.task_path)
+    if not task_dir.is_absolute():
+        task_dir = root / task_dir
+    if active.stale:
+        return task_dir.name, f"stale_{active.source_type}", active.source
+
+    task_json = task_dir / "task.json"
+    if not task_json.is_file():
+        return None
+    try:
+        data = json.loads(task_json.read_text(encoding="utf-8"))
+    except (json.JSONDecodeError, OSError):
+        return None
+
+    task_id = data.get("id") or task_dir.name
+    status = data.get("status", "")
+    if not isinstance(status, str) or not status:
+        return None
+    return task_id, status, active.source
+
+
+# ---------------------------------------------------------------------------
+# Breadcrumb loading: parse workflow.md, fall back to hardcoded defaults
+# ---------------------------------------------------------------------------
+
+# Supports STATUS values with letters, digits, underscores, hyphens
+# (so "in-review" / "blocked-by-team" work alongside "in_progress").
+_TAG_RE = re.compile(
+    r"\[workflow-state:([A-Za-z0-9_-]+)\]\s*\n(.*?)\n\s*\[/workflow-state:\1\]",
+    re.DOTALL,
+)
+
+def load_breadcrumbs(root: Path) -> dict[str, str]:
+    """Parse workflow.md for [workflow-state:STATUS] blocks.
+
+    Returns {status: body_text}. workflow.md is the single source of
+    truth — there are no fallback dicts in this script. Missing tags
+    (or a missing/unreadable workflow.md) fall back to a generic line
+    in build_breadcrumb so users see the broken state and fix
+    workflow.md, rather than the hook silently masking the issue.
+    """
+    workflow = root / ".trellis" / "workflow.md"
+    if not workflow.is_file():
+        return {}
+    try:
+        content = workflow.read_text(encoding="utf-8")
+    except OSError:
+        return {}
+
+    result: dict[str, str] = {}
+    for match in _TAG_RE.finditer(content):
+        status = match.group(1)
+        body = match.group(2).strip()
+        if body:
+            result[status] = body
+    return result
+
+
+def _read_trellis_config(root: Path) -> dict:
+    """Load .trellis/config.yaml via the bundled trellis_config helper.
+
+    The helper lives in .trellis/scripts/common; the hook lives outside the
+    scripts tree, so we extend sys.path before importing.
+    """
+    scripts_dir = root / ".trellis" / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    try:
+        from common.trellis_config import read_trellis_config  # type: ignore[import-not-found]
+    except Exception:
+        return {}
+    try:
+        return read_trellis_config(root)
+    except Exception:
+        return {}
+
+
+def _codex_mode_banner(config: dict) -> str:
+    """Emit a `<codex-mode>` banner for the additionalContext payload.
+
+    Reads `codex.dispatch_mode` from .trellis/config.yaml; defaults to
+    `inline` when missing or invalid because Codex sub-agents run with
+    `fork_turns="none"` isolation and can't inherit the parent session's
+    task context. The banner makes the active mode explicit to Codex AI
+    per turn, complementing the workflow-state body which is per-status.
+    Mode tells AI which dispatch protocol to follow; workflow-state tells
+    AI what step it's at.
+    """
+    mode = "inline"
+    if isinstance(config, dict):
+        codex_cfg = config.get("codex")
+        if isinstance(codex_cfg, dict):
+            cfg_mode = codex_cfg.get("dispatch_mode")
+            if cfg_mode in ("inline", "sub-agent"):
+                mode = cfg_mode
+    return f"<codex-mode>{mode}</codex-mode>"
+
+
+def resolve_breadcrumb_key(
+    status: str, platform: str | None, config: dict
+) -> str:
+    """Pick the breadcrumb tag key based on Codex dispatch_mode.
+
+    Codex defaults to ``inline`` because sub-agents run with ``fork_turns="none"``
+    isolation and can't inherit the parent session's task context. Users can
+    opt into ``codex.dispatch_mode: sub-agent`` in ``.trellis/config.yaml``
+    to use the parallel ``<status>-inline`` tag → ``<status>`` flip. Invalid
+    or missing values fall back to inline.
+
+    Non-codex platforms return the plain status unchanged.
+    """
+    if platform == "codex":
+        mode = "inline"
+        if isinstance(config, dict):
+            codex_cfg = config.get("codex")
+            if isinstance(codex_cfg, dict):
+                cfg_mode = codex_cfg.get("dispatch_mode")
+                if cfg_mode in ("inline", "sub-agent"):
+                    mode = cfg_mode
+        return f"{status}-inline" if mode == "inline" else status
+    return status
+
+
+def build_breadcrumb(
+    task_id: Optional[str],
+    status: str,
+    templates: dict[str, str],
+    source: str | None = None,
+    breadcrumb_key: str | None = None,
+) -> str:
+    """Build the <workflow-state>...</workflow-state> block.
+
+    - Known status (tag present in workflow.md) → detailed template body
+    - Unknown status (no tag, or workflow.md missing) → generic
+      "Refer to workflow.md for current step." line
+    - `no_task` pseudo-status (task_id is None) → header omits task info
+    """
+    lookup_key = breadcrumb_key or status
+    body = templates.get(lookup_key)
+    if body is None and lookup_key != status:
+        body = templates.get(status)
+    if body is None:
+        body = "Refer to workflow.md for current step."
+    header = f"Status: {status}" if task_id is None else f"Task: {task_id} ({status})"
+    if source:
+        header = f"{header}\nSource: {source}"
+    return f"<workflow-state>\n{header}\n{body}\n</workflow-state>"
+
+
+# ---------------------------------------------------------------------------
+# Entry
+# ---------------------------------------------------------------------------
+
+def main() -> int:
+    if os.environ.get("TRELLIS_HOOKS") == "0" or os.environ.get("TRELLIS_DISABLE_HOOKS") == "1":
+        return 0
+
+    try:
+        data = json.load(sys.stdin)
+    except (json.JSONDecodeError, ValueError):
+        data = {}
+
+    cwd_str = data.get("cwd") or os.getcwd()
+    cwd = Path(cwd_str)
+
+    root = find_trellis_root(cwd)
+    if root is None:
+        return 0  # not a Trellis project
+
+    templates = load_breadcrumbs(root)
+    platform = _detect_platform(data)
+    config = _read_trellis_config(root)
+    task = get_active_task(root, data)
+    if task is None:
+        # No active task — still emit a breadcrumb nudging AI toward
+        # trellis-brainstorm + task.py create when user describes real work.
+        no_task_key = resolve_breadcrumb_key("no_task", platform, config)
+        breadcrumb = build_breadcrumb(
+            None, "no_task", templates, breadcrumb_key=no_task_key
+        )
+    else:
+        task_id, status, source = task
+        status_key = resolve_breadcrumb_key(status, platform, config)
+        breadcrumb = build_breadcrumb(
+            task_id, status, templates, source, breadcrumb_key=status_key
+        )
+    if platform == "codex":
+        parts: list[str] = [CODEX_SUB_AGENT_NOTICE]
+        if task is None:
+            parts.append(CODEX_NO_TASK_BOOTSTRAP_NOTICE)
+        parts.append(_codex_mode_banner(config))
+        parts.append(breadcrumb)
+        breadcrumb = "\n\n".join(parts)
+
+    # Gemini CLI 0.40.x rejects "UserPromptSubmit" — its per-turn event is
+    # named "BeforeAgent". Other platforms (Claude/Cursor/Qoder/CodeBuddy/
+    # Droid/Codex/Copilot) accept the original Claude-style name.
+    hook_event_name = (
+        "BeforeAgent" if platform == "gemini" else "UserPromptSubmit"
+    )
+
+    output = {
+        "hookSpecificOutput": {
+            "hookEventName": hook_event_name,
+            "additionalContext": breadcrumb,
+        }
+    }
+    print(json.dumps(output))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.claude/hooks/session-start.py

@@ -0,0 +1,797 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Session Start Hook - Inject structured context
+"""
+from __future__ import annotations
+
+# IMPORTANT: Suppress all warnings FIRST
+import warnings
+warnings.filterwarnings("ignore")
+
+import json
+import os
+import re
+import shlex
+import subprocess
+import sys
+from io import StringIO
+from pathlib import Path
+
+
+def _normalize_windows_shell_path(path_str: str) -> str:
+    """Normalize Unix-style shell paths to real Windows paths.
+
+    On Windows, shells like Git Bash / MSYS2 / Cygwin may report paths like
+    `/d/Users/...` or `/cygdrive/d/Users/...`. `Path.resolve()` will misinterpret
+    these as `D:/d/Users...` on drive D: (or similar), breaking repo root
+    detection.
+
+    This function is intentionally conservative: it only rewrites patterns that
+    unambiguously represent a drive letter mount.
+    """
+    if not isinstance(path_str, str) or not path_str:
+        return path_str
+
+    # Only relevant on Windows; keep other platforms untouched.
+    if not sys.platform.startswith("win"):
+        return path_str
+
+    p = path_str.strip()
+
+    # Already a Windows drive path (C:\... or C:/...)
+    if re.match(r"^[A-Za-z]:[\/]", p):
+        return p
+
+    # MSYS/Git-Bash style: /c/Users/... or /d/Work/...
+    m = re.match(r"^/([A-Za-z])/(.*)", p)
+    if m:
+        drive, rest = m.group(1).upper(), m.group(2)
+        rest = rest.replace('/', '\\')
+        return f"{drive}:\\{rest}"
+
+    # Cygwin style: /cygdrive/c/Users/...
+    m = re.match(r"^/cygdrive/([A-Za-z])/(.*)", p)
+    if m:
+        drive, rest = m.group(1).upper(), m.group(2)
+        rest = rest.replace('/', '\\')
+        return f"{drive}:\\{rest}"
+
+    # WSL mounted drive (sometimes leaked into env): /mnt/c/Users/...
+    m = re.match(r"^/mnt/([A-Za-z])/(.*)", p)
+    if m:
+        drive, rest = m.group(1).upper(), m.group(2)
+        rest = rest.replace('/', '\\')
+        return f"{drive}:\\{rest}"
+
+    return path_str
+
+
+FIRST_REPLY_NOTICE = """<first-reply-notice>
+On the first visible assistant reply in this session, begin with exactly one short Chinese sentence:
+Trellis SessionStart 已注入：workflow、当前任务状态、开发者身份、git 状态、active tasks、spec 索引已加载。
+Then continue directly with the user's request. This notice is one-shot: do not repeat it after the first assistant reply in the same session.
+</first-reply-notice>"""
+
+# Force UTF-8 on stdin/stdout/stderr on Windows. Default codepage there is
+# cp936 / cp1252 / etc. — non-ASCII content (Chinese task names, prd snippets)
+# both in stdin (hook payload from host CLI) and stdout (our emitted blocks)
+# raises UnicodeDecodeError / UnicodeEncodeError. Equivalent to `python -X utf8`
+# but applied per-stream so we don't depend on host CLI's command wiring.
+if sys.platform.startswith("win"):
+    import io as _io
+    for _stream_name in ("stdin", "stdout", "stderr"):
+        _stream = getattr(sys, _stream_name, None)
+        if _stream is None:
+            continue
+        if hasattr(_stream, "reconfigure"):
+            try:
+                _stream.reconfigure(encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+            except Exception:
+                pass
+        elif hasattr(_stream, "detach"):
+            try:
+                setattr(sys, _stream_name, _io.TextIOWrapper(_stream.detach(), encoding="utf-8", errors="replace"))
+            except Exception:
+                pass
+
+
+
+def _has_curated_jsonl_entry(jsonl_path: Path) -> bool:
+    """Return True iff jsonl has at least one row with a ``file`` field.
+
+    A freshly seeded jsonl only contains a ``{"_example": ...}`` row (no
+    ``file`` key) — that is NOT "ready". Readiness requires at least one
+    curated entry. Matches the contract used by hook-inject and pull-based
+    sub-agent context loaders.
+    """
+    try:
+        for line in jsonl_path.read_text(encoding="utf-8").splitlines():
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                row = json.loads(line)
+            except json.JSONDecodeError:
+                continue
+            if isinstance(row, dict) and row.get("file"):
+                return True
+    except (OSError, UnicodeDecodeError):
+        return False
+    return False
+
+
+def should_skip_injection() -> bool:
+    """Check if any platform's non-interactive flag is set, or if Trellis
+    hooks are explicitly disabled via TRELLIS_HOOKS=0 / TRELLIS_DISABLE_HOOKS=1.
+    """
+    if os.environ.get("TRELLIS_HOOKS") == "0":
+        return True
+    if os.environ.get("TRELLIS_DISABLE_HOOKS") == "1":
+        return True
+    non_interactive_vars = [
+        "CLAUDE_NON_INTERACTIVE",
+        "QODER_NON_INTERACTIVE",
+        "CODEBUDDY_NON_INTERACTIVE",
+        "FACTORY_NON_INTERACTIVE",
+        "CURSOR_NON_INTERACTIVE",
+        "GEMINI_NON_INTERACTIVE",
+        "KIRO_NON_INTERACTIVE",
+        "COPILOT_NON_INTERACTIVE",
+    ]
+    return any(os.environ.get(var) == "1" for var in non_interactive_vars)
+
+
+def read_file(path: Path, fallback: str = "") -> str:
+    try:
+        return path.read_text(encoding="utf-8")
+    except (FileNotFoundError, PermissionError):
+        return fallback
+
+
+def _detect_platform(input_data: dict) -> str | None:
+    if isinstance(input_data.get("cursor_version"), str):
+        return "cursor"
+    env_map = {
+        "CLAUDE_PROJECT_DIR": "claude",
+        "CURSOR_PROJECT_DIR": "cursor",
+        "CODEBUDDY_PROJECT_DIR": "codebuddy",
+        "FACTORY_PROJECT_DIR": "droid",
+        "GEMINI_PROJECT_DIR": "gemini",
+        "QODER_PROJECT_DIR": "qoder",
+        "KIRO_PROJECT_DIR": "kiro",
+        "COPILOT_PROJECT_DIR": "copilot",
+    }
+    for env_name, platform in env_map.items():
+        if os.environ.get(env_name):
+            return platform
+    script_parts = set(Path(sys.argv[0]).parts)
+    if ".claude" in script_parts:
+        return "claude"
+    if ".cursor" in script_parts:
+        return "cursor"
+    if ".codex" in script_parts:
+        return "codex"
+    if ".gemini" in script_parts:
+        return "gemini"
+    if ".qoder" in script_parts:
+        return "qoder"
+    if ".codebuddy" in script_parts:
+        return "codebuddy"
+    if ".factory" in script_parts:
+        return "droid"
+    if ".kiro" in script_parts:
+        return "kiro"
+    return None
+
+
+def _resolve_context_key(trellis_dir: Path, input_data: dict) -> str | None:
+    scripts_dir = trellis_dir / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    from common.active_task import resolve_context_key  # type: ignore[import-not-found]
+
+    return resolve_context_key(input_data, platform=_detect_platform(input_data))
+
+
+def _persist_context_key_for_bash(context_key: str | None) -> None:
+    """Expose Trellis session identity to later Claude Code Bash commands.
+
+    Claude Code SessionStart hooks can append exports to CLAUDE_ENV_FILE; those
+    variables are then available to Bash tools in the same conversation. Without
+    this bridge, `task.py start` has hook stdin during SessionStart but no
+    session identity when the AI later runs it as a normal shell command.
+    """
+    if not context_key:
+        return
+    env_file = os.environ.get("CLAUDE_ENV_FILE")
+    if not env_file:
+        return
+    try:
+        with open(env_file, "a", encoding="utf-8") as handle:
+            handle.write(f"export TRELLIS_CONTEXT_ID={shlex.quote(context_key)}\n")
+    except OSError:
+        pass
+
+
+def _resolve_active_task(trellis_dir: Path, input_data: dict):
+    scripts_dir = trellis_dir / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    from common.active_task import resolve_active_task  # type: ignore[import-not-found]
+
+    return resolve_active_task(
+        trellis_dir.parent,
+        input_data,
+        platform=_detect_platform(input_data),
+    )
+
+
+def run_script(script_path: Path, context_key: str | None = None) -> str:
+    try:
+        if script_path.suffix == ".py":
+            # Add PYTHONIOENCODING to force UTF-8 in subprocess
+            env = os.environ.copy()
+            env["PYTHONIOENCODING"] = "utf-8"
+            if context_key:
+                env["TRELLIS_CONTEXT_ID"] = context_key
+            cmd = [sys.executable, "-W", "ignore", str(script_path)]
+        else:
+            env = os.environ.copy()
+            if context_key:
+                env["TRELLIS_CONTEXT_ID"] = context_key
+            cmd = [str(script_path)]
+
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            encoding="utf-8",
+            errors="replace",
+            timeout=5,
+            cwd=script_path.parent.parent.parent,
+            env=env,
+        )
+        return result.stdout if result.returncode == 0 else "No context available"
+    except (subprocess.TimeoutExpired, FileNotFoundError, PermissionError):
+        return "No context available"
+
+
+def _normalize_task_ref(task_ref: str) -> str:
+    normalized = task_ref.strip()
+    if not normalized:
+        return ""
+
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return str(path_obj)
+
+    normalized = normalized.replace("\\", "/")
+    while normalized.startswith("./"):
+        normalized = normalized[2:]
+
+    if normalized.startswith("tasks/"):
+        return f".trellis/{normalized}"
+
+    return normalized
+
+
+def _resolve_task_dir(trellis_dir: Path, task_ref: str) -> Path:
+    normalized = _normalize_task_ref(task_ref)
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return path_obj
+    if normalized.startswith(".trellis/"):
+        return trellis_dir.parent / path_obj
+    return trellis_dir / "tasks" / path_obj
+
+
+def _get_task_status(trellis_dir: Path, input_data: dict) -> str:
+    """Check current task status and return structured status string with explicit next action.
+
+    Returns a block with three fields:
+    - Status: current state
+    - Task: task identifier (when applicable)
+    - Next-Action: explicit skill/command/tool call the AI should invoke
+    """
+    active = _resolve_active_task(trellis_dir, input_data)
+
+    # Case 1: No active task — waiting for user to describe intent
+    if not active.task_path:
+        return (
+            "Status: NO ACTIVE TASK\n"
+            f"Source: {active.source}\n"
+            "Next-Action: After the user describes their intent, load skill `trellis-brainstorm` "
+            "to clarify requirements and create a task via `python ./.trellis/scripts/task.py create`.\n"
+            "Research reminder: for research-heavy tasks (comparing tools, reading external docs, "
+            "cross-platform surveys), spawn `trellis-research` sub-agents via the Task tool — "
+            "they persist findings to `{TASK_DIR}/research/*.md` and keep main context clean. "
+            "Do NOT do 10+ inline WebFetch/WebSearch in the main conversation.\n"
+            "User override (per-turn escape hatch): if the user's first message explicitly opts "
+            "out of the workflow (\"跳过 trellis\" / \"别走流程\" / \"小修一下\" / \"直接改\" / "
+            "\"skip trellis\" / \"no task\" / \"just do it\"), honor it for this turn — "
+            "acknowledge briefly and proceed without creating a task. Per-turn only."
+        )
+
+    # Case 2: Stale pointer — task dir was deleted
+    task_ref = active.task_path
+    task_dir = _resolve_task_dir(trellis_dir, task_ref)
+    if active.stale or not task_dir.is_dir():
+        return (
+            f"Status: STALE POINTER\nTask: {task_ref}\n"
+            f"Source: {active.source}\n"
+            f"Next-Action: Run `python ./.trellis/scripts/task.py finish` to clear the stale pointer, "
+            "then ask the user what to work on next."
+        )
+
+    # Read task.json
+    task_json_path = task_dir / "task.json"
+    task_data = {}
+    if task_json_path.is_file():
+        try:
+            task_data = json.loads(task_json_path.read_text(encoding="utf-8"))
+        except (json.JSONDecodeError, PermissionError):
+            pass
+
+    task_title = task_data.get("title", task_ref)
+    task_status = task_data.get("status", "unknown")
+
+    # Case 3: Task completed — time to archive
+    if task_status == "completed":
+        return (
+            f"Status: COMPLETED\nTask: {task_title}\n"
+            f"Source: {active.source}\n"
+            f"Next-Action: Load skill `trellis-update-spec` to capture learnings, "
+            f"then archive with `python ./.trellis/scripts/task.py archive {task_dir.name}`."
+        )
+
+    has_prd = (task_dir / "prd.md").is_file()
+
+    # Case 4: No PRD — still in Plan phase
+    if not has_prd:
+        return (
+            f"Status: PLANNING\nTask: {task_title}\n"
+            f"Source: {active.source}\n"
+            "Next-Action: Load skill `trellis-brainstorm` to clarify requirements with the user "
+            "and produce prd.md in the task directory.\n"
+            "Research reminder: when the task needs external research (tool comparison, docs, "
+            "conventions survey), spawn `trellis-research` sub-agents — don't WebFetch/WebSearch "
+            "inline in the main session. Findings go to `{task_dir}/research/*.md`; PRD only links to them."
+        )
+
+    # Case 4b: PRD exists but implement.jsonl has only seed (no curated entries) — Phase 1.3 gate
+    implement_jsonl = task_dir / "implement.jsonl"
+    if implement_jsonl.is_file() and not _has_curated_jsonl_entry(implement_jsonl):
+        return (
+            f"Status: PLANNING (Phase 1.3)\nTask: {task_title}\n"
+            f"Source: {active.source}\n"
+            "Next-Action: Curate `implement.jsonl` and `check.jsonl` with the spec + research files "
+            "the Phase 2 sub-agents will need. Only spec paths (`.trellis/spec/**/*.md`) and research "
+            "files (`{TASK_DIR}/research/*.md`) — no code paths. Run "
+            "`python ./.trellis/scripts/get_context.py --mode packages` to list available specs, "
+            "then edit the jsonl files or use `python ./.trellis/scripts/task.py add-context`. "
+            "See `.trellis/workflow.md` Phase 1.3 for details."
+        )
+
+    # Case 5: PRD + curated jsonl (or agent-less platform with no jsonl) — enter Execute phase
+    return (
+        f"Status: READY\nTask: {task_title}\n"
+        f"Source: {active.source}\n"
+        "Next required action: dispatch `trellis-implement` per Phase 2.1. "
+        "For agent-capable platforms, the default is to NOT edit code in the main session. "
+        "After implementation, dispatch `trellis-check` per Phase 2.2 before reporting completion.\n"
+        "Sub-agent roster: `trellis-implement` (writes code), `trellis-check` (verifies + self-fixes), "
+        "`trellis-research` (persists findings to `research/*.md` — use when you'd otherwise do "
+        "multiple WebFetch/WebSearch inline).\n"
+        "Sub-agent self-exemption: if you are reading this as a `trellis-implement` or "
+        "`trellis-check` sub-agent (your own role / agent name reflects that), this dispatch "
+        "instruction does NOT apply to you — you are already the dispatched sub-agent. "
+        "Implement / check directly without spawning another sub-agent of the same kind.\n"
+        "User override (per-turn escape hatch): if the user's CURRENT message explicitly tells the "
+        "main session to handle it directly (\"你直接改\" / \"别派 sub-agent\" / \"main session 写就行\" / "
+        "\"do it inline\" / \"不用 sub-agent\"), honor it for this turn and edit code directly. "
+        "Per-turn only; do NOT invent an override the user did not say."
+    )
+
+
+def _load_trellis_config(trellis_dir: Path, input_data: dict) -> tuple:
+    """Load Trellis config for session-start decisions.
+
+    Returns:
+        (is_mono, packages_dict, spec_scope, task_pkg, default_pkg)
+    """
+    scripts_dir = trellis_dir / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+
+    try:
+        from common.config import get_default_package, get_packages, get_spec_scope, is_monorepo  # type: ignore[import-not-found]
+        from common.paths import get_current_task  # type: ignore[import-not-found]
+
+        repo_root = trellis_dir.parent
+        is_mono = is_monorepo(repo_root)
+        packages = get_packages(repo_root) or {}
+        scope = get_spec_scope(repo_root)
+
+        # Get active task's package
+        task_pkg = None
+        current = get_current_task(
+            repo_root,
+            input_data,
+            platform=_detect_platform(input_data),
+        )
+        if current:
+            task_json = repo_root / current / "task.json"
+            if task_json.is_file():
+                try:
+                    data = json.loads(task_json.read_text(encoding="utf-8"))
+                    if isinstance(data, dict):
+                        tp = data.get("package")
+                        if isinstance(tp, str) and tp:
+                            task_pkg = tp
+                except (json.JSONDecodeError, OSError):
+                    pass
+
+        default_pkg = get_default_package(repo_root)
+        return is_mono, packages, scope, task_pkg, default_pkg
+    except Exception:
+        return False, {}, None, None, None
+
+
+def _check_legacy_spec(trellis_dir: Path, is_mono: bool, packages: dict) -> str | None:
+    """Check for legacy spec directory structure in monorepo.
+
+    Returns warning message if legacy structure detected, None otherwise.
+    """
+    if not is_mono or not packages:
+        return None
+
+    spec_dir = trellis_dir / "spec"
+    if not spec_dir.is_dir():
+        return None
+
+    # Check for legacy flat spec dirs (spec/backend/, spec/frontend/ with index.md)
+    has_legacy = False
+    for legacy_name in ("backend", "frontend"):
+        legacy_dir = spec_dir / legacy_name
+        if legacy_dir.is_dir() and (legacy_dir / "index.md").is_file():
+            has_legacy = True
+            break
+
+    if not has_legacy:
+        return None
+
+    # Check which packages are missing spec/<pkg>/ directory
+    missing = [
+        name for name in sorted(packages.keys())
+        if not (spec_dir / name).is_dir()
+    ]
+
+    if not missing:
+        return None  # All packages have spec dirs
+
+    if len(missing) == len(packages):
+        return (
+            f"[!] Legacy spec structure detected: found `spec/backend/` or `spec/frontend/` "
+            f"but no package-scoped `spec/<package>/` directories.\n"
+            f"Monorepo packages: {', '.join(sorted(packages.keys()))}\n"
+            f"Please reorganize: `spec/backend/` -> `spec/<package>/backend/`"
+        )
+    return (
+        f"[!] Partial spec migration detected: packages {', '.join(missing)} "
+        f"still missing `spec/<pkg>/` directory.\n"
+        f"Please complete migration for all packages."
+    )
+
+
+def _resolve_spec_scope(
+    is_mono: bool,
+    packages: dict,
+    scope,
+    task_pkg: str | None,
+    default_pkg: str | None,
+) -> set | None:
+    """Resolve which packages should have their specs injected.
+
+    Returns:
+        Set of package names to include, or None for full scan.
+    """
+    if not is_mono or not packages:
+        return None  # Single-repo: full scan
+
+    if scope is None:
+        return None  # No scope configured: full scan
+
+    if isinstance(scope, str) and scope == "active_task":
+        if task_pkg and task_pkg in packages:
+            return {task_pkg}
+        if default_pkg and default_pkg in packages:
+            return {default_pkg}
+        return None  # Fallback to full scan
+
+    if isinstance(scope, list):
+        valid = set()
+        for entry in scope:
+            if entry in packages:
+                valid.add(entry)
+            else:
+                print(
+                    f"Warning: spec_scope contains unknown package: {entry}, ignoring",
+                    file=sys.stderr,
+                )
+
+        if valid:
+            # Warn if active task is out of scope
+            if task_pkg and task_pkg not in valid:
+                print(
+                    f"Warning: active task package '{task_pkg}' is out of configured spec_scope",
+                    file=sys.stderr,
+                )
+            return valid
+
+        # All entries invalid: fallback chain
+        print(
+            "Warning: all spec_scope entries invalid, falling back to task/default/full",
+            file=sys.stderr,
+        )
+        if task_pkg and task_pkg in packages:
+            return {task_pkg}
+        if default_pkg and default_pkg in packages:
+            return {default_pkg}
+        return None  # Full scan
+
+    return None  # Unknown scope type: full scan
+
+
+def _extract_range(content: str, start_header: str, end_header: str) -> str:
+    """Extract lines starting at `## start_header` up to (but excluding) `## end_header`.
+
+    Both parameters are full header lines WITHOUT the `## ` prefix (e.g. "Phase Index").
+    Returns empty string if start header is not found.
+    End header missing → extracts to end of file.
+    """
+    lines = content.splitlines()
+    start: int | None = None
+    end: int = len(lines)
+    start_match = f"## {start_header}"
+    end_match = f"## {end_header}"
+    for i, line in enumerate(lines):
+        stripped = line.strip()
+        if start is None and stripped == start_match:
+            start = i
+            continue
+        if start is not None and stripped == end_match:
+            end = i
+            break
+    if start is None:
+        return ""
+    return "\n".join(lines[start:end]).rstrip()
+
+
+_BREADCRUMB_TAG_RE = re.compile(
+    r"\[workflow-state:([A-Za-z0-9_-]+)\]\s*\n.*?\n\s*\[/workflow-state:\1\]",
+    re.DOTALL,
+)
+
+
+def _strip_breadcrumb_tag_blocks(content: str) -> str:
+    """Remove `[workflow-state:STATUS]...[/workflow-state:STATUS]` blocks.
+
+    The tag blocks live inside `## Phase Index` (since v0.5.0-rc.0, when
+    they were colocated with their phase summaries) and are consumed by the
+    UserPromptSubmit hook (`inject-workflow-state.py`). The session-start
+    payload already covers the full step bodies, so re-inlining the
+    breadcrumbs here would just duplicate context.
+    """
+    return _BREADCRUMB_TAG_RE.sub("", content)
+
+
+def _build_workflow_overview(workflow_path: Path) -> str:
+    """Inject the workflow guide for the session.
+
+    Contents:
+      1. Section index (all `## ` headings — navigation)
+      2. Phase Index section (rules, skill routing table, anti-rationalization table)
+      3. Phase 1/2/3 step-level details (the actual how-to for each step)
+
+    The meta sections (Core Principles / Trellis System / Customizing
+    Trellis) are NOT injected — Core Principles is short prose the AI can
+    Read on demand; Trellis System lists reference commands duplicated in
+    step bodies; Customizing Trellis is for forks. Workflow-state breadcrumb
+    tag blocks (which now live inside Phase Index since v0.5.0-rc.0) are
+    stripped from the extracted range — they're consumed by the
+    UserPromptSubmit hook, not the session-start preamble.
+
+    Total budget: Phase Index ~2 KB + Phase 1/2/3 ~7 KB = ~9 KB.
+    """
+    content = read_file(workflow_path)
+    if not content:
+        return "No workflow.md found"
+
+    out_lines = [
+        "# Development Workflow — Section Index",
+        "Full guide: .trellis/workflow.md  (read on demand)",
+        "",
+        "## Table of Contents",
+    ]
+    for line in content.splitlines():
+        if line.startswith("## "):
+            out_lines.append(line)
+    out_lines += ["", "---", ""]
+
+    # Extract Phase Index through the end of Phase 3 (before "Customizing
+    # Trellis" — the docs-for-forks footer added in v0.5.0-rc.0). Since
+    # sections appear in order Phase Index → Phase 1 → Phase 2 → Phase 3 →
+    # Customizing Trellis, a single range grab captures all four. The
+    # breadcrumb tag blocks now embedded inside Phase Index are stripped so
+    # they don't duplicate the per-turn UserPromptSubmit injection.
+    phases = _extract_range(
+        content, "Phase Index", "Customizing Trellis (for forks)"
+    )
+    if phases:
+        out_lines.append(_strip_breadcrumb_tag_blocks(phases).rstrip())
+
+    return "\n".join(out_lines).rstrip()
+
+
+def main():
+    if should_skip_injection():
+        sys.exit(0)
+
+    try:
+        hook_input = json.loads(sys.stdin.read())
+        if not isinstance(hook_input, dict):
+            hook_input = {}
+    except (json.JSONDecodeError, ValueError):
+        hook_input = {}
+
+    # Try platform-specific env vars, hook cwd, fallback to cwd
+    project_dir_env_vars = [
+        "CLAUDE_PROJECT_DIR",
+        "QODER_PROJECT_DIR",
+        "CODEBUDDY_PROJECT_DIR",
+        "FACTORY_PROJECT_DIR",
+        "CURSOR_PROJECT_DIR",
+        "GEMINI_PROJECT_DIR",
+        "KIRO_PROJECT_DIR",
+        "COPILOT_PROJECT_DIR",
+    ]
+    project_dir = None
+    for var in project_dir_env_vars:
+        val = os.environ.get(var)
+        if val:
+            project_dir = Path(_normalize_windows_shell_path(val)).resolve()
+            break
+    if project_dir is None:
+        project_dir = Path(_normalize_windows_shell_path(hook_input.get("cwd", "."))).resolve()
+
+    trellis_dir = project_dir / ".trellis"
+    context_key = _resolve_context_key(trellis_dir, hook_input)
+    _persist_context_key_for_bash(context_key)
+
+    # Load config for scope filtering and legacy detection
+    is_mono, packages, scope_config, task_pkg, default_pkg = _load_trellis_config(
+        trellis_dir,
+        hook_input,
+    )
+    allowed_pkgs = _resolve_spec_scope(is_mono, packages, scope_config, task_pkg, default_pkg)
+
+    output = StringIO()
+
+    output.write("""<session-context>
+You are starting a new session in a Trellis-managed project.
+Read and follow all instructions below carefully.
+</session-context>
+
+""")
+    output.write(FIRST_REPLY_NOTICE)
+    output.write("\n\n")
+
+    # Legacy migration warning
+    legacy_warning = _check_legacy_spec(trellis_dir, is_mono, packages)
+    if legacy_warning:
+        output.write(f"<migration-warning>\n{legacy_warning}\n</migration-warning>\n\n")
+
+    output.write("<current-state>\n")
+    context_script = trellis_dir / "scripts" / "get_context.py"
+    output.write(run_script(context_script, context_key))
+    output.write("\n</current-state>\n\n")
+
+    output.write("<workflow>\n")
+    output.write(_build_workflow_overview(trellis_dir / "workflow.md"))
+    output.write("\n</workflow>\n\n")
+
+    output.write("<guidelines>\n")
+    output.write(
+        "Project spec indexes are listed by path below. Each index contains a "
+        "**Pre-Development Checklist** listing the specific guideline files to "
+        "read before coding.\n\n"
+        "- If you're spawning an implement/check sub-agent, context is injected "
+        "or loaded by the sub-agent via `{task}/implement.jsonl` / `check.jsonl`. "
+        "You do NOT need to read these indexes yourself.\n"
+        "- For agent-capable platforms, the default is to dispatch "
+        "`trellis-implement` and `trellis-check` (so JSONL context is loaded by "
+        "the sub-agents) rather than editing code in the main session. "
+        "Honor a per-turn user override only if the user's current message "
+        "explicitly opts out (see <task-status> below for override phrases).\n"
+        "- Sub-agent self-exemption: if you are reading this as a `trellis-implement` "
+        "or `trellis-check` sub-agent, the \"dispatch trellis-implement / trellis-check\" "
+        "rule above does NOT apply to you — you are already the dispatched sub-agent. "
+        "Do NOT spawn another sub-agent of the same kind; implement / check directly.\n\n"
+    )
+
+    # guides/ is cross-package thinking — always include inline (small, broadly useful)
+    guides_index = trellis_dir / "spec" / "guides" / "index.md"
+    if guides_index.is_file():
+        output.write("## guides (inlined — cross-package thinking guides)\n")
+        output.write(read_file(guides_index))
+        output.write("\n\n")
+
+    # Other spec indexes — paths only (main agent reads on demand;
+    # sub-agents get their specific specs via jsonl injection)
+    paths: list[str] = []
+    spec_dir = trellis_dir / "spec"
+    if spec_dir.is_dir():
+        for sub in sorted(spec_dir.iterdir()):
+            if not sub.is_dir() or sub.name.startswith("."):
+                continue
+            if sub.name == "guides":
+                continue  # already inlined above
+
+            index_file = sub / "index.md"
+            if index_file.is_file():
+                # Flat spec dir (single-repo layer like spec/backend/)
+                paths.append(f".trellis/spec/{sub.name}/index.md")
+            else:
+                # Nested package dirs (monorepo: spec/<pkg>/<layer>/index.md)
+                # Apply scope filter
+                if allowed_pkgs is not None and sub.name not in allowed_pkgs:
+                    continue
+                for nested in sorted(sub.iterdir()):
+                    if not nested.is_dir():
+                        continue
+                    nested_index = nested / "index.md"
+                    if nested_index.is_file():
+                        paths.append(
+                            f".trellis/spec/{sub.name}/{nested.name}/index.md"
+                        )
+
+    if paths:
+        output.write("## Available spec indexes (read on demand)\n")
+        for p in paths:
+            output.write(f"- {p}\n")
+        output.write("\n")
+
+    output.write(
+        "Discover more via: "
+        "`python ./.trellis/scripts/get_context.py --mode packages`\n"
+    )
+    output.write("</guidelines>\n\n")
+
+    # Check task status and inject structured tag
+    task_status = _get_task_status(trellis_dir, hook_input)
+    output.write(f"<task-status>\n{task_status}\n</task-status>\n\n")
+
+    output.write("""<ready>
+Context loaded. Workflow index, project state, and guidelines are already injected above — do NOT re-read them.
+When the user sends the first message, follow <task-status> and the workflow guide.
+If a task is READY, execute its Next required action without asking whether to continue.
+</ready>""")
+
+    context_text = output.getvalue()
+    result = {
+        # Claude Code / Qoder / CodeBuddy / Droid / Gemini / Copilot format
+        "hookSpecificOutput": {
+            "hookEventName": "SessionStart",
+            "additionalContext": context_text,
+        },
+        # Cursor sessionStart format (top-level snake_case per Cursor docs)
+        "additional_context": context_text,
+    }
+
+    # Output JSON - stdout is already configured for UTF-8
+    print(json.dumps(result, ensure_ascii=False), flush=True)
+
+
+if __name__ == "__main__":
+    main()

.claude/settings.json

@@ -0,0 +1,73 @@
+{
+  "env": {
+    "CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR": "1"
+  },
+  "hooks": {
+    "SessionStart": [
+      {
+        "matcher": "startup",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python .claude/hooks/session-start.py",
+            "timeout": 30
+          }
+        ]
+      },
+      {
+        "matcher": "clear",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python .claude/hooks/session-start.py",
+            "timeout": 30
+          }
+        ]
+      },
+      {
+        "matcher": "compact",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python .claude/hooks/session-start.py",
+            "timeout": 30
+          }
+        ]
+      }
+    ],
+    "PreToolUse": [
+      {
+        "matcher": "Task",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python .claude/hooks/inject-subagent-context.py",
+            "timeout": 30
+          }
+        ]
+      },
+      {
+        "matcher": "Agent",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python .claude/hooks/inject-subagent-context.py",
+            "timeout": 30
+          }
+        ]
+      }
+    ],
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python .claude/hooks/inject-workflow-state.py",
+            "timeout": 15
+          }
+        ]
+      }
+    ]
+  },
+  "enabledPlugins": {}
+}

.claude/skills/trellis-before-dev/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: trellis-before-dev
+description: "Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards."
+---
+
+Read the relevant development guidelines before starting your task.
+
+Execute these steps:
+
+1. **Discover packages and their spec layers**:
+   ```bash
+   python ./.trellis/scripts/get_context.py --mode packages
+   ```
+
+2. **Identify which specs apply** to your task based on:
+   - Which package you're modifying (e.g., `cli/`, `docs-site/`)
+   - What type of work (backend, frontend, unit-test, docs, etc.)
+
+3. **Read the spec index** for each relevant module:
+   ```bash
+   cat .trellis/spec/<package>/<layer>/index.md
+   ```
+   Follow the **"Pre-Development Checklist"** section in the index.
+
+4. **Read the specific guideline files** listed in the Pre-Development Checklist that are relevant to your task. The index is NOT the goal — it points you to the actual guideline files (e.g., `error-handling.md`, `conventions.md`, `mock-strategies.md`). Read those files to understand the coding standards and patterns.
+
+5. **Always read shared guides**:
+   ```bash
+   cat .trellis/spec/guides/index.md
+   ```
+
+6. Understand the coding standards and patterns you need to follow, then proceed with your development plan.
+
+This step is **mandatory** before writing any code.

.claude/skills/trellis-brainstorm/SKILL.md

@@ -0,0 +1,548 @@
+---
+name: trellis-brainstorm
+description: "Guides collaborative requirements discovery before implementation. Creates task directory, seeds PRD, asks high-value questions one at a time, researches technical choices, and converges on MVP scope. Use when requirements are unclear, there are multiple valid approaches, or the user describes a new feature or complex task."
+---
+
+# Brainstorm - Requirements Discovery (AI Coding Enhanced)
+
+**CoreRule**: Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+
+Ask the questions one at a time.
+
+If a question can be answered by exploring the codebase, explore the codebase instead.
+
+---
+
+Guide AI through collaborative requirements discovery **before implementation**, optimized for AI coding workflows:
+
+* **Task-first** (capture ideas immediately)
+* **Action-before-asking** (reduce low-value questions)
+* **Research-first** for technical choices (avoid asking users to invent options)
+* **Diverge → Converge** (expand thinking, then lock MVP)
+
+---
+
+## When to Use
+
+Triggered from /trellis:start when the user describes a development task, especially when:
+
+* requirements are unclear or evolving
+* there are multiple valid implementation paths
+* trade-offs matter (UX, reliability, maintainability, cost, performance)
+* the user might not know the best options up front
+
+---
+
+## Core Principles (Non-negotiable)
+
+1. **Task-first (capture early)**
+   Always ensure a task exists at the start so the user's ideas are recorded immediately.
+
+2. **Action before asking**
+   If you can derive the answer from repo code, docs, configs, conventions, or quick research — do that first.
+
+3. **One question per message**
+   Never overwhelm the user with a list of questions. Ask one, update PRD, repeat.
+
+4. **Prefer concrete options**
+   For preference/decision questions, present 2–3 feasible, specific approaches with trade-offs.
+
+5. **Research-first for technical choices**
+   If the decision depends on industry conventions / similar tools / established patterns, do research first, then propose options.
+
+6. **Diverge → Converge**
+   After initial understanding, proactively consider future evolution, related scenarios, and failure/edge cases — then converge to an MVP with explicit out-of-scope.
+
+7. **No meta questions**
+   Do not ask "should I search?" or "can you paste the code so I can continue?"
+   If you need information: search/inspect. If blocked: ask the minimal blocking question.
+
+---
+
+## Step 0: Ensure Task Exists (ALWAYS)
+
+Before any Q&A, ensure a task exists. If none exists, create one immediately.
+
+* Use a **temporary working title** derived from the user's message.
+* It's OK if the title is imperfect — refine later in PRD.
+
+```bash
+TASK_DIR=$(python ./.trellis/scripts/task.py create "brainstorm: <short goal>" --slug <auto>)
+```
+
+Use a slug without a date prefix. `task.py create` adds the `MM-DD-`
+directory prefix automatically.
+
+Create/seed `prd.md` immediately with what you know:
+
+```markdown
+# brainstorm: <short goal>
+
+## Goal
+
+<one paragraph: what + why>
+
+## What I already know
+
+* <facts from user message>
+* <facts discovered from repo/docs>
+
+## Assumptions (temporary)
+
+* <assumptions to validate>
+
+## Open Questions
+
+* <ONLY Blocking / Preference questions; keep list short>
+
+## Requirements (evolving)
+
+* <start with what is known>
+
+## Acceptance Criteria (evolving)
+
+* [ ] <testable criterion>
+
+## Definition of Done (team quality bar)
+
+* Tests added/updated (unit/integration where appropriate)
+* Lint / typecheck / CI green
+* Docs/notes updated if behavior changes
+* Rollout/rollback considered if risky
+
+## Out of Scope (explicit)
+
+* <what we will not do in this task>
+
+## Technical Notes
+
+* <files inspected, constraints, links, references>
+* <research notes summary if applicable>
+```
+
+---
+
+## Step 1: Auto-Context (DO THIS BEFORE ASKING QUESTIONS)
+
+Before asking questions like "what does the code look like?", gather context yourself:
+
+### Repo inspection checklist
+
+* Identify likely modules/files impacted
+* Locate existing patterns (similar features, conventions, error handling style)
+* Check configs, scripts, existing command definitions
+* Note any constraints (runtime, dependency policy, build tooling)
+
+### Documentation checklist
+
+* Look for existing PRDs/specs/templates
+* Look for command usage examples, README, ADRs if any
+
+Write findings into PRD:
+
+* Add to `What I already know`
+* Add constraints/links to `Technical Notes`
+
+---
+
+## Step 2: Classify Complexity (still useful, not gating task creation)
+
+| Complexity   | Criteria                                               | Action                                      |
+| ------------ | ------------------------------------------------------ | ------------------------------------------- |
+| **Trivial**  | Single-line fix, typo, obvious change                  | Skip brainstorm, implement directly         |
+| **Simple**   | Clear goal, 1–2 files, scope well-defined              | Ask 1 confirm question, then implement      |
+| **Moderate** | Multiple files, some ambiguity                         | Light brainstorm (2–3 high-value questions) |
+| **Complex**  | Vague goal, architectural choices, multiple approaches | Full brainstorm                             |
+
+> Note: Task already exists from Step 0. Classification only affects depth of brainstorming.
+
+---
+
+## Step 3: Question Gate (Ask ONLY high-value questions)
+
+Before asking ANY question, run the following gate:
+
+### Gate A — Can I derive this without the user?
+
+If answer is available via:
+
+* repo inspection (code/config)
+* docs/specs/conventions
+* quick market/OSS research
+
+→ **Do not ask.** Fetch it, summarize, update PRD.
+
+### Gate B — Is this a meta/lazy question?
+
+Examples:
+
+* "Should I search?"
+* "Can you paste the code so I can proceed?"
+* "What does the code look like?" (when repo is available)
+
+→ **Do not ask.** Take action.
+
+### Gate C — What type of question is it?
+
+* **Blocking**: cannot proceed without user input
+* **Preference**: multiple valid choices, depends on product/UX/risk preference
+* **Derivable**: should be answered by inspection/research
+
+→ Only ask **Blocking** or **Preference**.
+
+---
+
+## Step 4: Research-first Mode (Mandatory for technical choices)
+
+### Trigger conditions (any → research-first)
+
+* The task involves selecting an approach, library, protocol, framework, template system, plugin mechanism, or CLI UX convention
+* The user asks for "best practice", "how others do it", "recommendation"
+* The user can't reasonably enumerate options
+
+### Delegate to `trellis-research` sub-agent (don't research inline)
+
+For each research topic, **spawn a `trellis-research` sub-agent via the Task tool** — don't do WebFetch / WebSearch / `gh api` inline in the main conversation.
+
+Why:
+- The sub-agent has its own context window → doesn't pollute brainstorm context with raw tool output
+- It persists findings to `{TASK_DIR}/research/<topic>.md` (the contract — see `workflow.md` Phase 1.2)
+- It returns only `{file path, one-line summary}` to the main agent
+- Independent topics can be **parallelized** — spawn multiple sub-agents in one tool call
+
+> **Codex exception**: on Codex CLI, do NOT dispatch `trellis-research` for research-first mode — do the research inline (WebFetch / WebSearch in the main session) and write findings to `{TASK_DIR}/research/<topic>.md` yourself. Reason: Codex `spawn_agent` runs sub-agents with `fork_turns="none"` (isolated context, no parent session inheritance), so the research sub-agent cannot resolve the active task path via `task.py current` and silently aborts without producing files. Inline research on Codex avoids this failure mode. The 3+ inline research calls limit (B rule in `workflow.md`) is relaxed for Codex specifically.
+
+Agent type: `trellis-research`
+Task description template: "Research <specific question>; persist findings to `{TASK_DIR}/research/<topic-slug>.md`."
+
+❌ Bad (what you must NOT do):
+```
+Main agent: WebFetch(url-A) → WebFetch(url-B) → Bash(gh api ...)
+          → WebSearch(q1) → WebSearch(q2) → ... (10+ inline calls)
+          → Write(research/topic.md)
+```
+→ Pollutes main context with raw HTML/JSON, burns tokens.
+
+✅ Good:
+```
+Main agent: Task(subagent_type="trellis-research",
+                 prompt="Research topic A; persist to research/topic-a.md")
+          + Task(subagent_type="trellis-research",
+                 prompt="Research topic B; persist to research/topic-b.md")
+          + Task(subagent_type="trellis-research",
+                 prompt="Research topic C; persist to research/topic-c.md")
+→ Reads research/topic-{a,b,c}.md after they finish.
+```
+
+### Research steps (to pass into each sub-agent prompt)
+
+Each `trellis-research` sub-agent should:
+
+1. Identify 2–4 comparable tools/patterns for its topic
+2. Summarize common conventions and why they exist
+3. Map conventions onto our repo constraints
+4. Write findings to `{TASK_DIR}/research/<topic>.md`
+
+Main agent then reads the persisted files and produces **2–3 feasible approaches** in PRD.
+
+### Research output format (PRD)
+
+The PRD itself should only reference the persisted research files, not duplicate their content. Add a `## Research References` section pointing at `research/*.md`.
+
+Optionally, add a convergence section with feasible approaches derived from the research:
+
+```markdown
+## Research References
+
+* [`research/<topic-a>.md`](research/<topic-a>.md) — <one-line takeaway>
+* [`research/<topic-b>.md`](research/<topic-b>.md) — <one-line takeaway>
+
+## Research Notes
+
+### What similar tools do
+
+* ...
+* ...
+
+### Constraints from our repo/project
+
+* ...
+
+### Feasible approaches here
+
+**Approach A: <name>** (Recommended)
+
+* How it works:
+* Pros:
+* Cons:
+
+**Approach B: <name>**
+
+* How it works:
+* Pros:
+* Cons:
+
+**Approach C: <name>** (optional)
+
+* ...
+```
+
+Then ask **one** preference question:
+
+* "Which approach do you prefer: A / B / C (or other)?"
+
+---
+
+## Step 5: Expansion Sweep (DIVERGE) — Required after initial understanding
+
+After you can summarize the goal, proactively broaden thinking before converging.
+
+### Expansion categories (keep to 1–2 bullets each)
+
+1. **Future evolution**
+
+   * What might this feature become in 1–3 months?
+   * What extension points are worth preserving now?
+
+2. **Related scenarios**
+
+   * What adjacent commands/flows should remain consistent with this?
+   * Are there parity expectations (create vs update, import vs export, etc.)?
+
+3. **Failure & edge cases**
+
+   * Conflicts, offline/network failure, retries, idempotency, compatibility, rollback
+   * Input validation, security boundaries, permission checks
+
+### Expansion message template (to user)
+
+```markdown
+I understand you want to implement: <current goal>.
+
+Before diving into design, let me quickly diverge to consider three categories (to avoid rework later):
+
+1. Future evolution: <1–2 bullets>
+2. Related scenarios: <1–2 bullets>
+3. Failure/edge cases: <1–2 bullets>
+
+For this MVP, which would you like to include (or none)?
+
+1. Current requirement only (minimal viable)
+2. Add <X> (reserve for future extension)
+3. Add <Y> (improve robustness/consistency)
+4. Other: describe your preference
+```
+
+Then update PRD:
+
+* What's in MVP → `Requirements`
+* What's excluded → `Out of Scope`
+
+---
+
+## Step 6: Q&A Loop (CONVERGE)
+
+### Rules
+
+* One question per message
+* Prefer multiple-choice when possible
+* After each user answer:
+
+  * Update PRD immediately
+  * Move answered items from `Open Questions` → `Requirements`
+  * Update `Acceptance Criteria` with testable checkboxes
+  * Clarify `Out of Scope`
+
+### Question priority (recommended)
+
+1. **MVP scope boundary** (what is included/excluded)
+2. **Preference decisions** (after presenting concrete options)
+3. **Failure/edge behavior** (only for MVP-critical paths)
+4. **Success metrics & Acceptance Criteria** (what proves it works)
+
+### Preferred question format (multiple choice)
+
+```markdown
+For <topic>, which approach do you prefer?
+
+1. **Option A** — <what it means + trade-off>
+2. **Option B** — <what it means + trade-off>
+3. **Option C** — <what it means + trade-off>
+4. **Other** — describe your preference
+```
+
+---
+
+## Step 7: Propose Approaches + Record Decisions (Complex tasks)
+
+After requirements are clear enough, propose 2–3 approaches (if not already done via research-first):
+
+```markdown
+Based on current information, here are 2–3 feasible approaches:
+
+**Approach A: <name>** (Recommended)
+
+* How:
+* Pros:
+* Cons:
+
+**Approach B: <name>**
+
+* How:
+* Pros:
+* Cons:
+
+Which direction do you prefer?
+```
+
+Record the outcome in PRD as an ADR-lite section:
+
+```markdown
+## Decision (ADR-lite)
+
+**Context**: Why this decision was needed
+**Decision**: Which approach was chosen
+**Consequences**: Trade-offs, risks, potential future improvements
+```
+
+---
+
+## Step 8: Final Confirmation + Implementation Plan
+
+When open questions are resolved, confirm complete requirements with a structured summary:
+
+### Final confirmation format
+
+```markdown
+Here's my understanding of the complete requirements:
+
+**Goal**: <one sentence>
+
+**Requirements**:
+
+* ...
+* ...
+
+**Acceptance Criteria**:
+
+* [ ] ...
+* [ ] ...
+
+**Definition of Done**:
+
+* ...
+
+**Out of Scope**:
+
+* ...
+
+**Technical Approach**:
+<brief summary + key decisions>
+
+**Implementation Plan (small PRs)**:
+
+* PR1: <scaffolding + tests + minimal plumbing>
+* PR2: <core behavior>
+* PR3: <edge cases + docs + cleanup>
+
+Does this look correct? If yes, I'll proceed with implementation.
+```
+
+### Subtask Decomposition (Complex Tasks)
+
+For complex tasks with multiple independent work items, create subtasks:
+
+```bash
+# Create child tasks
+CHILD1=$(python ./.trellis/scripts/task.py create "Child task 1" --slug child1 --parent "$TASK_DIR")
+CHILD2=$(python ./.trellis/scripts/task.py create "Child task 2" --slug child2 --parent "$TASK_DIR")
+
+# Or link existing tasks
+python ./.trellis/scripts/task.py add-subtask "$TASK_DIR" "$CHILD_DIR"
+```
+
+---
+
+## PRD Target Structure (final)
+
+`prd.md` should converge to:
+
+```markdown
+# <Task Title>
+
+## Goal
+
+<why + what>
+
+## Requirements
+
+* ...
+
+## Acceptance Criteria
+
+* [ ] ...
+
+## Definition of Done
+
+* ...
+
+## Technical Approach
+
+<key design + decisions>
+
+## Decision (ADR-lite)
+
+Context / Decision / Consequences
+
+## Out of Scope
+
+* ...
+
+## Technical Notes
+
+<constraints, references, files, research notes>
+```
+
+---
+
+## Anti-Patterns (Hard Avoid)
+
+* Asking user for code/context that can be derived from repo
+* Asking user to choose an approach before presenting concrete options
+* Meta questions about whether to research
+* Staying narrowly on the initial request without considering evolution/edges
+* Letting brainstorming drift without updating PRD
+
+---
+
+## Integration with Start Workflow
+
+After brainstorm completes (Step 8 confirmation approved), the flow continues to the Task Workflow's **Phase 2: Prepare for Implementation**:
+
+```text
+Brainstorm
+  Step 0: Create task directory + seed PRD
+  Step 1–7: Discover requirements, research, converge
+  Step 8: Final confirmation → user approves
+  ↓
+Task Workflow Phase 2 (Prepare for Implementation)
+  Code-Spec Depth Check (if applicable)
+  → Research codebase (based on confirmed PRD)
+  → Configure code-spec context (jsonl files)
+  → Activate task
+  ↓
+Task Workflow Phase 3 (Execute)
+  Implement → Check → Complete
+```
+
+The task directory and PRD already exist from brainstorm, so Phase 1 of the Task Workflow is skipped entirely.
+
+---
+
+## Related Commands
+
+| Command | When to Use |
+|---------|-------------|
+| `/trellis:start` | Entry point that triggers brainstorm |
+| `/trellis:finish-work` | After implementation is complete |
+| `/trellis:update-spec` | If new patterns emerge during work |

.claude/skills/trellis-break-loop/SKILL.md

@@ -0,0 +1,130 @@
+---
+name: trellis-break-loop
+description: "Deep bug analysis to break the fix-forget-repeat cycle. Analyzes root cause category, why fixes failed, prevention mechanisms, and captures knowledge into specs. Use after fixing a bug to prevent the same class of bugs."
+---
+
+# Break the Loop - Deep Bug Analysis
+
+When debug is complete, use this for deep analysis to break the "fix bug -> forget -> repeat" cycle.
+
+---
+
+## Analysis Framework
+
+Analyze the bug you just fixed from these 5 dimensions:
+
+### 1. Root Cause Category
+
+Which category does this bug belong to?
+
+| Category | Characteristics | Example |
+|----------|-----------------|---------|
+| **A. Missing Spec** | No documentation on how to do it | New feature without checklist |
+| **B. Cross-Layer Contract** | Interface between layers unclear | API returns different format than expected |
+| **C. Change Propagation Failure** | Changed one place, missed others | Changed function signature, missed call sites |
+| **D. Test Coverage Gap** | Unit test passes, integration fails | Works alone, breaks when combined |
+| **E. Implicit Assumption** | Code relies on undocumented assumption | Timestamp seconds vs milliseconds |
+
+### 2. Why Fixes Failed (if applicable)
+
+If you tried multiple fixes before succeeding, analyze each failure:
+
+- **Surface Fix**: Fixed symptom, not root cause
+- **Incomplete Scope**: Found root cause, didn't cover all cases
+- **Tool Limitation**: grep missed it, type check wasn't strict
+- **Mental Model**: Kept looking in same layer, didn't think cross-layer
+
+### 3. Prevention Mechanisms
+
+What mechanisms would prevent this from happening again?
+
+| Type | Description | Example |
+|------|-------------|---------|
+| **Documentation** | Write it down so people know | Update thinking guide |
+| **Architecture** | Make the error impossible structurally | Type-safe wrappers |
+| **Compile-time** | Strict type checking, no escape hatches | Signature change causes compile error |
+| **Runtime** | Monitoring, alerts, scans | Detect orphan entities |
+| **Test Coverage** | E2E tests, integration tests | Verify full flow |
+| **Code Review** | Checklist, PR template | "Did you check X?" |
+
+### 4. Systematic Expansion
+
+What broader problems does this bug reveal?
+
+- **Similar Issues**: Where else might this problem exist?
+- **Design Flaw**: Is there a fundamental architecture issue?
+- **Process Flaw**: Is there a development process improvement?
+- **Knowledge Gap**: Is the team missing some understanding?
+
+### 5. Knowledge Capture
+
+Solidify insights into the system:
+
+- [ ] Update `.trellis/spec/guides/` thinking guides
+- [ ] Update relevant `.trellis/spec/` docs
+- [ ] Create issue record (if applicable)
+- [ ] Create feature ticket for root fix
+- [ ] Update check guidelines if needed
+
+---
+
+## Output Format
+
+Please output analysis in this format:
+
+```markdown
+## Bug Analysis: [Short Description]
+
+### 1. Root Cause Category
+- **Category**: [A/B/C/D/E] - [Category Name]
+- **Specific Cause**: [Detailed description]
+
+### 2. Why Fixes Failed (if applicable)
+1. [First attempt]: [Why it failed]
+2. [Second attempt]: [Why it failed]
+...
+
+### 3. Prevention Mechanisms
+| Priority | Mechanism | Specific Action | Status |
+|----------|-----------|-----------------|--------|
+| P0 | ... | ... | TODO/DONE |
+
+### 4. Systematic Expansion
+- **Similar Issues**: [List places with similar problems]
+- **Design Improvement**: [Architecture-level suggestions]
+- **Process Improvement**: [Development process suggestions]
+
+### 5. Knowledge Capture
+- [ ] [Documents to update / tickets to create]
+```
+
+---
+
+## Core Philosophy
+
+> **The value of debugging is not in fixing the bug, but in making this class of bugs never happen again.**
+
+Three levels of insight:
+1. **Tactical**: How to fix THIS bug
+2. **Strategic**: How to prevent THIS CLASS of bugs
+3. **Philosophical**: How to expand thinking patterns
+
+30 minutes of analysis saves 30 hours of future debugging.
+
+---
+
+## After Analysis: Immediate Actions
+
+**IMPORTANT**: After completing the analysis above, you MUST immediately:
+
+1. **Update spec/guides** - Don't just list TODOs, actually update the relevant files:
+   - If it's a cross-platform issue → update `cross-platform-thinking-guide.md`
+   - If it's a cross-layer issue → update `cross-layer-thinking-guide.md`
+   - If it's a code reuse issue → update `code-reuse-thinking-guide.md`
+   - If it's domain-specific → update `backend/*.md` or `frontend/*.md`
+
+2. **Sync templates** - After updating `.trellis/spec/`, sync to `src/templates/markdown/spec/`
+
+3. **Commit the spec updates** - This is the primary output, not just the analysis text
+
+> **The analysis is worthless if it stays in chat. The value is in the updated specs.**

.claude/skills/trellis-check/SKILL.md

@@ -0,0 +1,92 @@
+---
+name: trellis-check
+description: "Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions."
+---
+
+# Code Quality Check
+
+Comprehensive quality verification for recently written code. Combines spec compliance, cross-layer safety, and pre-commit checks.
+
+---
+
+## Step 1: Identify What Changed
+
+```bash
+git diff --name-only HEAD
+git status
+```
+
+## Step 2: Read Applicable Specs
+
+```bash
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+For each changed package/layer, read the spec index and follow its **Quality Check** section:
+
+```bash
+cat .trellis/spec/<package>/<layer>/index.md
+```
+
+Read the specific guideline files referenced — the index is a pointer, not the goal.
+
+## Step 3: Run Project Checks
+
+Run the project's lint, type-check, and test commands. Fix any failures before proceeding.
+
+## Step 4: Review Against Checklist
+
+### Code Quality
+
+- [ ] Linter passes?
+- [ ] Type checker passes (if applicable)?
+- [ ] Tests pass?
+- [ ] No debug logging left in?
+- [ ] No suppressed warnings or type-safety bypasses?
+
+### Test Coverage
+
+- [ ] New function → unit test added?
+- [ ] Bug fix → regression test added?
+- [ ] Changed behavior → existing tests updated?
+
+### Spec Sync
+
+- [ ] Does `.trellis/spec/` need updates? (new patterns, conventions, lessons learned)
+
+> "If I fixed a bug or discovered something non-obvious, should I document it so future me won't hit the same issue?" → If YES, update the relevant spec doc.
+
+## Step 5: Cross-Layer Dimensions (if applicable)
+
+Skip this step if your change is confined to a single layer.
+
+### A. Data Flow (changes touch 3+ layers)
+
+- [ ] Read flow traces correctly: Storage → Service → API → UI
+- [ ] Write flow traces correctly: UI → API → Service → Storage
+- [ ] Types/schemas correctly passed between layers?
+- [ ] Errors properly propagated to caller?
+
+### B. Code Reuse (modifying constants, creating utilities)
+
+- [ ] Searched for existing similar code before creating new?
+  ```bash
+  grep -r "pattern" src/
+  ```
+- [ ] If 2+ places define same value → extracted to shared constant?
+- [ ] After batch modification, all occurrences updated?
+
+### C. Import/Dependency (creating new files)
+
+- [ ] Correct import paths (relative vs absolute)?
+- [ ] No circular dependencies?
+
+### D. Same-Layer Consistency
+
+- [ ] Other places using the same concept are consistent?
+
+---
+
+## Step 6: Report and Fix
+
+Report violations found and fix them directly. Re-run project checks after fixes.

.claude/skills/trellis-meta/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: trellis-meta
+description: "Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, or workflows generated by trellis init."
+---
+
+# Trellis Meta
+
+This skill is for local Trellis users who have already run `trellis init` in a project. After reading it, an AI should understand the Trellis architecture, operating model, and customization entry points inside that user project, then modify the generated `.trellis/` and platform directory files according to the user's request.
+
+The default operating scope is local files in the user project:
+
+- `.trellis/`: workflow, config, tasks, spec, workspace, scripts, and runtime state.
+- Platform directories: `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, `.kiro/`, `.gemini/`, `.qoder/`, `.codebuddy/`, `.github/`, `.factory/`, `.pi/`, `.kilocode/`, `.agent/`, `.windsurf/`, and similar directories.
+- Shared skill layer: `.agents/skills/`.
+
+Do not assume the user has the Trellis source repository. Do not default to modifying the global npm install directory or `node_modules`.
+
+## How To Use
+
+1. Read `references/local-architecture/overview.md` first to establish the local Trellis system model.
+2. If the request involves a specific AI tool, read `references/platform-files/platform-map.md` and the relevant platform file notes.
+3. If the user wants to change behavior, read `references/customize-local/overview.md`, then open the specific customization topic.
+4. Before editing, read the actual files in the user project and treat local content as authoritative.
+
+## References
+
+### Local Architecture
+
+- `references/local-architecture/overview.md`: The three-layer local Trellis architecture and customization principles.
+- `references/local-architecture/generated-files.md`: Files generated by `trellis init` and their customization boundaries.
+- `references/local-architecture/workflow.md`: Phases, routing, and workflow-state blocks in `.trellis/workflow.md`.
+- `references/local-architecture/task-system.md`: Task directories, active tasks, JSONL context, and task runtime.
+- `references/local-architecture/spec-system.md`: How `.trellis/spec/` is organized and injected.
+- `references/local-architecture/workspace-memory.md`: `.trellis/workspace/`, journals, and cross-session memory.
+- `references/local-architecture/context-injection.md`: Hooks, sub-agent preludes, and context injection paths.
+
+### Platform Files
+
+- `references/platform-files/overview.md`: How shared `.trellis/` files relate to platform directories.
+- `references/platform-files/platform-map.md`: Platform directories and paths for skills, agents, hooks, and extensions.
+- `references/platform-files/hooks-and-settings.md`: How settings/config files, hooks, plugins, and extensions connect to Trellis.
+- `references/platform-files/agents.md`: Local file responsibilities for `trellis-research`, `trellis-implement`, and `trellis-check`.
+- `references/platform-files/skills-and-commands.md`: Differences between skills, commands, prompts, and workflows, plus how to change them.
+
+### Local Customization
+
+- `references/customize-local/overview.md`: Choose the right local customization entry point for the user's request.
+- `references/customize-local/change-workflow.md`: Change phases, routing, next actions, and workflow-state.
+- `references/customize-local/change-task-lifecycle.md`: Change task creation, status, archive behavior, and hooks.
+- `references/customize-local/change-context-loading.md`: Change how tasks, specs, journals, and hook context are loaded.
+- `references/customize-local/change-hooks.md`: Change platform hooks, settings, and shell session bridges.
+- `references/customize-local/change-agents.md`: Change research, implement, and check agent behavior.
+- `references/customize-local/change-skills-or-commands.md`: Add or modify local skills, commands, prompts, and workflows.
+- `references/customize-local/change-spec-structure.md`: Adjust the project spec structure under `.trellis/spec/`.
+- `references/customize-local/add-project-local-conventions.md`: Put team rules into project-local specs or local skills.
+
+## Current Rules
+
+- `.trellis/workflow.md` is the local workflow source of truth.
+- `.trellis/config.yaml` is the project-level Trellis configuration and task hook configuration entry point.
+- `.trellis/spec/` stores the user's project-specific coding conventions and design constraints.
+- `.trellis/tasks/` stores task PRDs, technical notes, research files, and JSONL context.
+- `.trellis/workspace/` stores developer journals and cross-session memory.
+- Platform settings/config files decide which hooks, agents, skills, commands, prompts, and workflows actually run.
+- `.trellis/.template-hashes.json` and `.trellis/.runtime/` are management/runtime state files. Confirm necessity before editing them.
+
+## Do Not
+
+- Do not treat Trellis upstream source code as the default target for local customization.
+- Do not modify the global npm install directory or `node_modules/@mindfoldhq/trellis` to implement project needs.
+- Do not overwrite user-modified local files with default templates.
+- Do not put team-private project rules into the public `trellis-meta`; put project rules in `.trellis/spec/` or a project-local skill.
+- Do not describe removed historical mechanisms as current Trellis behavior.

.claude/skills/trellis-meta/references/customize-local/add-project-local-conventions.md

@@ -0,0 +1,83 @@
+# Add Project-Local Conventions
+
+Often the user does not need to change Trellis mechanics; they need local AI to understand their team's conventions. In that case, prefer `.trellis/spec/` or a project-local skill instead of editing `trellis-meta`.
+
+## Where To Put Things
+
+| Content type | Location |
+| --- | --- |
+| Rules code must follow | `.trellis/spec/<layer>/` |
+| Cross-layer thinking methods | `.trellis/spec/guides/` |
+| AI capability for a project-specific flow | Platform-local skill |
+| One-off task material | `.trellis/tasks/<task>/` |
+| Session summary | `.trellis/workspace/<developer>/journal-N.md` |
+
+## Create A Project-Local Skill
+
+If the user wants AI to know "how this project customizes Trellis," create a local skill:
+
+```text
+.claude/skills/trellis-local/
+└── SKILL.md
+```
+
+Example:
+
+```md
+---
+name: trellis-local
+description: "Project-local Trellis customizations for this repository. Use when changing this project's Trellis workflow, hooks, local agents, or team-specific conventions."
+---
+
+# Trellis Local
+
+## Local Scope
+
+This skill documents this repository's Trellis customizations only.
+
+## Custom Workflow Rules
+
+- ...
+
+## Local Hook Changes
+
+- ...
+
+## Local Agent Changes
+
+- ...
+```
+
+For multi-platform projects, place equivalent versions in other platform skill directories, or use `.agents/skills/` for platforms that support the shared layer.
+
+## Write To `.trellis/spec/`
+
+If the content is a coding convention, write it to spec. Examples:
+
+```text
+.trellis/spec/backend/error-handling.md
+.trellis/spec/frontend/components.md
+.trellis/spec/guides/cross-platform-thinking-guide.md
+```
+
+After writing it, update the corresponding `index.md` so AI can find the new rule from the entry point.
+
+## Make The Current Task Use New Conventions
+
+After writing a spec, add it to the current task context:
+
+```bash
+python ./.trellis/scripts/task.py add-context <task> implement ".trellis/spec/backend/error-handling.md" "Error handling conventions"
+python ./.trellis/scripts/task.py add-context <task> check ".trellis/spec/backend/error-handling.md" "Review error handling"
+```
+
+## Do Not Store Project-Private Rules In `trellis-meta`
+
+`trellis-meta` is a public skill for understanding Trellis architecture and local customization entry points. Put project-private content in:
+
+- `.trellis/spec/`
+- a project-local skill
+- the current task
+- workspace journal
+
+This prevents future updates to Trellis's built-in `trellis-meta` from overwriting the team's own conventions.

.claude/skills/trellis-meta/references/customize-local/change-agents.md

@@ -0,0 +1,54 @@
+# Change Local Agents
+
+When the user wants to change `trellis-research`, `trellis-implement`, or `trellis-check` behavior, edit platform agent files in the user project.
+
+## Read These Files First
+
+1. Target platform agent directory
+2. `.trellis/workflow.md` Phase 2 / research routing
+3. Current task `prd.md`
+4. Current task `implement.jsonl` / `check.jsonl`
+5. Relevant hook or agent prelude
+
+## Common Paths
+
+| Platform | Path |
+| --- | --- |
+| Claude Code | `.claude/agents/trellis-*.md` |
+| Cursor | `.cursor/agents/trellis-*.md` |
+| OpenCode | `.opencode/agents/trellis-*.md` |
+| Codex | `.codex/agents/trellis-*.toml` |
+| Kiro | `.kiro/agents/trellis-*.json` |
+| Gemini CLI | `.gemini/agents/trellis-*.md` |
+| Qoder | `.qoder/agents/trellis-*.md` |
+| CodeBuddy | `.codebuddy/agents/trellis-*.md` |
+| Factory Droid | `.factory/droids/trellis-*.md` |
+| Pi Agent | `.pi/agents/trellis-*.md` |
+
+Use the actual paths in the user project as authoritative.
+
+## Common Needs
+
+| Need | Which agent to edit |
+| --- | --- |
+| Research must write files, not only reply in chat | `trellis-research` |
+| Certain local specs must be read before implementation | `trellis-implement` + `implement.jsonl` configuration rules |
+| Specific commands must run during checking | `trellis-check` |
+| Agent must not modify certain directories | The corresponding agent's write boundary instructions |
+| Agent output format must be fixed | The corresponding agent's final/reporting instructions |
+
+## Modification Principles
+
+1. **Preserve role boundaries**: research investigates and persists; implement writes implementation; check reviews and fixes.
+2. **Do not hard-code project specs into agents**: long-term specs belong in `.trellis/spec/`; agents are responsible for reading them.
+3. **Make read order explicit**: active task -> PRD -> info -> JSONL -> spec/research.
+4. **Make write boundaries explicit**: which directories may be written and which may not.
+5. **Synchronize across platforms**: when the user configured multiple platforms, decide whether to change only the current platform or all platform agents.
+
+## Agent Pull Platforms
+
+If an agent file contains a prelude for "read task/context after startup," do not remove those steps when editing. Otherwise the agent will work only from chat context and bypass Trellis's core mechanism.
+
+## Hook Push Platforms
+
+If context is injected by a hook, the agent file should still retain responsibility boundaries. Do not remove PRD/spec requirements from the agent just because a hook injects context.

.claude/skills/trellis-meta/references/customize-local/change-context-loading.md

@@ -0,0 +1,81 @@
+# Change Local Context Loading
+
+Context loading determines when AI reads workflow, task, spec, research, workspace, and git status. Read this page when the user says "AI does not know the current task," "the agent did not read specs," or "there is too much/too little context."
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. `.trellis/scripts/get_context.py`
+3. `.trellis/scripts/common/session_context.py`
+4. `.trellis/scripts/common/task_context.py`
+5. `.trellis/scripts/common/active_task.py`
+6. Current platform hooks or agent files
+7. The current task's `implement.jsonl` / `check.jsonl`
+
+## Context Sources
+
+| Source | Purpose |
+| --- | --- |
+| `.trellis/workflow.md` | Workflow and next-action hints. |
+| `.trellis/tasks/<task>/prd.md` | Current task requirements. |
+| `.trellis/tasks/<task>/implement.jsonl` | Spec/research to read before implementation. |
+| `.trellis/tasks/<task>/check.jsonl` | Spec/research to read during checking. |
+| `.trellis/spec/` | Project specs. |
+| `.trellis/workspace/` | Session records. |
+| git status | Current working tree changes. |
+
+## Common Needs And Edit Points
+
+| Need | Edit point |
+| --- | --- |
+| Inject more/less information in new sessions | `session_context.py` or the platform `session-start` hook. |
+| Change hints on each user input | `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The `inject-workflow-state` hook is parser-only and reads the block verbatim. |
+| Agent did not read specs | Task JSONL, agent prelude, `inject-subagent-context` hook. |
+| Active task is lost | `active_task.py` and platform session identity propagation. |
+| Change JSONL validation rules | `task_context.py`. |
+
+## JSONL Rules
+
+`implement.jsonl` / `check.jsonl` are the key context loading interface:
+
+```jsonl
+{"file": ".trellis/spec/backend/index.md", "reason": "Backend conventions"}
+{"file": ".trellis/tasks/04-28-x/research/api.md", "reason": "API research"}
+```
+
+Include only spec/research files. Do not put code files that will be modified into these manifests; agents read code files themselves during implementation.
+
+## Change Session Context
+
+If the user wants every new session to see more project state, edit:
+
+- `.trellis/scripts/common/session_context.py`
+- the corresponding platform `session-start` hook
+
+Context cannot grow without bound. Prefer injecting indexes and paths so the AI can read detailed files on demand.
+
+## Change Sub-Agent Context
+
+First determine which mode the platform uses:
+
+- hook push: edit the `inject-subagent-context` hook.
+- agent pull: edit the read steps in the corresponding `trellis-implement` / `trellis-check` agent file.
+
+In both modes, make sure the agent ultimately reads:
+
+1. active task
+2. `prd.md`
+3. `info.md` if present
+4. the corresponding JSONL
+5. spec/research referenced by the JSONL
+
+## Troubleshooting Order
+
+```bash
+python ./.trellis/scripts/task.py current --source
+python ./.trellis/scripts/task.py list-context <task>
+python ./.trellis/scripts/task.py validate <task>
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+Confirm the task and JSONL are correct before editing hooks/agents.

.claude/skills/trellis-meta/references/customize-local/change-hooks.md

@@ -0,0 +1,57 @@
+# Change Local Hooks
+
+Hooks are the automation layer that connects a platform to Trellis. When the user wants to change "when context is injected," "how shell commands inherit a session," or "which files are read before an agent starts," hooks are usually the edit point.
+
+## Read These Files First
+
+1. Target platform settings/config, such as `.claude/settings.json`, `.codex/hooks.json`, `.cursor/hooks.json`
+2. Target platform hooks directory
+3. `.trellis/scripts/common/active_task.py`
+4. `.trellis/scripts/common/session_context.py`
+5. `.trellis/workflow.md`
+
+## Common Hook Types
+
+| Hook | Purpose |
+| --- | --- |
+| session-start | Injects a Trellis overview when a session starts, clears, or compacts. |
+| workflow-state | Injects a state hint on each user input. |
+| sub-agent context | Injects PRD/spec/research before an agent starts. |
+| shell session bridge | Lets `task.py` commands in shell see the same session identity. |
+
+## Modification Steps
+
+1. Find the hook registration in settings/config.
+2. Confirm the registered script path exists.
+3. Read the hook script and identify inputs, outputs, and called `.trellis/scripts/`.
+4. Modify hook behavior.
+5. If the hook depends on workflow content, synchronize `.trellis/workflow.md`.
+
+## Example: Change New-Session Injection Content
+
+First find the session-start hook:
+
+```text
+.claude/settings.json
+.claude/hooks/session-start.py
+```
+
+If the hook ultimately calls `.trellis/scripts/get_context.py` or `session_context.py`, editing the local script is usually more robust than hard-coding content in the hook.
+
+## Example: Agent Did Not Read JSONL
+
+First confirm:
+
+```bash
+python ./.trellis/scripts/task.py current --source
+python ./.trellis/scripts/task.py validate <task>
+```
+
+If the task and JSONL are correct, determine whether the platform uses hook push or agent pull. For hook push, edit `inject-subagent-context`; for agent pull, edit the agent file.
+
+## Notes
+
+- Settings handle registration, hook scripts handle behavior; inspect both together.
+- Different platforms support different hook events. Do not directly copy another platform's settings.
+- Hooks should read project-local `.trellis/`; they should not depend on Trellis upstream source paths.
+- Hook failures should produce visible errors so AI does not silently lose context.

.claude/skills/trellis-meta/references/customize-local/change-skills-or-commands.md

@@ -0,0 +1,78 @@
+# Change Local Skills, Commands, Prompts, And Workflows
+
+When the user wants to change AI entry points, auto-trigger rules, or explicit command behavior, edit skills, commands, prompts, or workflows in local platform directories.
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. Target platform skill/command/prompt/workflow directory
+3. Related agent or hook files
+4. Whether project rules already exist in `.trellis/spec/`
+
+## Which Entry Type To Choose
+
+| Goal | Recommendation |
+| --- | --- |
+| AI should automatically know a capability | Add or modify a skill. |
+| User wants to trigger manually with a command | Add or modify a command/prompt/workflow. |
+| Team project conventions | Prefer `.trellis/spec/` or a project-local skill. |
+| Change Trellis flow semantics | Synchronize `.trellis/workflow.md`. |
+
+## Modify A Skill
+
+A skill is usually:
+
+```text
+<skill-name>/
+├── SKILL.md
+└── references/
+```
+
+`SKILL.md` should be short and responsible for triggering/routing. Put long content in `references/` so AI can read it on demand.
+
+The frontmatter description should specify when to use the skill. Example:
+
+```yaml
+description: "Use when customizing this project's deployment workflow and release checklist."
+```
+
+Do not write vague descriptions such as "helpful project skill"; they can trigger incorrectly.
+
+## Modify A Command/Prompt/Workflow
+
+Explicit entry points should state:
+
+- How the user triggers it.
+- Which `.trellis/` files to read.
+- Which scripts to run.
+- How to report after completion.
+
+If a command only repeats workflow rules, prefer making it reference/read `.trellis/workflow.md` instead of maintaining a second copy of the flow.
+
+## Common Paths
+
+| Platform | Entry directories |
+| --- | --- |
+| Claude Code | `.claude/skills/`, `.claude/commands/` |
+| Cursor | `.cursor/skills/`, `.cursor/commands/` |
+| OpenCode | `.opencode/skills/`, `.opencode/commands/` |
+| Codex | `.agents/skills/`, `.codex/skills/` |
+| GitHub Copilot | `.github/skills/`, `.github/prompts/` |
+| Kilo / Antigravity / Windsurf | workflows + skills |
+
+## Add A Project-Local Skill
+
+If the user wants to document team-private customizations, create a project-local skill, for example:
+
+```text
+.claude/skills/project-trellis-local/
+└── SKILL.md
+```
+
+For multi-platform projects, add equivalent versions in each platform skill directory, or use `.agents/skills/` on platforms that support the shared layer.
+
+## Notes
+
+- Do not mix every platform's syntax into one file.
+- Do not change only one platform entry point while claiming all platforms are supported.
+- Do not hide long-term engineering conventions inside a command; write them to `.trellis/spec/`.

.claude/skills/trellis-meta/references/customize-local/change-spec-structure.md

@@ -0,0 +1,83 @@
+# Change Local Spec Structure
+
+When the user wants to change the engineering conventions AI follows, add new spec layers, or adjust monorepo package mapping, edit `.trellis/spec/` and `.trellis/config.yaml`.
+
+## Read These Files First
+
+1. `.trellis/config.yaml`
+2. `.trellis/spec/`
+3. `.trellis/workflow.md` Phase 1.3 and Phase 3.3
+4. Current task `implement.jsonl` / `check.jsonl`
+
+## Common Needs
+
+| Need | Edit location |
+| --- | --- |
+| Add backend/frontend/docs/test spec layer | `.trellis/spec/<layer>/` or `.trellis/spec/<package>/<layer>/` |
+| Add shared thinking guides | `.trellis/spec/guides/` |
+| Adjust monorepo packages | `packages` in `.trellis/config.yaml` |
+| Change default package | `default_package` in `.trellis/config.yaml` |
+| Control spec scanning scope | `spec_scope` in `.trellis/config.yaml` |
+| Make a task read a new spec | Task `implement.jsonl` / `check.jsonl` |
+
+## Add A Spec Layer
+
+Single-repository example:
+
+```text
+.trellis/spec/security/
+├── index.md
+└── auth.md
+```
+
+Monorepo example:
+
+```text
+.trellis/spec/webapp/security/
+├── index.md
+└── auth.md
+```
+
+`index.md` should include:
+
+- What code this layer applies to.
+- Pre-Development Checklist.
+- Quality Check.
+- Links to specific guideline files.
+
+## Update Context
+
+Adding a spec does not mean every task automatically reads it. The current task must reference it in JSONL:
+
+```bash
+python ./.trellis/scripts/task.py add-context <task> implement ".trellis/spec/webapp/security/index.md" "Security conventions"
+python ./.trellis/scripts/task.py add-context <task> check ".trellis/spec/webapp/security/index.md" "Security review rules"
+```
+
+## Change Monorepo Packages
+
+Example `.trellis/config.yaml`:
+
+```yaml
+packages:
+  webapp:
+    path: apps/web
+  api:
+    path: apps/api
+default_package: webapp
+```
+
+After editing, run:
+
+```bash
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+Use this output to confirm AI can see the correct packages and spec layers.
+
+## Notes
+
+- Specs are user project conventions and can be changed according to project needs.
+- Do not put temporary task information into specs; put temporary information in the task.
+- Do not put long-term conventions only in agents or commands; preserve them in specs.
+- After changing spec structure, check whether existing task JSONL files still point to files that exist.

.claude/skills/trellis-meta/references/customize-local/change-task-lifecycle.md

@@ -0,0 +1,90 @@
+# Change Local Task Lifecycle
+
+Task lifecycle includes creation, start, context configuration, finish, archive, parent/child tasks, and lifecycle hooks. The default customization targets are `.trellis/tasks/`, `.trellis/config.yaml`, and `.trellis/scripts/`.
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. `.trellis/config.yaml`
+3. `.trellis/scripts/task.py`
+4. `.trellis/scripts/common/task_store.py`
+5. `.trellis/scripts/common/task_utils.py`
+6. The current task's `.trellis/tasks/<task>/task.json`
+
+## Common Needs And Edit Points
+
+| Need | Edit point |
+| --- | --- |
+| Automatically sync an external system after task creation | `hooks.after_create` in `.trellis/config.yaml`. |
+| Automatically update status after task start | `hooks.after_start` in `.trellis/config.yaml`. |
+| Run a script after task finish | `hooks.after_finish` in `.trellis/config.yaml`. |
+| Clean external resources after archive | `hooks.after_archive` in `.trellis/config.yaml`. |
+| Change default task fields | `.trellis/scripts/common/task_store.py`. |
+| Change task parsing/search | `.trellis/scripts/common/task_utils.py`. |
+| Change active task behavior | `.trellis/scripts/common/active_task.py`. |
+
+## lifecycle hooks
+
+`.trellis/config.yaml` supports:
+
+```yaml
+hooks:
+  after_create:
+    - "python .trellis/scripts/hooks/my_sync.py create"
+  after_start:
+    - "python .trellis/scripts/hooks/my_sync.py start"
+  after_finish:
+    - "python .trellis/scripts/hooks/my_sync.py finish"
+  after_archive:
+    - "python .trellis/scripts/hooks/my_sync.py archive"
+```
+
+Hook commands receive the `TASK_JSON_PATH` environment variable, pointing to the current task's `task.json`. Hook failures should usually warn, but not block the main task operation.
+
+## Change Task Fields
+
+If the user wants to add project-local fields, prefer putting them under `meta` in `task.json` to avoid breaking existing scripts' assumptions about standard fields.
+
+Example:
+
+```json
+"meta": {
+  "linearIssue": "ENG-123",
+  "risk": "high"
+}
+```
+
+If standard fields really need to change, inspect every local script that reads `task.json`.
+
+## Change Active Task
+
+Active task is session-level state stored in `.trellis/.runtime/sessions/`. Do not fall back to a global `.current-task` model. If the user wants to change active task behavior, edit:
+
+- `.trellis/scripts/common/active_task.py`
+- platform hooks or shell session bridges
+- active task descriptions in `.trellis/workflow.md`
+
+### `task.py create` Sets the Active Pointer
+
+`cmd_create` in `.trellis/scripts/common/task_store.py` calls `set_active_task` best-effort right after writing the new task directory. The behavior:
+
+- When the calling shell carries session identity (`TRELLIS_CONTEXT_ID` env var, or any platform-specific session env that `resolve_context_key` recognizes — see `active_task.py:_ENV_SESSION_KEYS`), the per-session pointer at `.trellis/.runtime/sessions/<context_key>.json` is rewritten to point at the new task. The task's `status=planning` and `[workflow-state:planning]` fires on the very next `UserPromptSubmit`.
+- When session identity is unavailable (raw CLI invocation outside an AI session, or a platform that doesn't propagate identity to shell), the task directory is still created and `status=planning` is still written, but the active pointer is left untouched. The user can attach the task later with `task.py start <dir>` once they're back in an AI session.
+
+This makes `[workflow-state:planning]` the live breadcrumb during the brainstorm and JSONL curation work that follows `task.py create`. The pre-R7 behavior left the breadcrumb stuck on `no_task` until `task.py start`, so the planning block was effectively dead text.
+
+If you fork `task.py` to add a new creation path (e.g. an external import that bypasses `cmd_create`), audit whether your path also calls `set_active_task`. Without that call, your created tasks will not surface as active. The full status writer table is in `.trellis/spec/cli/backend/workflow-state-contract.md`.
+
+## Modification Steps
+
+1. Confirm the current task with `python ./.trellis/scripts/task.py current --source`.
+2. Read the current task's `task.json` and confirm status and fields.
+3. For configuration needs, edit `.trellis/config.yaml` first.
+4. For script behavior needs, then edit `.trellis/scripts/`.
+5. If the AI flow changed, synchronize `.trellis/workflow.md`.
+
+## Do Not
+
+- Do not directly edit `.trellis/.runtime/sessions/` to "fix" business state.
+- Do not hard-code project-private fields into scripts; prefer `meta`.
+- Do not default to asking the user to fork Trellis CLI.

.claude/skills/trellis-meta/references/customize-local/change-workflow.md

@@ -0,0 +1,64 @@
+# Change Local Workflow
+
+When the user wants to change Trellis phases, next-action hints, whether to create tasks, whether to use sub-agents, or when to check/wrap up, edit `.trellis/workflow.md` first.
+
+## Read These Files First
+
+1. `.trellis/workflow.md`
+2. Entry files for the current platform, such as skills/commands/prompts/workflows
+3. The current task's `task.json` and `prd.md`
+
+## Common Needs And Edit Points
+
+| Need | Edit point |
+| --- | --- |
+| Change phase names or phase order | `Phase Index` and the corresponding Phase sections. |
+| Change whether to create a task when there is no task | `[workflow-state:no_task]` state block. |
+| Change the next step during planning | Phase 1 and `[workflow-state:planning]`. |
+| Change whether an agent is required during in_progress | Phase 2 and `[workflow-state:in_progress]`. |
+| Change wrap-up after completion | Phase 3 and `[workflow-state:completed]`. |
+| Change which skill a user intent triggers | `Skill Routing` table. |
+
+## Modification Steps
+
+1. Find the relevant section in `.trellis/workflow.md`.
+2. When changing rules, keep explicit trigger conditions and next actions.
+3. If adding or renaming a skill/agent, synchronize the corresponding files in platform directories.
+4. Workflow-state changes only need an edit to the `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The hook is parser-only — it reads whatever you put in the block. Keep the opening and closing tags' STATUS strings identical (`[workflow-state:foo]…[/workflow-state:foo]`); mismatched STATUS pairs are silently dropped.
+5. Make the AI reread `.trellis/workflow.md`; do not keep using rules from the old conversation.
+
+## Example: Relax Task Creation Requirements
+
+To change when task creation can be skipped, usually edit `[workflow-state:no_task]`:
+
+```md
+[workflow-state:no_task]
+Task is not required when the answer is a one-reply explanation, no files are changed, and no research is needed.
+[/workflow-state:no_task]
+```
+
+If the formal Phase 1 flow also needs to change, synchronize the Phase 1 section.
+
+## Example: One Platform Does Not Use Sub-Agents
+
+If the user wants only one platform to avoid sub-agents, first confirm whether that platform has a separate group in the workflow. Then change Phase 2 routing for that platform group instead of deleting all `trellis-implement` / `trellis-check` instructions across platforms.
+
+## `/trellis:continue` Route Table
+
+`/trellis:continue` resumes a task by deciding which phase step to load next. The decision combines `task.json.status` with the presence of artifacts inside the task directory. The mapping is fixed in the command itself; forks that add custom statuses must extend both the workflow.md tag block and this table.
+
+| `status` | Artifact state | Resume at |
+| --- | --- | --- |
+| `planning` | `prd.md` missing | Phase 1.1 (load `trellis-brainstorm`) |
+| `planning` | `prd.md` exists, `implement.jsonl` only has the seed `_example` row | Phase 1.3 (curate JSONL context) |
+| `planning` | `prd.md` exists, `implement.jsonl` curated | Phase 1.4 (run `task.py start`) |
+| `in_progress` | no implementation in conversation history | Phase 2.1 (`trellis-implement`) |
+| `in_progress` | implementation done, no `trellis-check` run | Phase 2.2 (`trellis-check`) |
+| `in_progress` | check passed | Phase 3.1 (verify quality + spec update) |
+| `completed` | task is still in active tree | Phase 3.5 (run `/trellis:finish-work` to archive) |
+
+When you add a custom status (e.g. `in-review`), add a `[workflow-state:in-review]` block in `.trellis/workflow.md` for the per-turn breadcrumb AND extend this route table — usually by editing the `/trellis:continue` command file (`.{platform}/commands/trellis/continue.md` or equivalent) to add a row that decides where to resume from. Without the route entry, `/trellis:continue` will fall through to a default branch and the user will not land on the step you intended.
+
+## Notes
+
+`.trellis/workflow.md` is the local project workflow, not an immutable template. The user can adapt it to team habits. After editing it, platform entry files may still contain old descriptions, so inspect them too.

.claude/skills/trellis-meta/references/customize-local/overview.md

@@ -0,0 +1,55 @@
+# Local Customization Overview
+
+This directory is for local AI working in a user project where Trellis was installed through npm and `trellis init` has already been run. The AI should modify generated `.trellis/` and platform directories inside the project, not Trellis CLI upstream source code.
+
+## First Determine What The User Actually Wants To Change
+
+| User wording | Read first |
+| --- | --- |
+| "Change the Trellis flow / phases / next prompt" | `change-workflow.md` |
+| "Change task creation, status, archive, or hooks" | `change-task-lifecycle.md` |
+| "AI did not read context / change injected content" | `change-context-loading.md` |
+| "A platform hook is not behaving as expected" | `change-hooks.md` |
+| "Change implement/check/research agent behavior" | `change-agents.md` |
+| "Add a skill/command/workflow/prompt" | `change-skills-or-commands.md` |
+| "Adjust the project spec structure" | `change-spec-structure.md` |
+| "Add team conventions and local notes" | `add-project-local-conventions.md` |
+
+## General Operation Order
+
+1. **Confirm platform and directories**: inspect which directories exist, such as `.claude/`, `.codex/`, `.cursor/`.
+2. **Confirm the current active task**: run `python ./.trellis/scripts/task.py current --source`.
+3. **Read the local source of truth**: prefer `.trellis/workflow.md`, `.trellis/config.yaml`, and relevant platform files.
+4. **Modify narrowly**: edit only files related to the user's request.
+5. **Synchronize semantics**: if a shared flow changes, check whether platform entry points also need changes; if a platform entry changes, check whether `.trellis/workflow.md` still agrees.
+
+## Local File Priority
+
+| Layer | Files |
+| --- | --- |
+| Workflow | `.trellis/workflow.md` |
+| Project configuration | `.trellis/config.yaml` |
+| Task material | `.trellis/tasks/<task>/` |
+| Project specs | `.trellis/spec/` |
+| Runtime scripts | `.trellis/scripts/` |
+| Platform integration | `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, and similar directories |
+| Shared skill | `.agents/skills/` |
+
+## Things Not To Do By Default
+
+- Do not edit the global npm install directory.
+- Do not edit `node_modules/@mindfoldhq/trellis`.
+- Do not assume the user has the Trellis GitHub repository.
+- Do not overwrite local files already modified by the user with default templates.
+- Do not put team project rules into public `trellis-meta`; project rules belong in `.trellis/spec/` or a local skill.
+
+## When To Inspect Upstream Source
+
+Switch to an upstream source-code perspective only when the user explicitly expresses one of these goals:
+
+- "I want to open a PR to Trellis"
+- "I want to change npm package publish contents"
+- "I want to fork Trellis"
+- "I want to modify the generation logic for `trellis init/update`"
+
+Otherwise, default to modifying local Trellis files inside the user project.

.claude/skills/trellis-meta/references/local-architecture/context-injection.md

@@ -0,0 +1,68 @@
+# Local Context Injection System
+
+Trellis context injection aims to make AI read the right files at the right time instead of relying on model memory. In a user project, injection is implemented by `.trellis/` scripts together with platform hooks, agents, and skills.
+
+## Injected Context Types
+
+| Type | Source | Purpose |
+| --- | --- | --- |
+| session context | `.trellis/scripts/get_context.py` | Current developer, git status, active task, active tasks, journal, packages. |
+| workflow context | `.trellis/workflow.md` | Current Trellis flow and next action. |
+| spec context | `.trellis/spec/` + task JSONL | Specs that must be followed during implementation/checking. |
+| task context | `.trellis/tasks/<task>/prd.md`, `info.md`, `research/` | Current task requirements, design, and research. |
+| platform context | Platform hooks/settings/agents | Lets different AI tools read the files above through their own mechanisms. |
+
+## session-start
+
+Platforms with session-start support inject a Trellis overview when a session starts, clears, compacts, or receives a similar event. Injected content usually includes:
+
+- workflow summary.
+- current task status.
+- active tasks.
+- spec index paths.
+- developer identity and git status.
+
+If the user feels the AI does not know the current task in a new session, first check whether the platform's session-start hook or equivalent mechanism is installed and running.
+
+## workflow-state
+
+workflow-state is a lightweight hint injected around each user turn. Based on current task status, it selects a block from `.trellis/workflow.md`, such as `no_task`, `planning`, `in_progress`, or `completed`.
+
+If the user wants to change "what the AI should do next in a given state," edit the corresponding state block in `.trellis/workflow.md` first.
+
+## sub-agent context
+
+Implement and check agents need task context. Trellis has two loading modes:
+
+1. **hook push**: a platform hook injects `prd.md` and the files referenced by `implement.jsonl` / `check.jsonl` before the agent starts.
+2. **agent pull**: the agent definition instructs the agent to read the active task, PRD, and JSONL context after startup.
+
+In both modes, JSONL files in the task directory are the key interface.
+
+## JSONL Reading Rules
+
+`implement.jsonl` and `check.jsonl` contain one JSON object per line:
+
+```jsonl
+{"file": ".trellis/spec/backend/index.md", "reason": "Backend rules"}
+```
+
+Readers should skip seed rows without a `file` field. When configuring JSONL, the AI should include only spec/research files, not pre-register code files that will be modified.
+
+## Active Task And Context Key
+
+Active task state lives in `.trellis/.runtime/sessions/` and is isolated per session. Hooks try to resolve the context key from platform events, environment variables, transcript paths, or `TRELLIS_CONTEXT_ID`.
+
+If shell commands cannot see the same context key, `task.py current --source` may report no active task. In that case, check whether the platform passes session identity into the shell instead of hand-writing a global current-task file.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Change session-start injected content | The platform's `session-start` hook or plugin file. |
+| Change per-turn workflow-state rules | `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The platform workflow-state hook parses these blocks verbatim and embeds no fallback text. |
+| Change how sub-agents read context | Platform agent definitions, the `inject-subagent-context` hook, or agent preludes. |
+| Change JSONL validation/display | `.trellis/scripts/common/task_context.py`. |
+| Change active task resolution | `.trellis/scripts/common/active_task.py`. |
+
+When modifying context injection, verify two things: new sessions can see the correct task, and sub-agents can see the correct PRD/spec/research.

.claude/skills/trellis-meta/references/local-architecture/generated-files.md

@@ -0,0 +1,80 @@
+# Local Files Generated After Init
+
+`trellis init` writes the Trellis runtime into the user project. Later, `trellis update` tries to update Trellis-managed template files, but it uses `.trellis/.template-hashes.json` to determine which files have already been modified by the user.
+
+This page only describes files that are visible and editable inside the user project.
+
+## `.trellis/`
+
+```text
+.trellis/
+├── workflow.md
+├── config.yaml
+├── .developer
+├── .version
+├── .template-hashes.json
+├── .runtime/
+├── scripts/
+├── spec/
+├── tasks/
+└── workspace/
+```
+
+| Path | Usually editable? | Notes |
+| --- | --- | --- |
+| `.trellis/workflow.md` | Yes | Local workflow documentation and AI routing rules. |
+| `.trellis/config.yaml` | Yes | Project configuration, hooks, packages, journal line limits, and related settings. |
+| `.trellis/spec/` | Yes | Project specs, intended to be updated regularly by users and AI. |
+| `.trellis/tasks/` | Yes | Task material and research artifacts, maintained by the task workflow. |
+| `.trellis/workspace/` | Yes | Session records, usually written by `add_session.py`. |
+| `.trellis/scripts/` | Carefully | Local runtime. It can be customized, but only after understanding the call chain. |
+| `.trellis/.runtime/` | No | Runtime state, usually written automatically by hooks/scripts. |
+| `.trellis/.developer` | Carefully | Current developer identity. |
+| `.trellis/.version` | No | Trellis version record used by update/migration logic. |
+| `.trellis/.template-hashes.json` | No | Template hash record. Do not hand-write business rules here. |
+
+## Platform Directories
+
+Different platforms generate different directories. Common categories:
+
+| Category | Example paths | Purpose |
+| --- | --- | --- |
+| hooks | `.claude/hooks/`, `.codex/hooks/`, `.cursor/hooks/` | Inject session context, workflow-state, and sub-agent context. |
+| settings | `.claude/settings.json`, `.codex/hooks.json`, `.qoder/settings.json` | Tell the platform when to run hooks or plugins. |
+| agents | `.claude/agents/`, `.codex/agents/`, `.kiro/agents/` | Define agents such as `trellis-research`, `trellis-implement`, and `trellis-check`. |
+| skills | `.claude/skills/`, `.agents/skills/`, `.qoder/skills/` | Skills that auto-trigger or can be read by AI. |
+| commands/prompts/workflows | `.cursor/commands/`, `.github/prompts/`, `.windsurf/workflows/` | Explicit user-invoked command or workflow entry points. |
+
+When modifying a platform directory, also confirm whether `.trellis/workflow.md` still describes the same flow.
+
+## Meaning Of Template Hashes
+
+`.trellis/.template-hashes.json` records the content hash from the last time Trellis wrote a template file. `trellis update` uses it to distinguish three cases:
+
+| Case | Update behavior |
+| --- | --- |
+| File was not modified by the user | It can be updated automatically. |
+| File was modified by the user | Prompt the user to overwrite, keep, or generate `.new`. |
+| File is no longer a current template | It may be deleted, renamed, or preserved according to migration rules. |
+
+When an AI customizes local Trellis files, it does not need to maintain hashes manually. It is normal for Trellis update to recognize the result as "modified by the user."
+
+## Local Customization Boundaries
+
+Editable by default:
+
+- `.trellis/workflow.md`
+- `.trellis/config.yaml`
+- `.trellis/spec/**`
+- `.trellis/scripts/**`
+- Platform hooks, settings, agents, skills, commands, prompts, and workflows
+
+Do not edit by default:
+
+- Global npm install directory
+- `node_modules/@mindfoldhq/trellis`
+- Trellis GitHub repository source code
+- Concrete state files under `.trellis/.runtime/**`
+- Hash contents inside `.trellis/.template-hashes.json`
+
+Switch to the Trellis CLI source-code perspective only when the user explicitly wants to contribute upstream.

.claude/skills/trellis-meta/references/local-architecture/overview.md

@@ -0,0 +1,51 @@
+# Local Trellis Architecture Overview
+
+`trellis-meta` is for user projects that have already run `trellis init`. The user's machine usually has only the npm-installed `trellis` command plus the Trellis files generated inside the project; it may not have the Trellis CLI source code.
+
+Therefore, when an AI uses this skill, the default customization target is local files inside the user project:
+
+- `.trellis/`: workflow, tasks, specs, memory, scripts, and runtime state.
+- Platform directories: `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, `.kiro/`, `.gemini/`, `.qoder/`, `.codebuddy/`, `.github/`, `.factory/`, `.pi/`, `.kilocode/`, `.agent/`, `.windsurf/`, and similar directories.
+- Shared skill layer: `.agents/skills/`.
+
+Do not default to guiding the user to fork the Trellis CLI repository. Treat upstream source code as the operating target only when the user explicitly says they want to change Trellis upstream source, publish an npm package, or contribute a PR.
+
+## Local System Model
+
+Trellis provides three layers inside a user project:
+
+1. **Workflow layer**: `.trellis/workflow.md` defines phases, routing, next actions, and prompt blocks.
+2. **Persistence layer**: `.trellis/tasks/`, `.trellis/spec/`, and `.trellis/workspace/` store tasks, specs, and session memory.
+3. **Platform integration layer**: hooks, settings, agents, skills, commands, prompts, and workflows in platform directories connect the Trellis workflow to different AI tools.
+
+All three layers live inside the user project, so an AI can read and modify them directly.
+
+## Core Paths
+
+| Path | Purpose |
+| --- | --- |
+| `.trellis/workflow.md` | Workflow phases, skill routing, and workflow-state prompt blocks. |
+| `.trellis/config.yaml` | Project configuration, task lifecycle hooks, monorepo package configuration, and journal configuration. |
+| `.trellis/spec/` | The user's project-specific coding conventions and thinking guides. |
+| `.trellis/tasks/` | Each task's PRD, technical notes, research files, and JSONL context. |
+| `.trellis/workspace/` | Per-developer journals and cross-session memory. |
+| `.trellis/scripts/` | Local Python runtime used by commands, hooks, and context injection. |
+| `.trellis/.runtime/` | Session-level runtime state, such as the current task pointer. |
+| `.trellis/.template-hashes.json` | Template hashes for Trellis-managed files, used by update to determine whether local files were modified by the user. |
+
+## AI Customization Principles
+
+1. **Find the local source of truth first**: Do not edit from memory. Read `.trellis/workflow.md`, `.trellis/config.yaml`, the relevant platform directory, and related task files first.
+2. **Edit the user project, not the npm package cache**: Modify generated files inside the project, not `node_modules` or the global npm install directory.
+3. **Keep platform files aligned with `.trellis/`**: If workflow routing changes, also check whether platform skills or commands still describe the same flow.
+4. **Put project-specific rules in `.trellis/spec/` or a local skill**: Do not put team conventions into `trellis-meta`.
+5. **Preserve user changes**: If a file was already modified locally, work from the current content instead of overwriting it with a default template.
+
+## How To Use This Directory
+
+- To understand which files exist after init, read `generated-files.md`.
+- To change phases, routing, or next actions, read `workflow.md`.
+- To change the task model, JSONL context, or active task behavior, read `task-system.md`.
+- To change coding convention injection, read `spec-system.md`.
+- To understand journals and cross-session memory, read `workspace-memory.md`.
+- To change hooks or sub-agent context loading, read `context-injection.md`.

.claude/skills/trellis-meta/references/local-architecture/spec-system.md

@@ -0,0 +1,102 @@
+# Local Spec System
+
+`.trellis/spec/` is the user's project-specific engineering spec library. Trellis is not about making AI memorize conventions; it injects relevant specs or requires the AI to read them at the right time.
+
+## Directory Model
+
+A common single-repository structure:
+
+```text
+.trellis/spec/
+├── backend/
+│   ├── index.md
+│   └── ...
+├── frontend/
+│   ├── index.md
+│   └── ...
+└── guides/
+    ├── index.md
+    └── ...
+```
+
+A common monorepo structure:
+
+```text
+.trellis/spec/
+├── cli/
+│   ├── backend/
+│   │   ├── index.md
+│   │   └── ...
+│   └── unit-test/
+│       ├── index.md
+│       └── ...
+├── docs-site/
+│   └── docs/
+│       ├── index.md
+│       └── ...
+└── guides/
+    ├── index.md
+    └── ...
+```
+
+`index.md` is the entry point for each layer. It should list the Pre-Development Checklist and Quality Check. Specific guidelines live in other Markdown files in the same directory.
+
+## Package Configuration
+
+`.trellis/config.yaml` can declare packages:
+
+```yaml
+packages:
+  cli:
+    path: packages/cli
+  docs-site:
+    path: docs-site
+    type: submodule
+default_package: cli
+```
+
+The AI can run:
+
+```bash
+python ./.trellis/scripts/get_context.py --mode packages
+```
+
+This command lists packages and spec layers for the current project. Use this output as the reference when configuring context JSONL.
+
+## How Specs Enter Tasks
+
+Before a task enters implementation, Phase 1.3 should write relevant specs into `implement.jsonl` / `check.jsonl`:
+
+```jsonl
+{"file": ".trellis/spec/cli/backend/index.md", "reason": "CLI backend conventions"}
+{"file": ".trellis/spec/cli/unit-test/conventions.md", "reason": "Test expectations"}
+```
+
+Sub-agents or platform preludes read these JSONL files and load the referenced specs. On platforms without sub-agent support, the AI should read the relevant specs directly according to the workflow.
+
+## What Specs Should Contain
+
+Specs should contain executable engineering conventions for the project, not generic best practices:
+
+- Where files should live.
+- How error handling should be expressed.
+- Input/output contracts for APIs, hooks, and commands.
+- Patterns that are forbidden.
+- Cases that require tests.
+- Project-specific pitfalls and how to avoid them.
+
+When the AI learns a new rule during implementation or debugging, it should update `.trellis/spec/` rather than only summarizing it in chat.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Add a new spec layer | `.trellis/spec/<package>/<layer>/index.md` and corresponding guideline files. |
+| Change monorepo spec mapping | `packages` / `default_package` / `spec_scope` in `.trellis/config.yaml`. |
+| Change which specs AI reads before implementation | The task's `implement.jsonl`. |
+| Change which specs AI reads during checking | The task's `check.jsonl`. |
+| Change when specs should be updated | Phase 3.3 in `.trellis/workflow.md` and the `trellis-update-spec` skill. |
+
+## Boundaries
+
+`.trellis/spec/` is the user's project specification, not a permanent copy of Trellis built-in templates. The AI should encourage the user to update it according to the actual project code instead of treating Trellis default templates as immutable documents.

.claude/skills/trellis-meta/references/local-architecture/task-system.md

@@ -0,0 +1,101 @@
+# Local Task System
+
+The Trellis task system is stored entirely under `.trellis/tasks/` in the user project. Each task is a directory containing requirements, context, research, state, and relationship information.
+
+## Task Directory Structure
+
+```text
+.trellis/tasks/
+├── 04-28-example-task/
+│   ├── task.json
+│   ├── prd.md
+│   ├── info.md
+│   ├── implement.jsonl
+│   ├── check.jsonl
+│   └── research/
+└── archive/
+    └── 2026-04/
+```
+
+| File | Purpose |
+| --- | --- |
+| `task.json` | Task metadata: status, assignee, priority, branch, parent/child tasks, and similar fields. |
+| `prd.md` | Requirements document; the most important business context during implementation. |
+| `info.md` | Optional technical design. |
+| `implement.jsonl` | List of spec/research files the implement agent must read first. |
+| `check.jsonl` | List of spec/research files the check agent must read first. |
+| `research/` | Research artifacts. Complex findings should not live only in chat. |
+
+## `task.json`
+
+`task.json` records task status and metadata. Common fields:
+
+| Field | Meaning |
+| --- | --- |
+| `id` / `name` / `title` | Task identity and title. |
+| `status` | Status such as `planning`, `in_progress`, `review`, or `completed`. |
+| `priority` | `P0`, `P1`, `P2`, `P3`. |
+| `creator` / `assignee` | Creator and assignee. |
+| `package` | Target package in a monorepo; may be empty. |
+| `branch` / `base_branch` | Working branch and PR target branch. |
+| `children` / `parent` | Parent/child task relationships. |
+| `commit` / `pr_url` | Commit and PR information after completion. |
+| `meta` | Extension fields. |
+
+The AI should not treat phase numbers as task status. Task progress is mainly determined by `status`, `prd.md`, whether JSONL context is configured, and the phase descriptions in `workflow.md`.
+
+## Active Task
+
+The user sees a "current task," but Trellis stores active task state per session.
+
+```text
+.trellis/.runtime/sessions/<context-key>.json
+```
+
+`task.py start` writes the task path into the runtime session file for the current session. `task.py current --source` shows the current task and where it came from. Different AI windows can point to different tasks without overwriting each other.
+
+If the platform or shell environment has no stable session identity, `task.py start` may be unable to set the active task. The AI should read the error, inspect the platform hook/session environment, and not fall back to a shared global pointer.
+
+## JSONL Context
+
+`implement.jsonl` and `check.jsonl` are context manifests for sub-agents to read first.
+
+Format:
+
+```jsonl
+{"file": ".trellis/spec/cli/backend/index.md", "reason": "Backend conventions"}
+{"file": ".trellis/tasks/04-28-example/research/api.md", "reason": "API research"}
+```
+
+Rules:
+
+- Include spec and research files.
+- Do not include code files that are about to be modified.
+- Do not treat temporary conclusions in chat as the only context.
+- Seed rows have no `file` field; they only prompt the AI to fill in real entries.
+
+## Common Commands
+
+```bash
+python ./.trellis/scripts/task.py create "<title>" --slug <slug>
+python ./.trellis/scripts/task.py start <task>
+python ./.trellis/scripts/task.py current --source
+python ./.trellis/scripts/task.py add-context <task> implement <file> <reason>
+python ./.trellis/scripts/task.py validate <task>
+python ./.trellis/scripts/task.py finish
+python ./.trellis/scripts/task.py archive <task>
+```
+
+When modifying the task system, the AI should prefer script commands to maintain structure. Edit JSON/Markdown directly only when scripts do not cover the need.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Change the default task template | `.trellis/scripts/common/task_store.py` and task creation instructions. |
+| Change status semantics | `.trellis/workflow.md`, workflow-state hook logic, and task usage conventions. |
+| Add task lifecycle actions | `hooks.after_*` in `.trellis/config.yaml`. |
+| Change context rules | Phase 1.3 in `.trellis/workflow.md` and related platform agent/hook instructions. |
+| Change archive policy | `.trellis/scripts/common/task_store.py` / `task_utils.py`. |
+
+These are local files in the user project. Do not default to editing Trellis CLI source code unless the user wants to contribute upstream.

.claude/skills/trellis-meta/references/local-architecture/workflow.md

@@ -0,0 +1,75 @@
+# Local Workflow System
+
+`.trellis/workflow.md` is the Trellis workflow source of truth inside the user project. An AI does not need Trellis source code to understand how the current project should move tasks forward; this file is enough.
+
+## File Responsibilities
+
+`.trellis/workflow.md` has three responsibilities:
+
+1. **Explain workflow phases**: Plan, Execute, Finish.
+2. **Define skill routing**: which skill or agent the AI should use when the user expresses a certain intent.
+3. **Provide workflow-state prompt blocks**: hooks can inject the prompt block for the current state into the conversation.
+
+## Current Phase Model
+
+```text
+Phase 1: Plan    -> clarify what to build, produce prd.md and required research
+Phase 2: Execute -> implement against the PRD and specs, then check
+Phase 3: Finish  -> final verification, preserve lessons, and wrap up
+```
+
+Each phase contains numbered steps, such as `1.3 Configure context`. These numbers are not runtime fields in `task.json`; they are workflow structure for AI and humans to read.
+
+## Skill Routing
+
+`workflow.md` separates routing by platform capability:
+
+- Platforms with sub-agent support: dispatch `trellis-implement` by default for implementation and `trellis-check` for checking.
+- Platforms without sub-agent support: the main session reads skills such as `trellis-before-dev`, then executes directly.
+
+When changing local AI behavior, update the routing descriptions in `workflow.md` first, then check whether the corresponding platform skill, command, or agent files need to stay in sync.
+
+## Workflow-State Prompt Blocks
+
+The bottom of `workflow.md` can contain state blocks like this:
+
+```text
+[workflow-state:no_task]
+...
+[/workflow-state:no_task]
+```
+
+Hooks choose the right block based on current task status and inject it into the conversation. Common states include:
+
+| State | Meaning |
+| --- | --- |
+| `no_task` | The current session has no active task. |
+| `planning` | The task is still in requirements, research, or context configuration. |
+| `in_progress` | The task has entered implementation and checking. |
+| `completed` | The task is complete and waiting for wrap-up or archive. |
+
+If the user wants to change policies such as "whether to create a task when there is no task," "when task creation may be skipped," or "whether sub-agents are required," edit these state blocks and the routing table above them.
+
+## Local Modification Patterns
+
+Common changes:
+
+| Goal | Edit point |
+| --- | --- |
+| Add a phase | Update the Phase Index, phase body, routing, and state blocks. |
+| Change task creation policy | Update the `no_task` state block and Phase 1 description. |
+| Change the default implementation/check path | Update Phase 2 and skill routing. |
+| Change the wrap-up flow | Update Phase 3 and `finish-work` related descriptions. Note the current split: Phase 3.4 = AI-driven code commits (batched, user-confirmed), Phase 3.5 = `/finish-work` (archive + record session). `/finish-work` refuses to run if the working tree is dirty. |
+| Change platform differences | Update routing descriptions grouped by platform. |
+
+After editing, make the AI reread `.trellis/workflow.md`; do not assume the flow from the old conversation is still valid.
+
+## Relationship To Platform Files
+
+`workflow.md` is the semantic center of the local workflow, but each platform can also have its own entry files:
+
+- skills, such as `trellis-brainstorm` and `trellis-check`.
+- commands/prompts/workflows, such as continue and finish-work.
+- hooks, such as session-start or workflow-state injection.
+
+If only `workflow.md` changes, platform entry files may still contain old language. When the user wants to change "what the AI actually does," also inspect the relevant platform directory.

.claude/skills/trellis-meta/references/local-architecture/workspace-memory.md

@@ -0,0 +1,71 @@
+# Local Workspace Memory System
+
+`.trellis/workspace/` stores cross-session memory. Its purpose is to let AI and humans understand what happened before across different windows and different days.
+
+## Directory Structure
+
+```text
+.trellis/workspace/
+├── index.md
+└── <developer>/
+    ├── index.md
+    ├── journal-1.md
+    └── journal-2.md
+```
+
+| File | Purpose |
+| --- | --- |
+| `.trellis/.developer` | Current developer identity. |
+| `.trellis/workspace/index.md` | Global workspace overview. |
+| `.trellis/workspace/<developer>/index.md` | Session index for a developer. |
+| `.trellis/workspace/<developer>/journal-N.md` | Session journal. |
+
+## Developer Identity
+
+Run this the first time:
+
+```bash
+python ./.trellis/scripts/init_developer.py <name>
+```
+
+This creates `.trellis/.developer` and the corresponding workspace directory. The AI should not change developer identity casually; if the identity is wrong, first confirm who is using the current project.
+
+## Journal
+
+`journal-N.md` records completed or partially completed work from each session. By default, each journal holds about 2000 lines; after that it rotates to the next file.
+
+Common command for recording a session:
+
+```bash
+python ./.trellis/scripts/add_session.py \
+  --title "Session title" \
+  --summary "What changed" \
+  --commit "abc1234"
+```
+
+Planning or review work without a commit can also be recorded by using `--no-commit` or an empty commit value.
+
+## Relationship Between Workspace Memory And Tasks
+
+| System | What it stores |
+| --- | --- |
+| `.trellis/tasks/` | Requirements, design, research, and state for a specific task. |
+| `.trellis/workspace/` | Work records across tasks and sessions. |
+| `.trellis/spec/` | Engineering knowledge preserved as long-term conventions. |
+
+If information is only useful for the current task, put it in the task directory.  
+If information describes what happened in the current session, put it in the workspace journal.  
+If information should be followed every time code is written in the future, put it in spec.
+
+## Local Customization Points
+
+| Need | Edit location |
+| --- | --- |
+| Change maximum journal lines | `max_journal_lines` in `.trellis/config.yaml`. |
+| Change session auto-commit message | `session_commit_message` in `.trellis/config.yaml`. |
+| Change session content format | `.trellis/scripts/add_session.py`. |
+| Change how workspace is displayed in context | `.trellis/scripts/common/session_context.py`. |
+
+## AI Usage Rules
+
+The AI should not treat workspace as the only source of truth. When resuming a task, read the current task first, then use workspace for background. After a task is complete, record important process notes in workspace; if long-term rules emerged, update spec.

.claude/skills/trellis-meta/references/platform-files/agents.md

@@ -0,0 +1,79 @@
+# Agents
+
+Trellis agent files define specialized roles. Common Trellis agents in a user project are:
+
+- `trellis-research`
+- `trellis-implement`
+- `trellis-check`
+
+File locations and formats differ by platform, but responsibility boundaries should stay consistent.
+
+## Agent Responsibilities
+
+| Agent | Responsibility |
+| --- | --- |
+| `trellis-research` | Investigate the question and write findings into the current task's `research/`. |
+| `trellis-implement` | Implement against `prd.md`, `info.md`, `implement.jsonl`, and related spec/research. |
+| `trellis-check` | Review changes, fix discovered issues, and run necessary checks. |
+
+Agent files should not become generic chat prompts. They should define input sources, write boundaries, whether code may be changed, and how results are reported.
+
+## Common Paths
+
+| Platform | Agent path |
+| --- | --- |
+| Claude Code | `.claude/agents/trellis-*.md` |
+| Cursor | `.cursor/agents/trellis-*.md` |
+| OpenCode | `.opencode/agents/trellis-*.md` |
+| Codex | `.codex/agents/trellis-*.toml` |
+| Kiro | `.kiro/agents/trellis-*.json` |
+| Gemini CLI | `.gemini/agents/trellis-*.md` |
+| Qoder | `.qoder/agents/trellis-*.md` |
+| CodeBuddy | `.codebuddy/agents/trellis-*.md` |
+| Factory Droid | `.factory/droids/trellis-*.md` |
+| Pi Agent | `.pi/agents/trellis-*.md` |
+
+GitHub Copilot agent/prompt support is provided by a combination of directories such as `.github/agents/`, `.github/prompts/`, and `.github/skills/`; inspect the files actually generated in the user project.
+
+Main-session workflow platforms such as Kilo, Antigravity, and Windsurf may not have Trellis sub-agent files. They usually rely on workflows/skills to guide the main session.
+
+## Two Context Loading Modes
+
+### hook push
+
+The platform hook injects task context before the agent starts. The agent file itself can focus more on responsibilities and boundaries.
+
+Common on platforms that support agent hooks.
+
+### agent pull
+
+The agent file instructs the agent to read after startup:
+
+- `python ./.trellis/scripts/task.py current --source`
+- current task `prd.md`
+- `info.md`
+- `implement.jsonl` or `check.jsonl`
+- spec/research files referenced by JSONL
+
+This mode fits platforms whose hooks cannot reliably rewrite sub-agent prompts.
+
+## Local Change Scenarios
+
+| User need | Edit location |
+| --- | --- |
+| Implement agent must follow extra restrictions | The platform's `trellis-implement` agent file. |
+| Check agent must run project-specific commands | `trellis-check` agent file, and `.trellis/spec/` if needed. |
+| Research agent must output a fixed format | `trellis-research` agent file. |
+| Agent cannot read task context | Agent prelude or `inject-subagent-context` hook. |
+| Add a project-specific agent | Platform agent directory + related workflow/command/skill entry point. |
+
+## Modification Principles
+
+1. **Keep responsibilities single-purpose**. Do not mix research, implement, and check responsibilities into one agent.
+2. **Specify the read order**. Agents must know to start from the active task and then find the PRD and JSONL.
+3. **Specify write boundaries**. Research usually only writes `research/`; implement can write code; check can fix issues.
+4. **Keep semantics synchronized in multi-platform projects**. If the user configured Claude, Codex, and Cursor together, decide whether changes to one platform's agent also need to be applied to others.
+
+## Do Not Default To Editing Upstream Templates
+
+Local AI should default to modifying platform agent files inside the user project. Discuss upstream template source only when the user explicitly wants to contribute the change back to Trellis.

.claude/skills/trellis-meta/references/platform-files/hooks-and-settings.md

@@ -0,0 +1,69 @@
+# Hooks And Settings
+
+Hooks/settings are the entry layer that connects a platform to Trellis. They decide which scripts, plugins, or extensions a platform runs for which events.
+
+## Settings Responsibilities
+
+settings/config files usually register:
+
+- session-start hook: injects a Trellis overview when a new session starts or context resets.
+- workflow-state hook: parses `[workflow-state:STATUS]` blocks from `.trellis/workflow.md` and emits the body matching the current task `status` on each user input. Parser-only; the script does not embed fallback content.
+- sub-agent context hook: injects task context when implementation/check/research agents start.
+- shell/session bridge: lets shell commands see the same Trellis session identity.
+- platform plugin or extension entry points.
+
+Common files:
+
+| Platform | settings/config |
+| --- | --- |
+| Claude Code | `.claude/settings.json` |
+| Cursor | `.cursor/hooks.json` |
+| Codex | `.codex/hooks.json`, `.codex/config.toml` |
+| OpenCode | `.opencode/package.json`, `.opencode/plugins/*` |
+| Kiro | `.kiro/hooks/` + platform config |
+| Gemini CLI | `.gemini/settings.json` |
+| Qoder | `.qoder/settings.json` |
+| CodeBuddy | `.codebuddy/settings.json` |
+| GitHub Copilot | `.github/copilot/hooks.json` |
+| Factory Droid | `.factory/settings.json` |
+| Pi Agent | `.pi/settings.json`, `.pi/extensions/trellis/` |
+
+Whether these files exist in a project depends on which `trellis init --<platform>` flags the user ran.
+
+## Hook Script Types
+
+| Script | Purpose |
+| --- | --- |
+| `session-start.py` | Generates session-start context. |
+| `inject-workflow-state.py` | Parses `[workflow-state:STATUS]` blocks in `.trellis/workflow.md` and emits the body matching the current task status. Falls back to `Refer to workflow.md for current step.` when no matching block exists. |
+| `inject-subagent-context.py` | Injects PRD, JSONL context, and related spec/research into sub-agents. |
+| `inject-shell-session-context.py` | Lets shell commands inherit Trellis session identity. |
+
+Not every platform has every hook. Do not copy files from another platform just because a platform lacks a hook; first confirm whether that platform supports the corresponding event.
+
+## Local Change Scenarios
+
+| User need | Edit location |
+| --- | --- |
+| AI should see more/less context in a new session | Platform `session-start` hook. |
+| Per-turn hint policy should change | `[workflow-state:STATUS]` block in `.trellis/workflow.md`. The hook parses workflow.md verbatim — no script edit required. |
+| Sub-agent cannot read PRD/spec | `inject-subagent-context` hook or agent prelude. |
+| `task.py current` in shell has no active task | Shell/session bridge hook or platform environment variable configuration. |
+| Disable an automatic injection | The corresponding hook registration in settings/config. |
+
+## Modification Principles
+
+1. **Settings wire things up; hooks define behavior**. If only the hook changes, the platform may never call it. If only settings change, behavior may not change.
+2. **Confirm platform event names first**. Different platforms use different names for SessionStart, UserPromptSubmit, AgentSpawn, shell execution, and similar events.
+3. **Hooks read local `.trellis/`, not upstream source**. `.trellis/scripts/` and `.trellis/workflow.md` in the user project are the default targets.
+4. **Errors must be visible**. Hook failures should tell the user what was not injected instead of silently leaving the AI without context.
+
+## Troubleshooting Path
+
+If the user says "AI did not read Trellis state":
+
+1. Check whether the platform settings register the hook.
+2. Check whether the hook file exists.
+3. Manually run the `.trellis/scripts/get_context.py` or `task.py current --source` command that the hook depends on.
+4. Check whether active task state exists in `.trellis/.runtime/sessions/`.
+5. Check whether the platform shell passes session identity.

.claude/skills/trellis-meta/references/platform-files/overview.md

@@ -0,0 +1,59 @@
+# Platform Files Overview
+
+Trellis connects the same local architecture to different AI tools. `.trellis/` stores the shared runtime; platform directories store adapter files that define how each AI tool enters Trellis.
+
+When a local AI modifies Trellis, it should distinguish two file categories first:
+
+- **Shared files**: `.trellis/workflow.md`, `.trellis/tasks/`, `.trellis/spec/`, `.trellis/scripts/`.
+- **Platform files**: `.claude/`, `.codex/`, `.cursor/`, `.opencode/`, `.kiro/`, `.gemini/`, `.qoder/`, `.codebuddy/`, `.github/`, `.factory/`, `.pi/`, `.kilocode/`, `.agent/`, `.windsurf/`, and similar directories.
+
+Platform files do not store business state. They let the corresponding AI tool read Trellis state, call Trellis scripts, and load Trellis skills/agents/hooks.
+
+## Platform File Categories
+
+| Category | Common paths | Purpose |
+| --- | --- | --- |
+| settings/config | `.claude/settings.json`, `.codex/hooks.json`, `.qoder/settings.json` | Register hooks, plugins, extensions, or platform behavior. |
+| hooks/plugins/extensions | `.claude/hooks/`, `.opencode/plugins/`, `.pi/extensions/` | Inject context at session start, user input, agent startup, shell execution, and similar events. |
+| agents | `.claude/agents/`, `.codex/agents/`, `.kiro/agents/` | Define `trellis-research`, `trellis-implement`, and `trellis-check`. |
+| skills | `.claude/skills/`, `.agents/skills/`, `.qoder/skills/` | Capability descriptions that auto-trigger or can be read on demand. |
+| commands/prompts/workflows | `.cursor/commands/`, `.github/prompts/`, `.windsurf/workflows/` | Entry points explicitly invoked by the user. |
+
+## Three Platform Integration Modes
+
+### 1. Hook / Extension Driven
+
+These platforms can trigger scripts or plugins on specific events and actively inject Trellis context into AI.
+
+Common capabilities:
+
+- session-start injection of a `.trellis/` overview.
+- workflow-state hints for each user turn.
+- PRD/spec/research injection when sub-agents start.
+- Shell commands inheriting session identity.
+
+To change "when the AI knows what," inspect hooks/plugins/extensions and settings first.
+
+### 2. Agent Prelude / Pull-Based
+
+Some platforms cannot reliably let hooks rewrite sub-agent prompts, so the agent file itself instructs the agent to read the active task, PRD, and JSONL context after startup.
+
+To change how sub-agents load context, inspect the agent files themselves.
+
+### 3. Main-Session Workflow
+
+Some platforms do not have Trellis sub-agent or hook capabilities. They rely on workflows/skills/commands to guide the main-session AI to read files, run scripts, and move tasks forward.
+
+To change behavior, inspect platform workflows/skills/commands and `.trellis/workflow.md`.
+
+## Local Modification Order
+
+When the user asks to customize behavior for a platform, the AI should inspect files in this order:
+
+1. Read `.trellis/workflow.md` to confirm the shared flow.
+2. Read the target platform's settings/config to see which hooks/agents/skills/commands are registered.
+3. Read the target platform's agents/skills/commands/hooks.
+4. Modify the local file closest to the user's need.
+5. If the change affects the shared flow, synchronize `.trellis/workflow.md` or `.trellis/spec/`.
+
+Do not modify only platform files and forget the shared workflow. Do not modify only `.trellis/workflow.md` and forget that platform entry points may still contain old descriptions.

.claude/skills/trellis-meta/references/platform-files/platform-map.md

@@ -0,0 +1,74 @@
+# Platform File Map
+
+This page lists common Trellis file locations in a user project by platform. Whether a platform directory exists in an actual project depends on which `trellis init --<platform>` commands the user ran.
+
+## Matrix
+
+| Platform | CLI flag | Main directory | Skill directory | Agent directory | Hooks/extensions |
+| --- | --- | --- | --- | --- | --- |
+| Claude Code | `--claude` | `.claude/` | `.claude/skills/` | `.claude/agents/` | `.claude/hooks/` + `.claude/settings.json` |
+| Cursor | `--cursor` | `.cursor/` | `.cursor/skills/` | `.cursor/agents/` | `.cursor/hooks.json` + `.cursor/hooks/` |
+| OpenCode | `--opencode` | `.opencode/` | `.opencode/skills/` | `.opencode/agents/` | `.opencode/plugins/` |
+| Codex | `--codex` | `.codex/` | `.agents/skills/` | `.codex/agents/` | `.codex/hooks/` + `.codex/hooks.json` |
+| Kilo | `--kilo` | `.kilocode/` | `.kilocode/skills/` | Usually none | `.kilocode/workflows/` |
+| Kiro | `--kiro` | `.kiro/` | `.kiro/skills/` | `.kiro/agents/` | `.kiro/hooks/` |
+| Gemini CLI | `--gemini` | `.gemini/` | `.agents/skills/` | `.gemini/agents/` | `.gemini/settings.json` + `.gemini/hooks/` |
+| Antigravity | `--antigravity` | `.agent/` | `.agent/skills/` | Usually none | `.agent/workflows/` |
+| Windsurf | `--windsurf` | `.windsurf/` | `.windsurf/skills/` | Usually none | `.windsurf/workflows/` |
+| Qoder | `--qoder` | `.qoder/` | `.qoder/skills/` | `.qoder/agents/` | `.qoder/hooks/` + `.qoder/settings.json` |
+| CodeBuddy | `--codebuddy` | `.codebuddy/` | `.codebuddy/skills/` | `.codebuddy/agents/` | `.codebuddy/hooks/` + `.codebuddy/settings.json` |
+| GitHub Copilot | `--copilot` | `.github/` | `.github/skills/` | `.github/agents/` | `.github/copilot/hooks/` + prompts |
+| Factory Droid | `--droid` | `.factory/` | `.factory/skills/` | `.factory/droids/` | `.factory/hooks/` + settings |
+| Pi Agent | `--pi` | `.pi/` | `.pi/skills/` | `.pi/agents/` | `.pi/extensions/trellis/` + `.pi/settings.json` |
+
+## Capability Groups
+
+### Trellis Sub-Agent Support
+
+These platforms usually have `trellis-research`, `trellis-implement`, and `trellis-check` files:
+
+- Claude Code
+- Cursor
+- OpenCode
+- Codex
+- Kiro
+- Gemini CLI
+- Qoder
+- CodeBuddy
+- GitHub Copilot
+- Factory Droid
+- Pi Agent
+
+When changing implementation/check/research behavior, look for the corresponding platform agent files first.
+
+### Main-Session Workflow Platforms
+
+These platforms rely more on workflows/skills to guide the main session:
+
+- Kilo
+- Antigravity
+- Windsurf
+
+When changing behavior, inspect workflows and skills first. Do not assume Trellis sub-agents exist.
+
+### Shared `.agents/skills/`
+
+Codex writes the shared `.agents/skills/` layer. Some tools that support agentskills.io can also read this directory. If the user wants multiple compatible tools to share one skill, consider `.agents/skills/` first, but do not assume every platform reads it.
+
+## Decision Rules When Modifying Platform Files
+
+1. User specified a platform: modify only that platform directory unless shared workflow/spec files must also change.
+2. User says "all platforms should do this": synchronize equivalent entry points platform by platform; do not modify only one directory.
+3. User only says "my AI": inspect the configuration directories that actually exist in the project and infer the current AI platform.
+4. User wants project rules: prefer `.trellis/spec/` or a project-local skill.
+5. User wants Trellis behavior: edit `.trellis/workflow.md` plus platform hooks/agents/skills/commands.
+
+## When Paths Differ
+
+Platform ecosystems change, and user projects may already be customized. If this table disagrees with local files, use the actual settings/config in the user project as authoritative:
+
+- Check the hook that settings registers.
+- Check the script that a command/prompt/workflow points to.
+- Judge behavior by the read rules currently written in the agent file.
+
+Do not delete a custom file just because it is not listed in this path table.

.claude/skills/trellis-meta/references/platform-files/skills-and-commands.md

@@ -0,0 +1,83 @@
+# Skills, Commands, Prompts, And Workflows
+
+Skills and commands are textual entry points for user interaction with Trellis. Different platforms use different names, but their core purpose is the same: tell the AI how to enter the Trellis flow when the user expresses a certain intent.
+
+## Conceptual Differences
+
+| Type | Trigger mode | Best for |
+| --- | --- | --- |
+| skill | AI auto-match or explicit user mention | Long-term capabilities, workflow rules, modification guides. |
+| command | Explicit user invocation | Clear operation entry points such as continue and finish-work. |
+| prompt | Explicit user invocation or platform selection | Similar to command, but in a platform prompt format. |
+| workflow | Explicit user selection or platform auto-match | Guides the main session when no sub-agent/hook exists. |
+
+Trellis workflow skills usually share one semantic set: brainstorm, before-dev, check, update-spec, break-loop. Multi-file built-in skills such as `trellis-meta` use layered references.
+
+## Common Paths
+
+| Platform | Common entries |
+| --- | --- |
+| Claude Code | `.claude/skills/`, `.claude/commands/` |
+| Cursor | `.cursor/skills/`, `.cursor/commands/` |
+| OpenCode | `.opencode/skills/`, `.opencode/commands/` |
+| Codex | `.agents/skills/`, `.codex/skills/` |
+| Kilo | `.kilocode/skills/`, `.kilocode/workflows/` |
+| Kiro | `.kiro/skills/` |
+| Gemini CLI | `.agents/skills/`, `.gemini/commands/` |
+| Antigravity | `.agent/skills/`, `.agent/workflows/` |
+| Windsurf | `.windsurf/skills/`, `.windsurf/workflows/` |
+| Qoder | `.qoder/skills/`, `.qoder/commands/` |
+| CodeBuddy | `.codebuddy/skills/`, `.codebuddy/commands/` |
+| GitHub Copilot | `.github/skills/`, `.github/prompts/` |
+| Factory Droid | `.factory/skills/`, `.factory/commands/` |
+| Pi Agent | `.pi/skills/` |
+
+In a user project, use the files actually generated by init as authoritative.
+
+## Skill Structure
+
+A common skill is a directory:
+
+```text
+trellis-meta/
+├── SKILL.md
+└── references/
+```
+
+`SKILL.md` should tell the AI:
+
+- When to use this skill.
+- Which reference to read first for the current task.
+- What not to do.
+
+References hold longer explanations so the entry file does not contain everything.
+
+## Command/Prompt/Workflow Structure
+
+Commands, prompts, and workflows are usually single files. Their content should include:
+
+- When to use it.
+- Which `.trellis/` files to read.
+- Which scripts to run.
+- How to report after completion.
+
+They should not store task state; task state belongs in `.trellis/tasks/` and `.trellis/.runtime/`.
+
+## Local Change Scenarios
+
+| User need | Edit location |
+| --- | --- |
+| Change AI auto-trigger rules | The corresponding skill's frontmatter description. |
+| Change user command behavior | The corresponding command/prompt/workflow file. |
+| Add a project-local skill | Platform skill directory, or shared `.agents/skills/`. |
+| Let multiple platforms share one capability | Write equivalent skills in each platform skill directory, or use the `.agents/skills/` shared layer on platforms that support it. |
+| Change finish/continue entry points | Platform commands/prompts/workflows. |
+
+## Modification Principles
+
+1. **Keep entry files short; references carry long content**. This matters especially for multi-file skills like `trellis-meta`.
+2. **Make trigger descriptions specific**. A description that is too broad can mis-trigger; one that is too narrow may not trigger.
+3. **Keep the same semantics consistent across platforms**. File formats can differ, but behavior descriptions should match.
+4. **Put project-specific capabilities in local skills**. Do not put team-private flows into public `trellis-meta`.
+
+If the user only wants local AI to know one more project rule, usually create a project-local skill or update `.trellis/spec/` instead of changing a Trellis built-in workflow skill.

.claude/skills/trellis-spec-bootstarp/SKILL.md

@@ -0,0 +1,41 @@
+---
+name: trellis-spec-bootstarp
+description: "Bootstrap project-specific Trellis coding specs with a platform-neutral single-agent workflow. Use when creating or refreshing .trellis/spec guidelines, analyzing a codebase with GitNexus, ABCoder, or source inspection, decomposing package/layer spec work, and writing real codebase-backed spec docs without placeholder text."
+---
+
+# Trellis Spec Bootstarp
+
+Use this skill to create or refresh `.trellis/spec/` guidelines from the real codebase. One capable agent owns the full loop: analyze the repository, choose the spec boundaries, write the docs, and verify the result. The workflow does not depend on a specific host, CLI, or agent brand.
+
+## Workflow
+
+1. Confirm Trellis is initialized and inspect the current `.trellis/spec/` tree.
+2. Analyze the repository architecture with the best available tools: GitNexus, ABCoder, language tooling, and direct source reads.
+3. Decompose the spec work by package and layer only when that reflects the actual codebase.
+4. Fill or reshape the spec files with concrete patterns, file paths, examples, and anti-patterns from the project.
+5. Verify that the final specs are internally consistent and contain no template placeholders.
+
+## Reference Routing
+
+| Need | Read |
+|------|------|
+| Repository architecture analysis | [references/repository-analysis.md](references/repository-analysis.md) |
+| Spec work decomposition and task planning | [references/spec-task-planning.md](references/spec-task-planning.md) |
+| Writing high-signal Trellis spec files | [references/spec-writing.md](references/spec-writing.md) |
+| GitNexus and ABCoder MCP setup | [references/mcp-setup.md](references/mcp-setup.md) |
+
+## Operating Rules
+
+- Treat templates as starting points, not contracts. Delete, rename, split, or add spec files when the repository calls for it.
+- Prefer source-backed rules over generic advice. Every important recommendation should point at a real file or repeated local pattern.
+- Keep execution single-owner by default. Optional helper agents are an implementation detail, not a requirement or user-visible dependency.
+- Do not write platform-specific instructions unless the target project already standardizes on that platform.
+- Do not leave placeholder text, empty headings, or copied boilerplate in `.trellis/spec/`.
+
+## Done Criteria
+
+- `.trellis/spec/` describes the project as it exists now.
+- Each relevant package or layer has practical coding guidance with real examples.
+- Non-applicable template sections are removed.
+- `index.md` files match the final spec file set.
+- Any required setup or analysis assumptions are documented in the relevant spec or task notes.

.claude/skills/trellis-spec-bootstarp/references/mcp-setup.md

@@ -0,0 +1,90 @@
+# MCP Setup
+
+GitNexus and ABCoder are recommended when bootstrapping Trellis specs because they expose architecture and AST context to the agent. They are tool choices, not platform requirements. Configure them through whatever MCP mechanism your agent host provides.
+
+## GitNexus
+
+GitNexus builds a code knowledge graph from the repository. Use it for module boundaries, execution flows, dependency relationships, blast radius, and graph queries.
+
+### Install and Index
+
+```bash
+# Run from the repository root.
+npx gitnexus analyze
+
+# Check index status.
+npx gitnexus status
+
+# Re-index after code changes when the analysis is stale.
+npx gitnexus analyze
+```
+
+The index is written to `.gitnexus/`. Keep embeddings only if the project already uses them; otherwise a normal index is enough for spec bootstrapping.
+
+### MCP Server Command
+
+Use this server command in the host's MCP configuration:
+
+```bash
+npx -y gitnexus mcp
+```
+
+### Useful Tools
+
+| Tool | Purpose |
+|------|---------|
+| `gitnexus_query` | Find execution flows and functional areas by concept |
+| `gitnexus_context` | Inspect callers, callees, references, and process participation for a symbol |
+| `gitnexus_impact` | Understand blast radius before changing a symbol |
+| `gitnexus_detect_changes` | Check changed symbols and affected flows before finishing |
+| `gitnexus_cypher` | Run direct graph queries |
+| `gitnexus_list_repos` | List indexed repositories |
+
+## ABCoder
+
+ABCoder parses code into UniAST and gives precise package, file, and node-level structure. Use it for signatures, type shapes, implementations, dependencies, and reverse references.
+
+### Install
+
+```bash
+go install github.com/cloudwego/abcoder@latest
+abcoder --help
+```
+
+### Parse Repositories
+
+```bash
+abcoder parse /absolute/path/to/package \
+  --lang typescript \
+  --name package-name \
+  --output ~/abcoder-asts
+```
+
+For monorepos, parse each package with a stable `--name` so task notes can reference the same repository names.
+
+### MCP Server Command
+
+Use this server command in the host's MCP configuration:
+
+```bash
+abcoder mcp ~/abcoder-asts
+```
+
+### Useful Tools
+
+| Tool | Layer | Purpose |
+|------|-------|---------|
+| `list_repos` | 1 | List parsed repositories |
+| `get_repo_structure` | 2 | Inspect packages and files |
+| `get_package_structure` | 3 | Inspect nodes within a package |
+| `get_file_structure` | 3 | Inspect functions, classes, types, and signatures in a file |
+| `get_ast_node` | 4 | Retrieve code, dependencies, references, and implementations |
+
+## Verification
+
+After configuration, verify from the agent host that both MCP servers are visible. Then run one simple query against each server before starting the spec writing pass.
+
+```bash
+ls .gitnexus/meta.json
+ls ~/abcoder-asts/*.json
+```

.claude/skills/trellis-spec-bootstarp/references/repository-analysis.md

@@ -0,0 +1,59 @@
+# Repository Analysis
+
+The goal is to discover the project's real architecture before writing rules. Do not start from generic spec templates and fill blanks. Start from the code, then let the spec structure follow.
+
+## Analysis Order
+
+1. Read the existing `.trellis/spec/` tree and note which files are templates, outdated, or already project-specific.
+2. Inspect package manifests, build scripts, workspace config, and top-level documentation to identify packages and runtime layers.
+3. Use GitNexus for execution flows, module clusters, dependency hubs, and impact-sensitive areas.
+4. Use ABCoder or language-native tooling for exact signatures, types, class boundaries, and implementation examples.
+5. Read representative source and test files directly before turning any finding into a spec rule.
+
+## What To Capture
+
+| Area | Questions |
+|------|-----------|
+| Package boundaries | What does each package own? What imports cross boundaries? |
+| Runtime layers | Which code is CLI, backend, frontend, worker, shared library, test-only, or tooling? |
+| Core abstractions | Which types, services, stores, commands, routes, or adapters define the system shape? |
+| Data flow | Where does user input enter, how is it validated, and where does state persist? |
+| Error handling | How are failures represented, logged, surfaced, and tested? |
+| Configuration | Where do defaults, environment config, generated files, and templates live? |
+| Tests | Which test styles are trusted examples for new work? |
+
+## GitNexus Usage
+
+Start broad, then inspect specific symbols:
+
+```text
+gitnexus_query({query: "CLI command execution flow"})
+gitnexus_query({query: "template generation and migration"})
+gitnexus_context({name: "SymbolName"})
+gitnexus_cypher({query: "MATCH (n)-[r]->(m) RETURN n.name, type(r), m.name LIMIT 30"})
+```
+
+Use GitNexus results to find important files and flows. Do not quote graph output as the final authority until you have checked the relevant source files.
+
+## ABCoder Usage
+
+Use ABCoder when the spec needs exact code shapes:
+
+```text
+list_repos()
+get_repo_structure({repo_name: "package-name"})
+get_file_structure({repo_name: "package-name", file_path: "src/example.ts"})
+get_ast_node({repo_name: "package-name", node_ids: [{mod_path: "...", pkg_path: "...", name: "SymbolName"}]})
+```
+
+ABCoder is most valuable for documenting constructor patterns, function signatures, type contracts, and reference chains.
+
+## Analysis Notes
+
+Keep short notes while analyzing. The notes should include:
+
+- Package or layer name.
+- Files that define the local pattern.
+- Rules the spec should teach.
+- Anti-patterns found in old code, comments, tests, or migration paths.
+- Spec files that should be created, deleted, renamed, or merged.

.claude/skills/trellis-spec-bootstarp/references/spec-task-planning.md

@@ -0,0 +1,61 @@
+# Spec Task Planning
+
+Use a single agent as the default execution model. The agent may create Trellis tasks for traceability, but the skill should not require a specific platform, CLI, or parallel worker model.
+
+## Decomposition
+
+Create spec work units around real ownership boundaries:
+
+- One package when a package has its own conventions.
+- One layer when the same package has distinct frontend, backend, CLI, worker, or shared-library rules.
+- One cross-cutting guide when a pattern spans packages and is not owned by one layer.
+
+Avoid artificial decomposition. A small library usually needs one focused spec pass, not several tasks.
+
+## Task Shape
+
+When a Trellis task is useful, write a concise PRD with these sections:
+
+```markdown
+# Fill <package-or-layer> Trellis Specs
+
+## Goal
+Write project-specific `.trellis/spec/` guidance for <scope>.
+
+## Scope
+- Spec directory:
+- Source directories to inspect:
+- Tests to inspect:
+- Out of scope:
+
+## Architecture Context
+Summarize the concrete findings from repository analysis.
+
+## Files To Create Or Update
+- `.trellis/spec/.../index.md`
+- `.trellis/spec/.../<topic>.md`
+
+## Rules
+- Adapt the spec file set to the real codebase.
+- Use real source examples with file paths.
+- Remove template-only sections that do not apply.
+- Do not modify product source code unless the task explicitly asks for it.
+
+## Acceptance Criteria
+- [ ] Specs contain concrete examples and anti-patterns from the repository.
+- [ ] No placeholder text remains.
+- [ ] Index files match the final spec files.
+- [ ] Claims are backed by source files, tests, or project docs.
+```
+
+## Optional Helper Agents
+
+If the host supports subagents, helpers can inspect independent packages or run verification. They are optional. The main agent still owns integration and final quality.
+
+Helper tasks must have clear ownership:
+
+- Read-only research tasks may inspect any source needed for the assigned scope.
+- Write tasks should own disjoint spec directories.
+- Verification tasks should check placeholder removal, broken links, and consistency.
+
+Do not encode helper-agent names, vendor-specific commands, or platform-specific routing in the skill. Put only the required work and acceptance criteria in the task.

.claude/skills/trellis-spec-bootstarp/references/spec-writing.md

@@ -0,0 +1,70 @@
+# Spec Writing
+
+Trellis specs are coding guidance for future agents. They should explain how to work in this repository, not how a generic project might be organized.
+
+## Write From Evidence
+
+Each important rule should be backed by one of these:
+
+- A source file that demonstrates the preferred pattern.
+- A test file that shows expected behavior.
+- A project document that defines the convention.
+- A repeated pattern across multiple files.
+
+Use short snippets only when they make the rule clearer. Prefer linking to the file path and naming the symbol or behavior.
+
+## File Structure
+
+Keep the spec tree aligned with the project:
+
+- Keep `index.md` as the navigation file for the spec directory.
+- Split topics when developers would look for them independently.
+- Merge topics when separate files would repeat the same rule.
+- Delete template files that do not apply.
+- Add new files for important local patterns the template missed.
+
+## Content Standards
+
+Good spec sections include:
+
+- When the rule applies.
+- The local pattern to follow.
+- The source or test files that prove the pattern.
+- Common mistakes or anti-patterns.
+- Verification commands or checks when they are specific and reliable.
+
+Avoid:
+
+- Placeholder prose.
+- Generic framework advice.
+- Tool instructions that only work in one agent host.
+- Long copied code blocks.
+- Rules based on a single accidental implementation detail.
+
+## Example Shape
+
+```markdown
+## Command Handlers
+
+Command handlers should keep argument parsing, validation, and side effects separate. The local pattern is:
+
+- Parse CLI flags at the command boundary.
+- Convert raw inputs into typed task options before invoking core logic.
+- Keep filesystem writes in the command or service layer, not in template helpers.
+
+Reference files:
+- `packages/cli/src/commands/example.ts`
+- `packages/cli/test/commands/example.test.ts`
+
+Avoid passing raw `process.argv` or unvalidated config objects into shared helpers.
+```
+
+## Final Pass
+
+Before finishing:
+
+```bash
+grep -R "To be filled\\|TODO: fill\\|placeholder" .trellis/spec
+```
+
+Also check links, index files, and whether any spec still describes a template rather than this repository.

.claude/skills/trellis-update-spec/SKILL.md

@@ -0,0 +1,356 @@
+---
+name: trellis-update-spec
+description: "Captures executable contracts and coding conventions into .trellis/spec/ documents. Use when learning something valuable from debugging, implementing, or discussion that should be preserved for future sessions."
+---
+
+# Update Code-Spec - Capture Executable Contracts
+
+When you learn something valuable (from debugging, implementing, or discussion), use this to update the relevant code-spec documents.
+
+**Timing**: After completing a task, fixing a bug, or discovering a new pattern
+
+---
+
+## Code-Spec First Rule (CRITICAL)
+
+In this project, "spec" for implementation work means **code-spec**:
+- Executable contracts (not principle-only text)
+- Concrete signatures, payload fields, env keys, and boundary behavior
+- Testable validation/error behavior
+
+If the change touches infra or cross-layer contracts, code-spec depth is mandatory.
+
+### Mandatory Triggers
+
+Apply code-spec depth when the change includes any of:
+- New/changed command or API signature
+- Cross-layer request/response contract change
+- Database schema/migration change
+- Infra integration (storage, queue, cache, secrets, env wiring)
+
+### Mandatory Output (7 Sections)
+
+For triggered tasks, include all sections below:
+1. Scope / Trigger
+2. Signatures (command/API/DB)
+3. Contracts (request/response/env)
+4. Validation & Error Matrix
+5. Good/Base/Bad Cases
+6. Tests Required (with assertion points)
+7. Wrong vs Correct (at least one pair)
+
+---
+
+## When to Update Code-Specs
+
+| Trigger | Example | Target Spec |
+|---------|---------|-------------|
+| **Implemented a feature** | Added a new integration or module | Relevant spec file |
+| **Made a design decision** | Chose extensibility pattern over simplicity | Relevant spec + "Design Decisions" section |
+| **Fixed a bug** | Found a subtle issue with error handling | Relevant spec (e.g., error-handling docs) |
+| **Discovered a pattern** | Found a better way to structure code | Relevant spec file |
+| **Hit a gotcha** | Learned that X must be done before Y | Relevant spec + "Common Mistakes" section |
+| **Established a convention** | Team agreed on naming pattern | Quality guidelines |
+| **New thinking trigger** | "Don't forget to check X before doing Y" | `guides/*.md` (as a checklist item) |
+
+**Key Insight**: Code-spec updates are NOT just for problems. Every feature implementation contains design decisions and contracts that future AI/developers need to execute safely.
+
+---
+
+## Spec Structure Overview
+
+```
+.trellis/spec/
+├── <layer>/           # Per-layer coding standards (e.g., backend/, frontend/, api/)
+│   ├── index.md       # Overview and links
+│   └── *.md           # Topic-specific guidelines
+└── guides/            # Thinking checklists (NOT coding specs!)
+    ├── index.md       # Guide index
+    └── *.md           # Topic-specific guides
+```
+
+### CRITICAL: Code-Spec vs Guide - Know the Difference
+
+| Type | Location | Purpose | Content Style |
+|------|----------|---------|---------------|
+| **Code-Spec** | `<layer>/*.md` | Tell AI "how to implement safely" | Signatures, contracts, matrices, cases, test points |
+| **Guide** | `guides/*.md` | Help AI "what to think about" | Checklists, questions, pointers to specs |
+
+**Decision Rule**: Ask yourself:
+
+- "This is **how to write** the code" → Put in a spec layer directory
+- "This is **what to consider** before writing" → Put in `guides/`
+
+**Example**:
+
+| Learning | Wrong Location | Correct Location |
+|----------|----------------|------------------|
+| "Use API X not API Y for this task" | ❌ `guides/` (too specific for a thinking guide) | ✅ Relevant spec file (concrete convention) |
+| "Remember to check X when doing Y" | ❌ Spec file (too abstract for a spec) | ✅ `guides/` (thinking checklist) |
+
+**Guides should be short checklists that point to specs**, not duplicate the detailed rules.
+
+---
+
+## Update Process
+
+### Step 1: Identify What You Learned
+
+Answer these questions:
+
+1. **What did you learn?** (Be specific)
+2. **Why is it important?** (What problem does it prevent?)
+3. **Where does it belong?** (Which spec file?)
+
+### Step 2: Classify the Update Type
+
+| Type | Description | Action |
+|------|-------------|--------|
+| **Design Decision** | Why we chose approach X over Y | Add to "Design Decisions" section |
+| **Project Convention** | How we do X in this project | Add to relevant section with examples |
+| **New Pattern** | A reusable approach discovered | Add to "Patterns" section |
+| **Forbidden Pattern** | Something that causes problems | Add to "Anti-patterns" or "Don't" section |
+| **Common Mistake** | Easy-to-make error | Add to "Common Mistakes" section |
+| **Convention** | Agreed-upon standard | Add to relevant section |
+| **Gotcha** | Non-obvious behavior | Add warning callout |
+
+### Step 3: Read the Target Code-Spec
+
+Before editing, read the current code-spec to:
+- Understand existing structure
+- Avoid duplicating content
+- Find the right section for your update
+
+```bash
+cat .trellis/spec/<category>/<file>.md
+```
+
+### Step 4: Make the Update
+
+Follow these principles:
+
+1. **Be Specific**: Include concrete examples, not just abstract rules
+2. **Explain Why**: State the problem this prevents
+3. **Show Contracts**: Add signatures, payload fields, and error behavior
+4. **Show Code**: Add code snippets for key patterns
+5. **Keep it Short**: One concept per section
+
+### Step 5: Update the Index (if needed)
+
+If you added a new section or the code-spec status changed, update the category's `index.md`.
+
+---
+
+## Update Templates
+
+### Mandatory Template for Infra/Cross-Layer Work
+
+```markdown
+## Scenario: <name>
+
+### 1. Scope / Trigger
+- Trigger: <why this requires code-spec depth>
+
+### 2. Signatures
+- Backend command/API/DB signature(s)
+
+### 3. Contracts
+- Request fields (name, type, constraints)
+- Response fields (name, type, constraints)
+- Environment keys (required/optional)
+
+### 4. Validation & Error Matrix
+- <condition> -> <error>
+
+### 5. Good/Base/Bad Cases
+- Good: ...
+- Base: ...
+- Bad: ...
+
+### 6. Tests Required
+- Unit/Integration/E2E with assertion points
+
+### 7. Wrong vs Correct
+#### Wrong
+...
+#### Correct
+...
+```
+
+### Adding a Design Decision
+
+```markdown
+### Design Decision: [Decision Name]
+
+**Context**: What problem were we solving?
+
+**Options Considered**:
+1. Option A - brief description
+2. Option B - brief description
+
+**Decision**: We chose Option X because...
+
+**Example**:
+\`\`\`typescript
+// How it's implemented
+code example
+\`\`\`
+
+**Extensibility**: How to extend this in the future...
+```
+
+### Adding a Project Convention
+
+```markdown
+### Convention: [Convention Name]
+
+**What**: Brief description of the convention.
+
+**Why**: Why we do it this way in this project.
+
+**Example**:
+\`\`\`typescript
+// How to follow this convention
+code example
+\`\`\`
+
+**Related**: Links to related conventions or specs.
+```
+
+### Adding a New Pattern
+
+```markdown
+### Pattern Name
+
+**Problem**: What problem does this solve?
+
+**Solution**: Brief description of the approach.
+
+**Example**:
+\`\`\`
+// Good
+code example
+
+// Bad
+code example
+\`\`\`
+
+**Why**: Explanation of why this works better.
+```
+
+### Adding a Forbidden Pattern
+
+```markdown
+### Don't: Pattern Name
+
+**Problem**:
+\`\`\`
+// Don't do this
+bad code example
+\`\`\`
+
+**Why it's bad**: Explanation of the issue.
+
+**Instead**:
+\`\`\`
+// Do this instead
+good code example
+\`\`\`
+```
+
+### Adding a Common Mistake
+
+```markdown
+### Common Mistake: Description
+
+**Symptom**: What goes wrong
+
+**Cause**: Why this happens
+
+**Fix**: How to correct it
+
+**Prevention**: How to avoid it in the future
+```
+
+### Adding a Gotcha
+
+```markdown
+> **Warning**: Brief description of the non-obvious behavior.
+>
+> Details about when this happens and how to handle it.
+```
+
+---
+
+## Interactive Mode
+
+If you're unsure what to update, answer these prompts:
+
+1. **What did you just finish?**
+   - [ ] Fixed a bug
+   - [ ] Implemented a feature
+   - [ ] Refactored code
+   - [ ] Had a discussion about approach
+
+2. **What did you learn or decide?**
+   - Design decision (why X over Y)
+   - Project convention (how we do X)
+   - Non-obvious behavior (gotcha)
+   - Better approach (pattern)
+
+3. **Would future AI/developers need to know this?**
+   - To understand how the code works → Yes, update spec
+   - To maintain or extend the feature → Yes, update spec
+   - To avoid repeating mistakes → Yes, update spec
+   - Purely one-off implementation detail → Maybe skip
+
+4. **Which area does it relate to?**
+   - [ ] Backend code
+   - [ ] Frontend code
+   - [ ] Cross-layer data flow
+   - [ ] Code organization/reuse
+   - [ ] Quality/testing
+
+---
+
+## Quality Checklist
+
+Before finishing your code-spec update:
+
+- [ ] Is the content specific and actionable?
+- [ ] Did you include a code example?
+- [ ] Did you explain WHY, not just WHAT?
+- [ ] Did you include executable signatures/contracts?
+- [ ] Did you include validation and error matrix?
+- [ ] Did you include Good/Base/Bad cases?
+- [ ] Did you include required tests with assertion points?
+- [ ] Is it in the right code-spec file?
+- [ ] Does it duplicate existing content?
+- [ ] Would a new team member understand it?
+
+---
+
+## Relationship to Other Commands
+
+```
+Development Flow:
+  Learn something → /trellis:update-spec → Knowledge captured
+       ↑                                  ↓
+  /trellis:break-loop ←──────────────────── Future sessions benefit
+  (deep bug analysis)
+```
+
+- `/trellis:break-loop` - Analyzes bugs deeply, often reveals spec updates needed
+- `/trellis:update-spec` - Actually makes the updates
+- `/trellis:finish-work` - Reminds you to check if specs need updates
+
+---
+
+## Core Philosophy
+
+> **Code-specs are living documents. Every debugging session, every "aha moment" is an opportunity to make the implementation contract clearer.**
+
+The goal is **institutional memory**:
+- What one person learns, everyone benefits from
+- What AI learns in one session, persists to future sessions
+- Mistakes become documented guardrails

.codex/agents/trellis-check.toml

@@ -0,0 +1,109 @@
+name = "trellis-check"
+description = "Workspace-write Trellis reviewer that self-fixes spec drift, lint/type-check failures, and missing tests."
+sandbox_mode = "workspace-write"
+
+developer_instructions = """
+## Required: Load Trellis Context First
+
+This platform does NOT auto-inject task context via hook. Before doing anything else, you MUST load context yourself.
+
+### Step 1: Find the active task path
+
+Try in order — stop at the first one that yields a task path:
+
+1. **Look at the dispatch prompt** you received from the main agent. If its first line is `Active task: <path>` (e.g. `Active task: .trellis/tasks/04-17-foo`), use that path. The main agent is required to include this line on class-2 platforms.
+2. **Run** `python ./.trellis/scripts/task.py current --source` and read the `Current task:` line.
+3. **If both fail** (no `Active task:` line in the prompt and `task.py current` returns no task), ask the user which task to work on; do NOT guess.
+
+### Step 2: Load task context from the resolved path
+
+1. Read the task's `prd.md` (requirements) and `info.md` if it exists (technical design).
+2. Read `<task-path>/check.jsonl` — JSONL list of dev spec files relevant to this agent.
+3. For each entry in the JSONL, Read its `file` path — these are the dev specs you must follow.
+   **Skip rows without a `"file"` field** (e.g. `{"_example": "..."}` seed rows left over from `task.py create` before the curator ran).
+
+If `check.jsonl` has no curated entries (only a seed row, or the file is missing), fall back to: read `prd.md`, list available specs with `python ./.trellis/scripts/get_context.py --mode packages`, and pick the specs that match the task domain yourself. Do NOT block on the missing jsonl — proceed with prd-only context plus your spec judgment.
+
+If the resolved task path has no `prd.md`, ask the user what to work on; do NOT proceed without context.
+
+---
+
+You are running as the `trellis-check` sub-agent. The main session has dispatched you to review and self-fix.
+
+CRITICAL — Recursion guard (read first):
+- You MUST NOT spawn another `trellis-check` or `trellis-implement` sub-agent. Do the review and fixes directly in this turn.
+- Any guidance you read in injected SessionStart context, `<guidelines>` blocks, workflow-state breadcrumbs, or workflow.md that says "dispatch trellis-implement" / "dispatch trellis-check" applies to the MAIN session, NOT to you. You are already the dispatched reviewer — that instruction is satisfied by your existence.
+- Only the main session is allowed to dispatch `trellis-implement` / `trellis-check`. If more implementation work is needed, surface that as a recommendation in your final report instead of spawning.
+
+---
+
+## Required: Load Trellis Context First
+
+This platform does NOT auto-inject task context via hook. Before doing anything else, you MUST load context yourself.
+
+### Step 1: Find the active task path
+
+Try in order — stop at the first one that yields a task path:
+
+1. **Look at the dispatch prompt** you received from the main agent. If its first line is `Active task: <path>` (e.g. `Active task: .trellis/tasks/04-17-foo`), use that path. The main agent is required to include this line on class-2 platforms.
+2. **Run** `python ./.trellis/scripts/task.py current --source` and read the `Current task:` line.
+3. **If both fail** (no `Active task:` line in the prompt and `task.py current` returns no task), ask the user which task to work on; do NOT guess.
+
+### Step 2: Load task context from the resolved path
+
+1. Read the task's `prd.md` (requirements) and `info.md` if it exists (technical design).
+2. Read `<task-path>/check.jsonl` — JSONL list of dev spec files relevant to this agent.
+3. For each entry in the JSONL, Read its `file` path — these are the dev specs you must follow.
+   **Skip rows without a `"file"` field** (e.g. `{"_example": "..."}` seed rows left over from `task.py create` before the curator ran).
+
+If `check.jsonl` has no curated entries (only a seed row, or the file is missing), fall back to: read `prd.md`, list available specs with `python ./.trellis/scripts/get_context.py --mode packages`, and pick the specs that match the task domain yourself. Do NOT block on the missing jsonl — proceed with prd-only context plus your spec judgment.
+
+If the resolved task path has no `prd.md`, ask the user what to work on; do NOT proceed without context.
+
+---
+
+You are the Trellis reviewer agent.
+
+Your job is to review code changes against specs AND fix issues directly — not just report them. You have write access; use it.
+
+Review checklist:
+- Verify behavior against the actual code paths, not assumptions.
+- Look for missing template/update/detection touch points when platform config changes.
+- Check whether tests should be added or updated.
+- Check whether `.trellis/spec/` docs need sync after implementation.
+- Run lint and type-check; fix any failures.
+- Prefer concrete findings over speculative warnings.
+
+When you find an issue:
+1. Fix it directly using edit/write tools.
+2. Re-run lint and type-check until green.
+3. Record what you changed and why.
+
+Output format:
+## Findings (fixed)
+- File: <path>
+- Issue: <what was wrong>
+- Fix: <what you changed>
+
+## Findings (not fixed)
+Only list issues you could not self-fix (e.g. missing product decision, out-of-scope). Explain why.
+
+## Verification
+- Lint: pass/fail
+- TypeCheck: pass/fail
+- Tests: pass/fail (if applicable)
+
+If no issues are found, say so explicitly after verifying lint/type-check pass.
+"""
+
+# Disable Codex collab tools entirely for this sub-agent. With both
+# multi_agent and multi_agent_v2 off, `spawn_agent` / `wait_agent` /
+# `list_agents` / `close_agent` are not registered in the sub-agent's tool
+# list at all — the model literally cannot call them. This is the structural
+# fix for the wait_agent self-deadlock when the parent inherits its
+# transcript via Codex's default `fork_turns="all"` (#240 follow-up, #241).
+[features]
+multi_agent = false
+
+[features.multi_agent_v2]
+enabled = false

.codex/agents/trellis-implement.toml

@@ -0,0 +1,90 @@
+name = "trellis-implement"
+description = "Workspace-write Trellis implementer that follows specs and keeps generated templates in sync."
+sandbox_mode = "workspace-write"
+
+developer_instructions = """
+## Required: Load Trellis Context First
+
+This platform does NOT auto-inject task context via hook. Before doing anything else, you MUST load context yourself.
+
+### Step 1: Find the active task path
+
+Try in order — stop at the first one that yields a task path:
+
+1. **Look at the dispatch prompt** you received from the main agent. If its first line is `Active task: <path>` (e.g. `Active task: .trellis/tasks/04-17-foo`), use that path. The main agent is required to include this line on class-2 platforms.
+2. **Run** `python ./.trellis/scripts/task.py current --source` and read the `Current task:` line.
+3. **If both fail** (no `Active task:` line in the prompt and `task.py current` returns no task), ask the user which task to work on; do NOT guess.
+
+### Step 2: Load task context from the resolved path
+
+1. Read the task's `prd.md` (requirements) and `info.md` if it exists (technical design).
+2. Read `<task-path>/implement.jsonl` — JSONL list of dev spec files relevant to this agent.
+3. For each entry in the JSONL, Read its `file` path — these are the dev specs you must follow.
+   **Skip rows without a `"file"` field** (e.g. `{"_example": "..."}` seed rows left over from `task.py create` before the curator ran).
+
+If `implement.jsonl` has no curated entries (only a seed row, or the file is missing), fall back to: read `prd.md`, list available specs with `python ./.trellis/scripts/get_context.py --mode packages`, and pick the specs that match the task domain yourself. Do NOT block on the missing jsonl — proceed with prd-only context plus your spec judgment.
+
+If the resolved task path has no `prd.md`, ask the user what to work on; do NOT proceed without context.
+
+---
+
+You are running as the `trellis-implement` sub-agent. The main session has dispatched you to do the work.
+
+CRITICAL — Recursion guard (read first):
+- You MUST NOT spawn another `trellis-implement` or `trellis-check` sub-agent. Do the implementation work directly in this turn.
+- Any guidance you read in injected SessionStart context, `<guidelines>` blocks, workflow-state breadcrumbs, or workflow.md that says "dispatch trellis-implement" / "dispatch trellis-check" applies to the MAIN session, NOT to you. You are already the dispatched implementer — that instruction is satisfied by your existence.
+- Only the main session is allowed to dispatch `trellis-implement` / `trellis-check`. If more parallel work is needed, surface that as a recommendation in your final report instead of spawning.
+
+---
+
+## Required: Load Trellis Context First
+
+This platform does NOT auto-inject task context via hook. Before doing anything else, you MUST load context yourself.
+
+### Step 1: Find the active task path
+
+Try in order — stop at the first one that yields a task path:
+
+1. **Look at the dispatch prompt** you received from the main agent. If its first line is `Active task: <path>` (e.g. `Active task: .trellis/tasks/04-17-foo`), use that path. The main agent is required to include this line on class-2 platforms.
+2. **Run** `python ./.trellis/scripts/task.py current --source` and read the `Current task:` line.
+3. **If both fail** (no `Active task:` line in the prompt and `task.py current` returns no task), ask the user which task to work on; do NOT guess.
+
+### Step 2: Load task context from the resolved path
+
+1. Read the task's `prd.md` (requirements) and `info.md` if it exists (technical design).
+2. Read `<task-path>/implement.jsonl` — JSONL list of dev spec files relevant to this agent.
+3. For each entry in the JSONL, Read its `file` path — these are the dev specs you must follow.
+   **Skip rows without a `"file"` field** (e.g. `{"_example": "..."}` seed rows left over from `task.py create` before the curator ran).
+
+If `implement.jsonl` has no curated entries (only a seed row, or the file is missing), fall back to: read `prd.md`, list available specs with `python ./.trellis/scripts/get_context.py --mode packages`, and pick the specs that match the task domain yourself. Do NOT block on the missing jsonl — proceed with prd-only context plus your spec judgment.
+
+If the resolved task path has no `prd.md`, ask the user what to work on; do NOT proceed without context.
+
+---
+
+You are the Trellis implementer agent.
+
+Rules:
+- Read before write. Follow `.trellis/spec/` guidance relevant to the task.
+- Keep changes focused on the requested scope.
+- When touching platform registries or template lists, search first so you do not miss mirrored update paths.
+- If you modify `.trellis/scripts/`, keep `packages/cli/src/templates/trellis/scripts/` in sync.
+- Do not make destructive git changes unless explicitly asked.
+
+Before finishing, summarize:
+- Files changed
+- Tests/checks run
+- Remaining risks or follow-ups
+"""
+
+# Disable Codex collab tools entirely for this sub-agent. With both
+# multi_agent and multi_agent_v2 off, `spawn_agent` / `wait_agent` /
+# `list_agents` / `close_agent` are not registered in the sub-agent's tool
+# list at all — the model literally cannot call them. This is the structural
+# fix for the wait_agent self-deadlock when the parent inherits its
+# transcript via Codex's default `fork_turns="all"` (#240 follow-up, #241).
+[features]
+multi_agent = false
+
+[features.multi_agent_v2]
+enabled = false

.codex/agents/trellis-research.toml

@@ -0,0 +1,73 @@
+name = "trellis-research"
+description = "Trellis researcher for specs, code patterns, and affected files. Writes findings into {TASK_DIR}/research/ — read-only elsewhere."
+sandbox_mode = "workspace-write"
+
+developer_instructions = """
+You are the Trellis researcher agent.
+
+## Core principle
+
+Conversations get compacted; files don't. Every research topic MUST be
+persisted to `{TASK_DIR}/research/<topic>.md`. Returning findings only
+through the chat reply is a failure.
+
+## Workflow
+
+1. Run `python ./.trellis/scripts/task.py current --source` to get the
+   active task path and source. If no active task is set, ask the user
+   where to write output; do not guess.
+2. Run `mkdir -p <TASK_DIR>/research` to ensure the directory exists.
+3. Read `.trellis/workflow.md`, relevant `.trellis/spec/` files, and
+   target code before forming an opinion.
+4. For each research topic, write `<TASK_DIR>/research/<slug>.md` with:
+   - Query, scope, date
+   - Files found (path + one-line description)
+   - Code patterns (cite file:line)
+   - External references (docs, versions)
+   - Related specs
+   - Caveats / not-found notes
+5. Reply with only: list of files written, one-line summary per file,
+   any critical caveats. Do not paste full research into the reply.
+
+## Scope limits
+
+Write allowed ONLY in `{TASK_DIR}/research/`.
+
+Write forbidden everywhere else:
+- Code files (`src/`, `lib/`, …)
+- Spec files (`.trellis/spec/`) — use `update-spec` skill instead
+- `.trellis/scripts/`, `.trellis/workflow.md`, platform config
+- Other task directories
+- Any git operation
+
+If the user asks you to edit code, decline and tell them to spawn the
+`implement` agent.
+
+## Output format for each research file
+
+```
+# Research: <topic>
+
+- Query: ...
+- Scope: internal / external / mixed
+- Date: YYYY-MM-DD
+
+## Findings
+...
+
+## Caveats / Not Found
+...
+```
+"""
+
+# Disable Codex collab tools entirely for this sub-agent. With both
+# multi_agent and multi_agent_v2 off, `spawn_agent` / `wait_agent` /
+# `list_agents` / `close_agent` are not registered in the sub-agent's tool
+# list at all — the model literally cannot call them. This is the structural
+# fix for the wait_agent self-deadlock when the parent inherits its
+# transcript via Codex's default `fork_turns="all"` (#240 follow-up, #241).
+[features]
+multi_agent = false
+
+[features.multi_agent_v2]
+enabled = false

.codex/config.toml

@@ -0,0 +1,28 @@
+# Project-scoped Codex defaults for Trellis workflows.
+# Codex merges this layer after the user-level config when the project
+# is marked as a trusted project. To trust this project, add it under
+# `[projects]` in ~/.codex/config.toml, e.g.:
+#
+#   [projects."/abs/path/to/this/repo"]
+#   trust_level = "trusted"
+
+# Keep AGENTS.md as the primary project instruction file.
+project_doc_fallback_filenames = ["AGENTS.md"]
+
+# Codex hooks (`hooks.json` in this directory) only fire when the user
+# has enabled them in their USER-level config: `[features].hooks = true`
+# in ~/.codex/config.toml (Codex 0.129+; legacy name: `codex_hooks = true`,
+# still works but emits a deprecation warning on 0.129+). Project-level
+# config.toml cannot set feature flags; they must be user-level.
+# Codex 0.129+ additionally gates each installed hook behind a one-time
+# `/hooks` TUI review; until the user approves it, the hook stays inactive.
+
+# NOTE: Trellis intentionally does NOT write a [features.multi_agent_v2]
+# block here. Codex CLI changed `features` deserialization between 0.130
+# and 0.131: the structured table form (with max_concurrent_threads_per_session
+# / *_wait_timeout_ms) is only accepted by 0.131+. On 0.130 and earlier —
+# including the codex CLI bundled inside the Codex desktop app — it fails
+# with `data did not match any variant of untagged enum FeatureToml`, which
+# aborts the entire config load and blocks Codex from starting. Codex's own
+# default for multi_agent_v2 is used instead; tune it in your user-level
+# config if needed.

.codex/hooks.json

@@ -0,0 +1,15 @@
+{
+  "hooks": {
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "python -X utf8 .codex/hooks/inject-workflow-state.py",
+            "timeout": 15
+          }
+        ]
+      }
+    ]
+  }
+}

.codex/hooks/inject-workflow-state.py

@@ -0,0 +1,387 @@
+#!/usr/bin/env python3
+"""Trellis per-turn breadcrumb hook (UserPromptSubmit / BeforeAgent equivalent).
+
+Runs on every user prompt. Resolves the active task through Trellis'
+session-aware active task resolver and emits a short <workflow-state>
+block reminding the main AI what task is active and its expected flow.
+
+The emitted ``hookEventName`` field is platform-aware: most hosts expect
+``UserPromptSubmit`` (Claude Code naming, also accepted by Cursor / Qoder /
+CodeBuddy / Droid / Codex / Copilot wiring), but Gemini CLI 0.40.x renamed
+its per-turn event to ``BeforeAgent`` and its schema validator rejects the
+legacy name. ``_detect_platform`` picks the right value at runtime.
+Breadcrumb text is pulled exclusively from workflow.md
+[workflow-state:STATUS] tag blocks — workflow.md is the single source of
+truth. There are no fallback dicts in this script: when workflow.md is
+missing or a tag is absent, the breadcrumb degrades to a generic
+"Refer to workflow.md for current step." line so users see (and fix)
+the broken state instead of the hook silently masking it.
+
+Shared across all hook-capable platforms (Claude, Cursor, Codex, Qoder,
+CodeBuddy, Droid, Gemini, Copilot). Kiro is not wired (no per-turn
+hook entry point). Written to each platform's hooks directory via
+writeSharedHooks() at init time.
+
+Silent exit 0 cases (no output):
+  - No .trellis/ directory found (not a Trellis project)
+  - task.json malformed or missing status
+"""
+from __future__ import annotations
+
+import json
+import os
+import re
+import sys
+from pathlib import Path
+
+# Force UTF-8 on stdin/stdout/stderr on Windows. Default codepage there is
+# cp936 / cp1252 / etc. — non-ASCII content (Chinese task names, prd snippets)
+# both in stdin (hook payload from host CLI) and stdout (our emitted blocks)
+# raises UnicodeDecodeError / UnicodeEncodeError. Equivalent to `python -X utf8`
+# but applied per-stream so we don't depend on host CLI's command wiring.
+if sys.platform.startswith("win"):
+    import io as _io
+    for _stream_name in ("stdin", "stdout", "stderr"):
+        _stream = getattr(sys, _stream_name, None)
+        if _stream is None:
+            continue
+        if hasattr(_stream, "reconfigure"):
+            try:
+                _stream.reconfigure(encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+            except Exception:
+                pass
+        elif hasattr(_stream, "detach"):
+            try:
+                setattr(sys, _stream_name, _io.TextIOWrapper(_stream.detach(), encoding="utf-8", errors="replace"))
+            except Exception:
+                pass
+from typing import Optional
+
+
+CODEX_SUB_AGENT_NOTICE = """<sub-agent-notice>
+SUB-AGENT NOTICE - READ FIRST IF SPAWNED VIA spawn_agent
+
+If your parent session spawned you via spawn_agent with an explicit task
+message above this hook output, that message is your only job.
+- Execute the parent message exactly as written, then return.
+- Ignore all Trellis workflow guidance below this notice.
+- Do NOT call task.py start, task.py add-context, or task.py archive.
+- Do NOT call wait_agent or spawn_agent.
+- Do NOT modify .trellis/tasks/* or any other file unless the parent message
+  explicitly asks for that.
+
+If you are the main interactive Codex session and the user is typing at the
+terminal with no parent agent, use the workflow guidance below normally.
+</sub-agent-notice>"""
+
+
+# Bootstrap notice for Codex while the session has no active task. Replaces the
+# heavyweight SessionStart context injection — instead of pushing 9.5 KB of
+# workflow text up front, we just nudge the AI to read the `trellis-start` skill once.
+# The nudge keeps showing up while status == "no_task" (cheap text, AI won't
+# re-read after the first time). Once a task is created the breadcrumb status
+# flips and this notice stops appearing automatically. Sub-agents are warded
+# off by the <sub-agent-notice> above plus the explicit exemption below.
+CODEX_NO_TASK_BOOTSTRAP_NOTICE = """<trellis-bootstrap>
+You are running in a Trellis-managed Codex session and there is no active task yet.
+If you have not already loaded Trellis context this session, read the `trellis-start` skill once:
+
+  $trellis-start
+
+(equivalent to reading `.agents/skills/trellis-start/SKILL.md` and following its Steps 1-3)
+
+The skill walks you through workflow.md, dev profile, git status, active tasks, and spec
+indexes. Then route the user's request per the <workflow-state> A/B/C rules below.
+
+Sub-agent exemption: if you are a sub-agent (spawned via spawn_agent with a parent task
+message), DO NOT read `$trellis-start`. Execute the parent message directly as instructed by the
+<sub-agent-notice> above.
+</trellis-bootstrap>"""
+
+
+# ---------------------------------------------------------------------------
+# CWD-robust Trellis root discovery (fixes hook-path-robustness for this hook)
+# ---------------------------------------------------------------------------
+
+def find_trellis_root(start: Path) -> Optional[Path]:
+    """Walk up from start to find directory containing .trellis/.
+
+    Handles CWD drift: subdirectory launches, monorepo packages, etc.
+    Returns None if no .trellis/ found (silent no-op).
+    """
+    cur = start.resolve()
+    while cur != cur.parent:
+        if (cur / ".trellis").is_dir():
+            return cur
+        cur = cur.parent
+    return None
+
+
+# ---------------------------------------------------------------------------
+# Active task discovery
+# ---------------------------------------------------------------------------
+
+def _detect_platform(input_data: dict) -> str | None:
+    if isinstance(input_data.get("cursor_version"), str):
+        return "cursor"
+    env_map = {
+        "CLAUDE_PROJECT_DIR": "claude",
+        "CURSOR_PROJECT_DIR": "cursor",
+        "CODEBUDDY_PROJECT_DIR": "codebuddy",
+        "FACTORY_PROJECT_DIR": "droid",
+        "GEMINI_PROJECT_DIR": "gemini",
+        "QODER_PROJECT_DIR": "qoder",
+        "KIRO_PROJECT_DIR": "kiro",
+        "COPILOT_PROJECT_DIR": "copilot",
+    }
+    for env_name, platform in env_map.items():
+        if os.environ.get(env_name):
+            return platform
+    script_parts = set(Path(sys.argv[0]).parts)
+    if ".claude" in script_parts:
+        return "claude"
+    if ".cursor" in script_parts:
+        return "cursor"
+    if ".codex" in script_parts:
+        return "codex"
+    if ".gemini" in script_parts:
+        return "gemini"
+    if ".qoder" in script_parts:
+        return "qoder"
+    if ".codebuddy" in script_parts:
+        return "codebuddy"
+    if ".factory" in script_parts:
+        return "droid"
+    if ".kiro" in script_parts:
+        return "kiro"
+    return None
+
+
+def _resolve_active_task(root: Path, input_data: dict):
+    scripts_dir = root / ".trellis" / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    from common.active_task import resolve_active_task  # type: ignore[import-not-found]
+
+    return resolve_active_task(root, input_data, platform=_detect_platform(input_data))
+
+
+def get_active_task(root: Path, input_data: dict) -> Optional[tuple[str, str, str]]:
+    """Return (task_id, status, source) from the current active task."""
+    active = _resolve_active_task(root, input_data)
+    if not active.task_path:
+        return None
+
+    task_dir = Path(active.task_path)
+    if not task_dir.is_absolute():
+        task_dir = root / task_dir
+    if active.stale:
+        return task_dir.name, f"stale_{active.source_type}", active.source
+
+    task_json = task_dir / "task.json"
+    if not task_json.is_file():
+        return None
+    try:
+        data = json.loads(task_json.read_text(encoding="utf-8"))
+    except (json.JSONDecodeError, OSError):
+        return None
+
+    task_id = data.get("id") or task_dir.name
+    status = data.get("status", "")
+    if not isinstance(status, str) or not status:
+        return None
+    return task_id, status, active.source
+
+
+# ---------------------------------------------------------------------------
+# Breadcrumb loading: parse workflow.md, fall back to hardcoded defaults
+# ---------------------------------------------------------------------------
+
+# Supports STATUS values with letters, digits, underscores, hyphens
+# (so "in-review" / "blocked-by-team" work alongside "in_progress").
+_TAG_RE = re.compile(
+    r"\[workflow-state:([A-Za-z0-9_-]+)\]\s*\n(.*?)\n\s*\[/workflow-state:\1\]",
+    re.DOTALL,
+)
+
+def load_breadcrumbs(root: Path) -> dict[str, str]:
+    """Parse workflow.md for [workflow-state:STATUS] blocks.
+
+    Returns {status: body_text}. workflow.md is the single source of
+    truth — there are no fallback dicts in this script. Missing tags
+    (or a missing/unreadable workflow.md) fall back to a generic line
+    in build_breadcrumb so users see the broken state and fix
+    workflow.md, rather than the hook silently masking the issue.
+    """
+    workflow = root / ".trellis" / "workflow.md"
+    if not workflow.is_file():
+        return {}
+    try:
+        content = workflow.read_text(encoding="utf-8")
+    except OSError:
+        return {}
+
+    result: dict[str, str] = {}
+    for match in _TAG_RE.finditer(content):
+        status = match.group(1)
+        body = match.group(2).strip()
+        if body:
+            result[status] = body
+    return result
+
+
+def _read_trellis_config(root: Path) -> dict:
+    """Load .trellis/config.yaml via the bundled trellis_config helper.
+
+    The helper lives in .trellis/scripts/common; the hook lives outside the
+    scripts tree, so we extend sys.path before importing.
+    """
+    scripts_dir = root / ".trellis" / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    try:
+        from common.trellis_config import read_trellis_config  # type: ignore[import-not-found]
+    except Exception:
+        return {}
+    try:
+        return read_trellis_config(root)
+    except Exception:
+        return {}
+
+
+def _codex_mode_banner(config: dict) -> str:
+    """Emit a `<codex-mode>` banner for the additionalContext payload.
+
+    Reads `codex.dispatch_mode` from .trellis/config.yaml; defaults to
+    `inline` when missing or invalid because Codex sub-agents run with
+    `fork_turns="none"` isolation and can't inherit the parent session's
+    task context. The banner makes the active mode explicit to Codex AI
+    per turn, complementing the workflow-state body which is per-status.
+    Mode tells AI which dispatch protocol to follow; workflow-state tells
+    AI what step it's at.
+    """
+    mode = "inline"
+    if isinstance(config, dict):
+        codex_cfg = config.get("codex")
+        if isinstance(codex_cfg, dict):
+            cfg_mode = codex_cfg.get("dispatch_mode")
+            if cfg_mode in ("inline", "sub-agent"):
+                mode = cfg_mode
+    return f"<codex-mode>{mode}</codex-mode>"
+
+
+def resolve_breadcrumb_key(
+    status: str, platform: str | None, config: dict
+) -> str:
+    """Pick the breadcrumb tag key based on Codex dispatch_mode.
+
+    Codex defaults to ``inline`` because sub-agents run with ``fork_turns="none"``
+    isolation and can't inherit the parent session's task context. Users can
+    opt into ``codex.dispatch_mode: sub-agent`` in ``.trellis/config.yaml``
+    to use the parallel ``<status>-inline`` tag → ``<status>`` flip. Invalid
+    or missing values fall back to inline.
+
+    Non-codex platforms return the plain status unchanged.
+    """
+    if platform == "codex":
+        mode = "inline"
+        if isinstance(config, dict):
+            codex_cfg = config.get("codex")
+            if isinstance(codex_cfg, dict):
+                cfg_mode = codex_cfg.get("dispatch_mode")
+                if cfg_mode in ("inline", "sub-agent"):
+                    mode = cfg_mode
+        return f"{status}-inline" if mode == "inline" else status
+    return status
+
+
+def build_breadcrumb(
+    task_id: Optional[str],
+    status: str,
+    templates: dict[str, str],
+    source: str | None = None,
+    breadcrumb_key: str | None = None,
+) -> str:
+    """Build the <workflow-state>...</workflow-state> block.
+
+    - Known status (tag present in workflow.md) → detailed template body
+    - Unknown status (no tag, or workflow.md missing) → generic
+      "Refer to workflow.md for current step." line
+    - `no_task` pseudo-status (task_id is None) → header omits task info
+    """
+    lookup_key = breadcrumb_key or status
+    body = templates.get(lookup_key)
+    if body is None and lookup_key != status:
+        body = templates.get(status)
+    if body is None:
+        body = "Refer to workflow.md for current step."
+    header = f"Status: {status}" if task_id is None else f"Task: {task_id} ({status})"
+    if source:
+        header = f"{header}\nSource: {source}"
+    return f"<workflow-state>\n{header}\n{body}\n</workflow-state>"
+
+
+# ---------------------------------------------------------------------------
+# Entry
+# ---------------------------------------------------------------------------
+
+def main() -> int:
+    if os.environ.get("TRELLIS_HOOKS") == "0" or os.environ.get("TRELLIS_DISABLE_HOOKS") == "1":
+        return 0
+
+    try:
+        data = json.load(sys.stdin)
+    except (json.JSONDecodeError, ValueError):
+        data = {}
+
+    cwd_str = data.get("cwd") or os.getcwd()
+    cwd = Path(cwd_str)
+
+    root = find_trellis_root(cwd)
+    if root is None:
+        return 0  # not a Trellis project
+
+    templates = load_breadcrumbs(root)
+    platform = _detect_platform(data)
+    config = _read_trellis_config(root)
+    task = get_active_task(root, data)
+    if task is None:
+        # No active task — still emit a breadcrumb nudging AI toward
+        # trellis-brainstorm + task.py create when user describes real work.
+        no_task_key = resolve_breadcrumb_key("no_task", platform, config)
+        breadcrumb = build_breadcrumb(
+            None, "no_task", templates, breadcrumb_key=no_task_key
+        )
+    else:
+        task_id, status, source = task
+        status_key = resolve_breadcrumb_key(status, platform, config)
+        breadcrumb = build_breadcrumb(
+            task_id, status, templates, source, breadcrumb_key=status_key
+        )
+    if platform == "codex":
+        parts: list[str] = [CODEX_SUB_AGENT_NOTICE]
+        if task is None:
+            parts.append(CODEX_NO_TASK_BOOTSTRAP_NOTICE)
+        parts.append(_codex_mode_banner(config))
+        parts.append(breadcrumb)
+        breadcrumb = "\n\n".join(parts)
+
+    # Gemini CLI 0.40.x rejects "UserPromptSubmit" — its per-turn event is
+    # named "BeforeAgent". Other platforms (Claude/Cursor/Qoder/CodeBuddy/
+    # Droid/Codex/Copilot) accept the original Claude-style name.
+    hook_event_name = (
+        "BeforeAgent" if platform == "gemini" else "UserPromptSubmit"
+    )
+
+    output = {
+        "hookSpecificOutput": {
+            "hookEventName": hook_event_name,
+            "additionalContext": breadcrumb,
+        }
+    }
+    print(json.dumps(output))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.codex/hooks/session-start.py

@@ -0,0 +1,481 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Codex Session Start Hook - Inject Trellis context into Codex sessions.
+
+Output format follows Codex hook protocol:
+  stdout JSON → { hookSpecificOutput: { hookEventName: "SessionStart", additionalContext: "..." } }
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import re
+import subprocess
+import sys
+import warnings
+from io import StringIO
+from pathlib import Path
+
+# Force UTF-8 on stdin/stdout/stderr on Windows. Default codepage there is
+# cp936 / cp1252 / etc. — non-ASCII content (Chinese task names, prd snippets)
+# both in stdin (hook payload from host CLI) and stdout (our emitted blocks)
+# raises UnicodeDecodeError / UnicodeEncodeError. Equivalent to `python -X utf8`
+# but applied per-stream so we don't depend on host CLI's command wiring.
+if sys.platform.startswith("win"):
+    import io as _io
+    for _stream_name in ("stdin", "stdout", "stderr"):
+        _stream = getattr(sys, _stream_name, None)
+        if _stream is None:
+            continue
+        if hasattr(_stream, "reconfigure"):
+            try:
+                _stream.reconfigure(encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+            except Exception:
+                pass
+        elif hasattr(_stream, "detach"):
+            try:
+                setattr(sys, _stream_name, _io.TextIOWrapper(_stream.detach(), encoding="utf-8", errors="replace"))
+            except Exception:
+                pass
+
+
+def _normalize_windows_shell_path(path_str: str) -> str:
+    """Normalize Unix-style shell paths to real Windows paths.
+
+    On Windows, shells like Git Bash / MSYS2 / Cygwin may report paths like
+    `/d/Users/...` or `/cygdrive/d/Users/...`. `Path.resolve()` will misinterpret
+    these as `D:/d/Users...` on drive D: (or similar), breaking repo root
+    detection.
+
+    This function is intentionally conservative: it only rewrites patterns that
+    unambiguously represent a drive letter mount.
+    """
+    if not isinstance(path_str, str) or not path_str:
+        return path_str
+
+    # Only relevant on Windows; keep other platforms untouched.
+    if not sys.platform.startswith("win"):
+        return path_str
+
+    p = path_str.strip()
+
+    # Already a Windows drive path (C:\... or C:/...)
+    if re.match(r"^[A-Za-z]:[\/]", p):
+        return p
+
+    # MSYS/Git-Bash style: /c/Users/... or /d/Work/...
+    m = re.match(r"^/([A-Za-z])/(.*)", p)
+    if m:
+        drive, rest = m.group(1).upper(), m.group(2)
+        rest = rest.replace('/', '\\')
+        return f"{drive}:\\{rest}"
+
+    # Cygwin style: /cygdrive/c/Users/...
+    m = re.match(r"^/cygdrive/([A-Za-z])/(.*)", p)
+    if m:
+        drive, rest = m.group(1).upper(), m.group(2)
+        rest = rest.replace('/', '\\')
+        return f"{drive}:\\{rest}"
+
+    # WSL mounted drive (sometimes leaked into env): /mnt/c/Users/...
+    m = re.match(r"^/mnt/([A-Za-z])/(.*)", p)
+    if m:
+        drive, rest = m.group(1).upper(), m.group(2)
+        rest = rest.replace('/', '\\')
+        return f"{drive}:\\{rest}"
+
+    return path_str
+
+
+warnings.filterwarnings("ignore")
+
+FIRST_REPLY_NOTICE = """<first-reply-notice>
+On the first visible assistant reply in this session, begin with exactly one short Chinese sentence:
+Trellis SessionStart 已注入：workflow、当前任务状态、开发者身份、git 状态、active tasks、spec 索引已加载。
+Then continue directly with the user's request. This notice is one-shot: do not repeat it after the first assistant reply in the same session.
+</first-reply-notice>"""
+
+SUB_AGENT_NOTICE = """<sub-agent-notice>
+SUB-AGENT NOTICE - READ FIRST IF SPAWNED VIA spawn_agent
+
+If your parent session spawned you via spawn_agent with an explicit task
+message above this hook output, that message is your only job.
+- Execute the parent message exactly as written, then return.
+- Ignore all Trellis workflow guidance below this notice.
+- Do NOT call task.py start, task.py add-context, or task.py archive.
+- Do NOT call wait_agent or spawn_agent.
+- Do NOT modify .trellis/tasks/* or any other file unless the parent message
+  explicitly asks for that.
+
+If you are the main interactive Codex session and the user is typing at the
+terminal with no parent agent, use the workflow guidance below normally.
+</sub-agent-notice>"""
+
+
+def should_skip_injection() -> bool:
+    if os.environ.get("TRELLIS_HOOKS") == "0":
+        return True
+    if os.environ.get("TRELLIS_DISABLE_HOOKS") == "1":
+        return True
+    return os.environ.get("CODEX_NON_INTERACTIVE") == "1"
+
+
+def configure_project_encoding(project_dir: Path) -> None:
+    """Reuse Trellis' shared Windows stdio encoding helper before JSON output."""
+    scripts_dir = project_dir / ".trellis" / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+
+    try:
+        from common import configure_encoding  # type: ignore[import-not-found]
+
+        configure_encoding()
+    except Exception:
+        pass
+
+
+def _has_curated_jsonl_entry(jsonl_path: Path) -> bool:
+    """Return True iff jsonl has at least one row with a ``file`` field.
+
+    A freshly seeded jsonl only contains a ``{"_example": ...}`` row (no
+    ``file`` key) — that is NOT "ready". Readiness requires at least one
+    curated entry. Matches the contract used by ``inject-subagent-context.py``.
+    """
+    try:
+        for line in jsonl_path.read_text(encoding="utf-8").splitlines():
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                row = json.loads(line)
+            except json.JSONDecodeError:
+                continue
+            if isinstance(row, dict) and row.get("file"):
+                return True
+    except (OSError, UnicodeDecodeError):
+        return False
+    return False
+
+
+def read_file(path: Path, fallback: str = "") -> str:
+    try:
+        return path.read_text(encoding="utf-8")
+    except (FileNotFoundError, PermissionError):
+        return fallback
+
+
+def _resolve_context_key(project_dir: Path, hook_input: dict) -> str | None:
+    scripts_dir = project_dir / ".trellis" / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    try:
+        from common.active_task import resolve_context_key  # type: ignore[import-not-found]
+    except Exception:
+        return None
+    return resolve_context_key(hook_input, platform="codex")
+
+
+def _resolve_active_task(trellis_dir: Path, hook_input: dict):
+    scripts_dir = trellis_dir / "scripts"
+    if str(scripts_dir) not in sys.path:
+        sys.path.insert(0, str(scripts_dir))
+    from common.active_task import resolve_active_task  # type: ignore[import-not-found]
+
+    return resolve_active_task(trellis_dir.parent, hook_input, platform="codex")
+
+
+def run_script(script_path: Path, context_key: str | None = None) -> str:
+    try:
+        env = os.environ.copy()
+        env["PYTHONIOENCODING"] = "utf-8"
+        if context_key:
+            env["TRELLIS_CONTEXT_ID"] = context_key
+        cmd = [sys.executable, "-W", "ignore", str(script_path)]
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            encoding="utf-8",
+            errors="replace",
+            timeout=5,
+            cwd=str(script_path.parent.parent.parent),
+            env=env,
+        )
+        return result.stdout if result.returncode == 0 else "No context available"
+    except (subprocess.TimeoutExpired, FileNotFoundError, PermissionError):
+        return "No context available"
+
+
+def _normalize_task_ref(task_ref: str) -> str:
+    normalized = task_ref.strip()
+    if not normalized:
+        return ""
+
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return str(path_obj)
+
+    normalized = normalized.replace("\\", "/")
+    while normalized.startswith("./"):
+        normalized = normalized[2:]
+
+    if normalized.startswith("tasks/"):
+        return f".trellis/{normalized}"
+
+    return normalized
+
+
+def _resolve_task_dir(trellis_dir: Path, task_ref: str) -> Path:
+    normalized = _normalize_task_ref(task_ref)
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return path_obj
+    if normalized.startswith(".trellis/"):
+        return trellis_dir.parent / path_obj
+    return trellis_dir / "tasks" / path_obj
+
+
+def _get_task_status(trellis_dir: Path, hook_input: dict) -> str:
+    active = _resolve_active_task(trellis_dir, hook_input)
+    if not active.task_path:
+        return f"Status: NO ACTIVE TASK\nSource: {active.source}\nNext: Describe what you want to work on"
+
+    task_ref = active.task_path
+    task_dir = _resolve_task_dir(trellis_dir, task_ref)
+    if active.stale or not task_dir.is_dir():
+        return f"Status: STALE POINTER\nTask: {task_ref}\nSource: {active.source}\nNext: Task directory not found. Run: python ./.trellis/scripts/task.py finish"
+
+    task_json_path = task_dir / "task.json"
+    task_data: dict = {}
+    if task_json_path.is_file():
+        try:
+            task_data = json.loads(task_json_path.read_text(encoding="utf-8"))
+        except (json.JSONDecodeError, PermissionError):
+            pass
+
+    task_title = task_data.get("title", task_ref)
+    task_status = task_data.get("status", "unknown")
+
+    if task_status == "completed":
+        return f"Status: COMPLETED\nTask: {task_title}\nSource: {active.source}\nNext: Archive with `python ./.trellis/scripts/task.py archive {task_dir.name}` or start a new task"
+
+    has_context = False
+    for jsonl_name in ("implement.jsonl", "check.jsonl", "spec.jsonl"):
+        jsonl_path = task_dir / jsonl_name
+        if jsonl_path.is_file() and _has_curated_jsonl_entry(jsonl_path):
+            has_context = True
+            break
+
+    has_prd = (task_dir / "prd.md").is_file()
+
+    if not has_prd:
+        return f"Status: NOT READY\nTask: {task_title}\nSource: {active.source}\nMissing: prd.md not created\nNext: Write PRD (see workflow.md Phase 1.1) then curate implement.jsonl per Phase 1.3"
+
+    if not has_context:
+        return f"Status: NOT READY\nTask: {task_title}\nSource: {active.source}\nMissing: implement.jsonl / check.jsonl missing or empty\nNext: Curate entries per workflow.md Phase 1.3 (spec + research files only), then `task.py start`"
+
+    return (
+        f"Status: READY\nTask: {task_title}\n"
+        f"Source: {active.source}\n"
+        "Next required action: dispatch `trellis-implement` per Phase 2.1. "
+        "For agent-capable platforms, the default is to NOT edit code in the main session. "
+        "After implementation, dispatch `trellis-check` per Phase 2.2 before reporting completion.\n"
+        "Sub-agent self-exemption: if you are reading this as a `trellis-implement` or "
+        "`trellis-check` sub-agent (your own role / agent name reflects that), this dispatch "
+        "instruction does NOT apply to you — you are already the dispatched sub-agent. "
+        "Implement / check directly without spawning another sub-agent of the same kind.\n"
+        "User override (per-turn escape hatch): if the user's CURRENT message explicitly tells the "
+        "main session to handle it directly (\"你直接改\" / \"别派 sub-agent\" / \"main session 写就行\" / "
+        "\"do it inline\" / \"不用 sub-agent\"), honor it for this turn and edit code directly. "
+        "Per-turn only; do NOT invent an override the user did not say."
+    )
+
+
+def _extract_range(content: str, start_header: str, end_header: str) -> str:
+    """Extract lines starting at `## start_header` up to (but excluding) `## end_header`."""
+    lines = content.splitlines()
+    start: "int | None" = None
+    end: int = len(lines)
+    start_match = f"## {start_header}"
+    end_match = f"## {end_header}"
+    for i, line in enumerate(lines):
+        stripped = line.strip()
+        if start is None and stripped == start_match:
+            start = i
+            continue
+        if start is not None and stripped == end_match:
+            end = i
+            break
+    if start is None:
+        return ""
+    return "\n".join(lines[start:end]).rstrip()
+
+
+_BREADCRUMB_TAG_RE = re.compile(
+    r"\[workflow-state:([A-Za-z0-9_-]+)\]\s*\n.*?\n\s*\[/workflow-state:\1\]",
+    re.DOTALL,
+)
+
+
+def _strip_breadcrumb_tag_blocks(content: str) -> str:
+    return _BREADCRUMB_TAG_RE.sub("", content)
+
+
+def _build_workflow_toc(workflow_path: Path) -> str:
+    """Inject workflow guide: TOC + Phase Index + Phase 1/2/3 step details.
+
+    Since v0.5.0-rc.0 the [workflow-state:STATUS] breadcrumb tag blocks
+    live inside ## Phase Index. They're consumed by inject-workflow-state.py
+    on each UserPromptSubmit, so strip them from the session-start payload
+    to avoid duplicating context.
+    """
+    content = read_file(workflow_path)
+    if not content:
+        return "No workflow.md found"
+
+    out_lines = [
+        "# Development Workflow — Section Index",
+        "Full guide: .trellis/workflow.md  (read on demand)",
+        "",
+        "## Table of Contents",
+    ]
+    for line in content.splitlines():
+        if line.startswith("## "):
+            out_lines.append(line)
+    out_lines += ["", "---", ""]
+
+    phases = _extract_range(content, "Phase Index", "Customizing Trellis (for forks)")
+    if phases:
+        out_lines.append(_strip_breadcrumb_tag_blocks(phases).rstrip())
+
+    return "\n".join(out_lines).rstrip()
+
+
+def main() -> None:
+    if should_skip_injection():
+        sys.exit(0)
+
+    # Read hook input from stdin
+    try:
+        hook_input = json.loads(sys.stdin.read())
+        if not isinstance(hook_input, dict):
+            hook_input = {}
+        project_dir = Path(_normalize_windows_shell_path(hook_input.get("cwd", "."))).resolve()
+    except (json.JSONDecodeError, KeyError):
+        hook_input = {}
+        project_dir = Path(".").resolve()
+
+    configure_project_encoding(project_dir)
+
+    trellis_dir = project_dir / ".trellis"
+    context_key = _resolve_context_key(project_dir, hook_input)
+
+    output = StringIO()
+
+    output.write(SUB_AGENT_NOTICE)
+    output.write("\n\n")
+
+    output.write("""<session-context>
+You are starting a new session in a Trellis-managed project.
+Read and follow all instructions below carefully.
+</session-context>
+
+""")
+    output.write(FIRST_REPLY_NOTICE)
+    output.write("\n\n")
+
+    output.write("<current-state>\n")
+    context_script = trellis_dir / "scripts" / "get_context.py"
+    output.write(run_script(context_script, context_key))
+    output.write("\n</current-state>\n\n")
+
+    output.write("<workflow>\n")
+    output.write(_build_workflow_toc(trellis_dir / "workflow.md"))
+    output.write("\n</workflow>\n\n")
+
+    output.write("<guidelines>\n")
+    output.write(
+        "Project spec indexes are listed by path below. Each index contains a "
+        "**Pre-Development Checklist** listing the specific guideline files to "
+        "read before coding.\n\n"
+        "- If you're spawning an implement/check sub-agent, context is injected "
+        "automatically via `{task}/implement.jsonl` / `check.jsonl`. You do NOT "
+        "need to read these indexes yourself.\n"
+        "- For agent-capable platforms, the default is to dispatch "
+        "`trellis-implement` and `trellis-check` (so JSONL context is loaded by "
+        "the sub-agents) rather than editing code in the main session. "
+        "Honor a per-turn user override only if the user's current message "
+        "explicitly opts out (see <task-status> below for override phrases).\n"
+        "- Sub-agent self-exemption: if you are reading this as a `trellis-implement` "
+        "or `trellis-check` sub-agent, the \"dispatch trellis-implement / trellis-check\" "
+        "rule above does NOT apply to you — you are already the dispatched sub-agent. "
+        "Do NOT spawn another sub-agent of the same kind; implement / check directly.\n\n"
+    )
+
+    # guides/ inlined (cross-package thinking, broadly useful)
+    guides_index = trellis_dir / "spec" / "guides" / "index.md"
+    if guides_index.is_file():
+        output.write("## guides (inlined — cross-package thinking guides)\n")
+        output.write(read_file(guides_index))
+        output.write("\n\n")
+
+    # Other indexes — paths only
+    paths: list[str] = []
+    spec_dir = trellis_dir / "spec"
+    if spec_dir.is_dir():
+        for sub in sorted(spec_dir.iterdir()):
+            if not sub.is_dir() or sub.name.startswith("."):
+                continue
+            if sub.name == "guides":
+                continue
+            index_file = sub / "index.md"
+            if index_file.is_file():
+                paths.append(f".trellis/spec/{sub.name}/index.md")
+            else:
+                for nested in sorted(sub.iterdir()):
+                    if not nested.is_dir():
+                        continue
+                    nested_index = nested / "index.md"
+                    if nested_index.is_file():
+                        paths.append(
+                            f".trellis/spec/{sub.name}/{nested.name}/index.md"
+                        )
+
+    if paths:
+        output.write("## Available spec indexes (read on demand)\n")
+        for p in paths:
+            output.write(f"- {p}\n")
+        output.write("\n")
+
+    output.write(
+        "Discover more via: "
+        "`python ./.trellis/scripts/get_context.py --mode packages`\n"
+    )
+    output.write("</guidelines>\n\n")
+
+    task_status = _get_task_status(trellis_dir, hook_input)
+    output.write(f"<task-status>\n{task_status}\n</task-status>\n\n")
+
+    output.write("""<ready>
+Context loaded. Workflow index, project state, and guidelines are already injected above — do NOT re-read them.
+When the user sends the first message, follow <task-status> and the workflow guide.
+If a task is READY, execute its Next required action without asking whether to continue.
+</ready>""")
+
+    context = output.getvalue()
+    result = {
+        "suppressOutput": True,
+        "systemMessage": f"Trellis context injected ({len(context)} chars)",
+        "hookSpecificOutput": {
+            "hookEventName": "SessionStart",
+            "additionalContext": context,
+        },
+    }
+
+    print(json.dumps(result, ensure_ascii=False), flush=True)
+
+
+if __name__ == "__main__":
+    main()

.trellis/.gitignore

@@ -0,0 +1,32 @@
+# Developer identity (local only)
+.developer
+
+# Current task pointer (each dev works on different task)
+.current-task
+
+# Session/window scoped runtime state
+.runtime/
+
+# Ralph Loop state file
+.ralph-state.json
+
+# Agent runtime files
+.agents/
+.agent-log
+.session-id
+
+# Task directory runtime files
+.plan-log
+
+# Atomic update temp files
+*.tmp
+
+# Update backup directories
+.backup-*
+
+# Conflict resolution temp files
+*.new
+
+# Python cache
+**/__pycache__/
+**/*.pyc

.trellis/.template-hashes.json

@@ -0,0 +1,119 @@
+{
+  "__version": 2,
+  "hashes": {
+    ".claude/agents/trellis-check.md": "d1359521f7f3e9bbbf10e856a3e0912c423581a88ac188b1f0523d6357962909",
+    ".claude/agents/trellis-implement.md": "61155f06ccdd26e5aeb8171face2a029a8fb77a3d1a2b277442ded186853446c",
+    ".claude/agents/trellis-research.md": "f95e69d638266056713e79c884ead1e99d376d70284f66255b6dd139a3e712be",
+    ".claude/settings.json": "01226db3027908dac1260955e205877ee46c1d410912172d8bae9c53527b3b0f",
+    ".claude/hooks/inject-subagent-context.py": "d8d69631b43ef469030ff78410c2e082f721f79b7d6eaa754b7a1a1c05810242",
+    ".claude/hooks/inject-workflow-state.py": "fe4cca4db7ca8c252f614efca16fa588009a4238542a2c9aa85167409f6f9a4c",
+    ".claude/hooks/session-start.py": "8b31b8e87f6a678ca58711b5558a5292cb0cfea0cb9c54a75b0c7186efcfb58a",
+    ".claude/commands/trellis/continue.md": "e609e940236f33a9b05a15173606cc3f72285994904d6723382c490d94994aba",
+    ".claude/commands/trellis/finish-work.md": "f11f661cff6d5d26dccb5e9574c3d2c7873a9dfaed7962d471ff5ea2fd48d691",
+    ".claude/skills/trellis-before-dev/SKILL.md": "310e0121d5915a8aa46596fc172b53a7bdbaae4fd11699500e3166783a15a180",
+    ".claude/skills/trellis-brainstorm/SKILL.md": "603d023a10dbee625d540df98020f2dde4b6e5c2bf981226253b88d8eff7c388",
+    ".claude/skills/trellis-break-loop/SKILL.md": "35afb53fef42cd494e566f1ef170dbf442ec2be7e19931f28a14079b4dda753f",
+    ".claude/skills/trellis-check/SKILL.md": "8ce33f85051a339e77722bab214562ba7aa041629e285381434bf51c7c710205",
+    ".claude/skills/trellis-update-spec/SKILL.md": "d975db7af166578488958751ae2c56edb827a68bddb569aa27acc3453f64e610",
+    ".claude/skills/trellis-meta/references/customize-local/add-project-local-conventions.md": "ef3380e71aa9f5103d37b467b1f725a8033ac516e4de31e4d790be02ec2c39e8",
+    ".claude/skills/trellis-meta/references/customize-local/change-agents.md": "7f2982162463f107f8b1a4fa1a41fee2bc7dbd0cc8e90c48559aba30c3ea403c",
+    ".claude/skills/trellis-meta/references/customize-local/change-context-loading.md": "aacdaaca13a4420b9fddf0023d90d3bf06d4aa96ae51c44a201f81b3f3723088",
+    ".claude/skills/trellis-meta/references/customize-local/change-hooks.md": "c8b35dda1530de521cf6bb043188f0cbbea0c9180b1aa44e64e31e20433ef4ca",
+    ".claude/skills/trellis-meta/references/customize-local/change-skills-or-commands.md": "b3009ef20a4f24e5d8b196109dc9bab6bd30fc030dbc4fb796afdd2ca912e1ea",
+    ".claude/skills/trellis-meta/references/customize-local/change-spec-structure.md": "b6facc3976df445ff478ca06459b87b67b7c494b98ccfc53a55bdb78a079babf",
+    ".claude/skills/trellis-meta/references/customize-local/change-task-lifecycle.md": "148b7442ef8106de907afd06f9d1ca96f7ec074caedced3dd4175b3a26698ca2",
+    ".claude/skills/trellis-meta/references/customize-local/change-workflow.md": "6f1707a2cc032c50e41e5624cef46071dd53dc9810bc6b3cae66d86508dea1cb",
+    ".claude/skills/trellis-meta/references/customize-local/overview.md": "465db9cecf085b37f7aed2fc5240c92c638e937f7960ca35b0f05a780dd4fdc9",
+    ".claude/skills/trellis-meta/references/local-architecture/context-injection.md": "31286b9c05e600db7d179100eca533f9b8a4aab3a9c255cb69e8dccacb4e8375",
+    ".claude/skills/trellis-meta/references/local-architecture/generated-files.md": "4356517517cef0ba7f3ba01965a4ba8953505702e4085f0797d3e36817c9669f",
+    ".claude/skills/trellis-meta/references/local-architecture/overview.md": "45ffd4ee95020f58201adc885f3dfc89b26483c2b350d96ca7f2f57f94d5ff5f",
+    ".claude/skills/trellis-meta/references/local-architecture/spec-system.md": "dd53adaf18374c8ce598092a24847c43a4e661b2708c379615e86defd21f107d",
+    ".claude/skills/trellis-meta/references/local-architecture/task-system.md": "c80af5ae864b86c33eac4442d1244451f6cbcf5f87effccd17cd1856aa00315e",
+    ".claude/skills/trellis-meta/references/local-architecture/workflow.md": "cfcdc6e4468a5d9c816e929fcca01640cd41cfdaaa4824118b40a8e460c927b6",
+    ".claude/skills/trellis-meta/references/local-architecture/workspace-memory.md": "79786a1ca2980b1785a36aba8142f9d879459c47dc000c999f638e5c864d04d3",
+    ".claude/skills/trellis-meta/references/platform-files/agents.md": "700e1b7ba89b304f0ee7d26528d897f0c66e382801913e20b59323651f5ca675",
+    ".claude/skills/trellis-meta/references/platform-files/hooks-and-settings.md": "6e2d6d88719c2779fe34004f63d36cff203d8f64e7fb620f7cb1cde15c37c462",
+    ".claude/skills/trellis-meta/references/platform-files/overview.md": "6479cd2393166b4b369b511c44b78cbc64975c8b1df96ee1d4d1bd06b75cd48d",
+    ".claude/skills/trellis-meta/references/platform-files/platform-map.md": "ded6751c06f31d0a701d33c9dd69c482a583539ad3ed464aaad9e705f793b212",
+    ".claude/skills/trellis-meta/references/platform-files/skills-and-commands.md": "85435eb8bb6921283575bca51268fc534c22fd3ca33782e841ee5c76140ae48f",
+    ".claude/skills/trellis-meta/SKILL.md": "942e898a6fd769a93a3ca6f43f9fe0412d0adae011654fd384e9cacbd2af4f34",
+    ".claude/skills/trellis-spec-bootstarp/references/mcp-setup.md": "df542fc8f279edd38046d26a7c8151804b708f57b24d4aa2733cea587a88c65e",
+    ".claude/skills/trellis-spec-bootstarp/references/repository-analysis.md": "0dae98d774f6e34559b9f3442888ac43e3a8af110c37cbefc49ce256986858b6",
+    ".claude/skills/trellis-spec-bootstarp/references/spec-task-planning.md": "ef493d028c3b0807a8a534bb71fb92a68129f273db763ad27ceb464a522e799d",
+    ".claude/skills/trellis-spec-bootstarp/references/spec-writing.md": "e9800fe9ed4a4cd87062ea1829cf2caa8d170ec15e141678a6a30e74c497f47d",
+    ".claude/skills/trellis-spec-bootstarp/SKILL.md": "81f400092b21392161e7d9dfa9111c9be36c81bc8641d252ed28e08373449ac0",
+    ".agents/skills/trellis-continue/SKILL.md": "122b45675d33e23e71540a591606d9ba8d028215b2abcd07db86bf45624841dd",
+    ".agents/skills/trellis-finish-work/SKILL.md": "79e6d165358253a7379cae647bbd50b6bf174a1107f451b768a2bb4ba7cc0b87",
+    ".agents/skills/trellis-before-dev/SKILL.md": "310e0121d5915a8aa46596fc172b53a7bdbaae4fd11699500e3166783a15a180",
+    ".agents/skills/trellis-brainstorm/SKILL.md": "0ade8c1cd37e107a2e878025ffc42e8a870d154bcad53f8c63399836aa40a635",
+    ".agents/skills/trellis-break-loop/SKILL.md": "35afb53fef42cd494e566f1ef170dbf442ec2be7e19931f28a14079b4dda753f",
+    ".agents/skills/trellis-check/SKILL.md": "8ce33f85051a339e77722bab214562ba7aa041629e285381434bf51c7c710205",
+    ".agents/skills/trellis-update-spec/SKILL.md": "003ce08a3404aeb50998029392c4d4e57b626edf526d3ebd585032bb92dcbb96",
+    ".agents/skills/trellis-meta/references/customize-local/add-project-local-conventions.md": "ef3380e71aa9f5103d37b467b1f725a8033ac516e4de31e4d790be02ec2c39e8",
+    ".agents/skills/trellis-meta/references/customize-local/change-agents.md": "7f2982162463f107f8b1a4fa1a41fee2bc7dbd0cc8e90c48559aba30c3ea403c",
+    ".agents/skills/trellis-meta/references/customize-local/change-context-loading.md": "aacdaaca13a4420b9fddf0023d90d3bf06d4aa96ae51c44a201f81b3f3723088",
+    ".agents/skills/trellis-meta/references/customize-local/change-hooks.md": "c8b35dda1530de521cf6bb043188f0cbbea0c9180b1aa44e64e31e20433ef4ca",
+    ".agents/skills/trellis-meta/references/customize-local/change-skills-or-commands.md": "b3009ef20a4f24e5d8b196109dc9bab6bd30fc030dbc4fb796afdd2ca912e1ea",
+    ".agents/skills/trellis-meta/references/customize-local/change-spec-structure.md": "b6facc3976df445ff478ca06459b87b67b7c494b98ccfc53a55bdb78a079babf",
+    ".agents/skills/trellis-meta/references/customize-local/change-task-lifecycle.md": "148b7442ef8106de907afd06f9d1ca96f7ec074caedced3dd4175b3a26698ca2",
+    ".agents/skills/trellis-meta/references/customize-local/change-workflow.md": "6f1707a2cc032c50e41e5624cef46071dd53dc9810bc6b3cae66d86508dea1cb",
+    ".agents/skills/trellis-meta/references/customize-local/overview.md": "465db9cecf085b37f7aed2fc5240c92c638e937f7960ca35b0f05a780dd4fdc9",
+    ".agents/skills/trellis-meta/references/local-architecture/context-injection.md": "31286b9c05e600db7d179100eca533f9b8a4aab3a9c255cb69e8dccacb4e8375",
+    ".agents/skills/trellis-meta/references/local-architecture/generated-files.md": "4356517517cef0ba7f3ba01965a4ba8953505702e4085f0797d3e36817c9669f",
+    ".agents/skills/trellis-meta/references/local-architecture/overview.md": "45ffd4ee95020f58201adc885f3dfc89b26483c2b350d96ca7f2f57f94d5ff5f",
+    ".agents/skills/trellis-meta/references/local-architecture/spec-system.md": "dd53adaf18374c8ce598092a24847c43a4e661b2708c379615e86defd21f107d",
+    ".agents/skills/trellis-meta/references/local-architecture/task-system.md": "c80af5ae864b86c33eac4442d1244451f6cbcf5f87effccd17cd1856aa00315e",
+    ".agents/skills/trellis-meta/references/local-architecture/workflow.md": "cfcdc6e4468a5d9c816e929fcca01640cd41cfdaaa4824118b40a8e460c927b6",
+    ".agents/skills/trellis-meta/references/local-architecture/workspace-memory.md": "79786a1ca2980b1785a36aba8142f9d879459c47dc000c999f638e5c864d04d3",
+    ".agents/skills/trellis-meta/references/platform-files/agents.md": "700e1b7ba89b304f0ee7d26528d897f0c66e382801913e20b59323651f5ca675",
+    ".agents/skills/trellis-meta/references/platform-files/hooks-and-settings.md": "6e2d6d88719c2779fe34004f63d36cff203d8f64e7fb620f7cb1cde15c37c462",
+    ".agents/skills/trellis-meta/references/platform-files/overview.md": "6479cd2393166b4b369b511c44b78cbc64975c8b1df96ee1d4d1bd06b75cd48d",
+    ".agents/skills/trellis-meta/references/platform-files/platform-map.md": "ded6751c06f31d0a701d33c9dd69c482a583539ad3ed464aaad9e705f793b212",
+    ".agents/skills/trellis-meta/references/platform-files/skills-and-commands.md": "85435eb8bb6921283575bca51268fc534c22fd3ca33782e841ee5c76140ae48f",
+    ".agents/skills/trellis-meta/SKILL.md": "942e898a6fd769a93a3ca6f43f9fe0412d0adae011654fd384e9cacbd2af4f34",
+    ".agents/skills/trellis-spec-bootstarp/references/mcp-setup.md": "df542fc8f279edd38046d26a7c8151804b708f57b24d4aa2733cea587a88c65e",
+    ".agents/skills/trellis-spec-bootstarp/references/repository-analysis.md": "0dae98d774f6e34559b9f3442888ac43e3a8af110c37cbefc49ce256986858b6",
+    ".agents/skills/trellis-spec-bootstarp/references/spec-task-planning.md": "ef493d028c3b0807a8a534bb71fb92a68129f273db763ad27ceb464a522e799d",
+    ".agents/skills/trellis-spec-bootstarp/references/spec-writing.md": "e9800fe9ed4a4cd87062ea1829cf2caa8d170ec15e141678a6a30e74c497f47d",
+    ".agents/skills/trellis-spec-bootstarp/SKILL.md": "81f400092b21392161e7d9dfa9111c9be36c81bc8641d252ed28e08373449ac0",
+    ".agents/skills/trellis-start/SKILL.md": "1079cf20a0c7b7decff5f992cb31c7a212debad819c290a95fc1bb855c0356b7",
+    ".codex/agents/trellis-check.toml": "a89c70b6ac6ee0a77bc215a22c3097d60605269818434e9f37949a01355a47d8",
+    ".codex/agents/trellis-implement.toml": "ba118cdc8ec8665b64de3fd7d6dc76788374807d3db2d40c7612b05df0506cdd",
+    ".codex/agents/trellis-research.toml": "73bf9654d99ee60cec9f6d77fe60fe2e32afbdd7d3f01c8f759c131364bf3c31",
+    ".codex/hooks/session-start.py": "3fd36631fc85a9d12a698d79b459008d568dc276bc0aa2bf0191acebb559c934",
+    ".codex/hooks/inject-workflow-state.py": "fe4cca4db7ca8c252f614efca16fa588009a4238542a2c9aa85167409f6f9a4c",
+    ".codex/hooks.json": "7bad6065612c5bd0d4e0bb587bf3c9f3950c8060f9a52f4defd7247dd9ba8aec",
+    ".codex/config.toml": "4224eb7df6802a623cb1bee522aed0a23ba6be862b90f1b597a313fc16864b06",
+    "AGENTS.md": "6cacfe99748b435d0660c2463c697bc323d53798aecf3492283ca8eac1b29682",
+    ".trellis/config.yaml": "5c9207418cecc390e9d86d589b4183b831f76697d92fb42fefd5221cd8772e51",
+    ".trellis/scripts/add_session.py": "f26b66a539d160c739d4b88fd926b3d7f6745be326cd57131e5ef17a7b011fbe",
+    ".trellis/scripts/common/active_task.py": "6c88ed40ef7289bca0f6d2ecba0f8b8aef46cd58788080fbeeea88de138a431f",
+    ".trellis/scripts/common/cli_adapter.py": "cd844d1e84b1a09b373b3a7609e4d5606ee9d4825154c002cc9bb3f54c8e2fb9",
+    ".trellis/scripts/common/config.py": "25c5a53ad20d6909be5209222e4208a84528805316a4d78350529459a364edb1",
+    ".trellis/scripts/common/developer.py": "b2141b0145a41f8cedb4f9a24c925796edb2f0f6fde7c86b559513ec30499368",
+    ".trellis/scripts/common/git.py": "e14817be7de122d3a106f509c2825aeb9669d962ba73ba241642d2931cfdf1d6",
+    ".trellis/scripts/common/git_context.py": "fa30ced454f1a91ffc9f8b2abeb32225e3447cbdc90bad783797374eba07265d",
+    ".trellis/scripts/common/io.py": "6480b181f2bc505323b28ed7a66963d7b7edc96251e83b4c8e7a45907cc721c8",
+    ".trellis/scripts/common/log.py": "471df6895cfac80f995edebbf9974f6b7440634b7a688f28b8331c868bc0f3cf",
+    ".trellis/scripts/common/packages_context.py": "efe158d7c99c2268851d0216fbb08de22836e418a8dbeb73575b8cc249eed7b7",
+    ".trellis/scripts/common/paths.py": "05898ef136cc7c4d861b05fbf2b16d53ddd3e6f311a231d4fcfcb81bde7c45ee",
+    ".trellis/scripts/common/safe_commit.py": "8789bff4b30a9065469210f2efab3f59f03dddd77bef4e4b6a5bb641f93539f4",
+    ".trellis/scripts/common/session_context.py": "d669b96fd7a608808695b9e82e9bfd1693a9ae98ade03cc8dce6c24487696793",
+    ".trellis/scripts/common/tasks.py": "4436a8b0b53c270a35989e26d9dbd92669408c6562d88c02083a404562da85fe",
+    ".trellis/scripts/common/task_context.py": "1c16a7fa82d363010d0d0ebdc038296ae1552bf6e90214787d707f49567bc159",
+    ".trellis/scripts/common/task_queue.py": "0be61f713462b1fe4574927c82fc4704e678afe72dcb9813543aedf2f9e9e0c5",
+    ".trellis/scripts/common/task_store.py": "4a6ad7f15fd6fdca0da174804ee2d750919d42e46066a891c7525aa8d8a2c592",
+    ".trellis/scripts/common/task_utils.py": "f5ef4af87ba3e11d8b19630c0c96d009de1811fc9be56c2027a9c96e21ed103e",
+    ".trellis/scripts/common/trellis_config.py": "0839dcf90ebbd77712c276930a89335b3313927051650c91d220fb51ca2a6a3c",
+    ".trellis/scripts/common/types.py": "9962081cc2608fb9d1deb32c6880e336f62cdca6b338e7ae813304701e155ee9",
+    ".trellis/scripts/common/workflow_phase.py": "2b260f4a7770e9c3223129836716bd8e2c0f0568acd682224a57415bc1dc726b",
+    ".trellis/scripts/common/__init__.py": "3d5e9347141f0296319a5beb29d69ae714c5a474b9078caeb3edd7c5f6562e22",
+    ".trellis/scripts/get_context.py": "af3ea7cd563a453227cf2cb4ab04d667390046b7febfac2217348d0892781f4b",
+    ".trellis/scripts/get_developer.py": "84c27076323c3e0f2c9c8ed16e8aa865e225d902a187c37e20ee1a46e7142d8f",
+    ".trellis/scripts/hooks/linear_sync.py": "cfc270b7ff775caa5b2434823c45414a3b37f9ba2aa1e293a26daef9fd2e577a",
+    ".trellis/scripts/init_developer.py": "0943f1c240993649ab89b91a2c5b379e84daa8c53b35f0490774bff05a552873",
+    ".trellis/scripts/task.py": "e2614fbfc1308c90c0708a11475ca6684ea0a1e2a845140300192229589a2f1f",
+    ".trellis/scripts/__init__.py": "1242be5b972094c2e141aecbe81a4efd478f6534e3d5e28306374e6a18fcf46c",
+    ".trellis/workflow.md": "94810f640dcfe6fdaebcf6e9d0d6cec554610192c4f953b288029570ba8bc89d"
+  }
+}

.trellis/.version

@@ -0,0 +1 @@
+0.5.19

.trellis/config.yaml

@@ -0,0 +1,90 @@
+# Trellis Configuration
+# Project-level settings for the Trellis workflow system
+#
+# All values have sensible defaults. Only override what you need.
+
+#-------------------------------------------------------------------------------
+# Session Recording
+#-------------------------------------------------------------------------------
+
+# Commit message used when auto-committing journal/index changes
+# after running add_session.py
+session_commit_message: "chore: record journal"
+
+# Maximum lines per journal file before rotating to a new one
+max_journal_lines: 2000
+
+#-------------------------------------------------------------------------------
+# Session Auto-Commit
+#-------------------------------------------------------------------------------
+
+# Auto-commit behavior for session journal + task archive operations.
+# - true (default): scripts auto-stage and auto-commit journal / task changes
+#   after add_session.py / task.py archive runs.
+# - false: scripts do not touch git. Files (journal-*.md, task archive moves)
+#   are still written to disk; you decide whether to git add / commit.
+#
+# Use `false` if your project's .gitignore intentionally excludes `.trellis/`
+# and you want session data kept local-only, or if you prefer to review
+# staged changes manually before each commit.
+#
+# Accepts: true / false / yes / no / 1 / 0 / on / off (case-insensitive).
+#
+# session_auto_commit: true
+
+#-------------------------------------------------------------------------------
+# Task Lifecycle Hooks
+#-------------------------------------------------------------------------------
+
+# Shell commands to run after task lifecycle events.
+# Each hook receives TASK_JSON_PATH environment variable pointing to task.json.
+# Hook failures print a warning but do not block the main operation.
+#
+# hooks:
+#   after_create:
+#     - "echo 'Task created'"
+#   after_start:
+#     - "echo 'Task started'"
+#   after_finish:
+#     - "echo 'Task finished'"
+#   after_archive:
+#     - "echo 'Task archived'"
+
+#-------------------------------------------------------------------------------
+# Monorepo / Packages
+#-------------------------------------------------------------------------------
+
+# Declare packages for monorepo projects.
+# Trellis auto-detects workspaces during `trellis init`, but you can also
+# configure them manually here.
+#
+# packages:
+#   frontend:
+#     path: packages/frontend
+#   backend:
+#     path: packages/backend
+#   docs:
+#     path: docs-site
+#     type: submodule
+#   # For polyrepo / meta-repo layouts (independent .git in each subdir),
+#   # mark the package with `git: true`. The runtime treats it as an
+#   # independent repository for things like git-context display.
+#   webapp:
+#     path: ./webapp
+#     git: true
+
+# Default package used when --package is not specified.
+# default_package: frontend
+
+#-------------------------------------------------------------------------------
+# Codex (dispatch behavior)
+#-------------------------------------------------------------------------------
+# Codex-only knob; other platforms ignore it. Default ("inline") makes the
+# main Codex agent edit code directly because Codex sub-agents run with
+# `fork_turns="none"` isolation and can't inherit the parent session's
+# task context. Set to "sub-agent" to opt into the legacy dispatch model
+# (main agent spawns trellis-implement / trellis-check / trellis-research
+# sub-agents).
+#
+# codex:
+#   dispatch_mode: inline  # or "sub-agent" to dispatch trellis-* sub-agents

.trellis/scripts/__init__.py

@@ -0,0 +1,5 @@
+"""
+Trellis Python Scripts
+
+This module provides Python implementations of Trellis workflow scripts.
+"""

.trellis/scripts/add_session.py

@@ -0,0 +1,547 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Add a new session to journal file and update index.md.
+
+Usage:
+    python add_session.py --title "Title" --commit "hash" --summary "Summary" [--package cli]
+    python add_session.py --title "Title" --branch "feat/my-branch"
+
+    # Pipe detailed content via stdin (use --stdin to opt in):
+    cat << 'EOF' | python add_session.py --stdin --title "Title" --summary "Summary"
+    <session content here>
+    EOF
+
+Branch resolution order:
+    1. --branch CLI arg (explicit)
+    2. task.json branch field (from active task)
+    3. git branch --show-current (auto-detect)
+    4. None (omitted gracefully)
+"""
+
+from __future__ import annotations
+
+import argparse
+import re
+import sys
+from datetime import datetime
+from pathlib import Path
+
+from common.paths import (
+    FILE_JOURNAL_PREFIX,
+    get_repo_root,
+    get_current_task,
+    get_developer,
+    get_workspace_dir,
+)
+from common.developer import ensure_developer
+from common.git import run_git
+from common.safe_commit import (
+    print_gitignore_warning,
+    safe_git_add,
+    safe_trellis_paths_to_add,
+)
+from common.tasks import load_task
+from common.config import (
+    get_packages,
+    get_session_auto_commit,
+    get_session_commit_message,
+    get_max_journal_lines,
+    is_monorepo,
+    resolve_package,
+    validate_package,
+)
+
+
+# =============================================================================
+# Helper Functions
+# =============================================================================
+
+def get_latest_journal_info(dev_dir: Path) -> tuple[Path | None, int, int]:
+    """Get latest journal file info.
+
+    Returns:
+        Tuple of (file_path, file_number, line_count).
+    """
+    latest_file: Path | None = None
+    latest_num = -1
+
+    for f in dev_dir.glob(f"{FILE_JOURNAL_PREFIX}*.md"):
+        if not f.is_file():
+            continue
+
+        match = re.search(r"(\d+)$", f.stem)
+        if match:
+            num = int(match.group(1))
+            if num > latest_num:
+                latest_num = num
+                latest_file = f
+
+    if latest_file:
+        lines = len(latest_file.read_text(encoding="utf-8").splitlines())
+        return latest_file, latest_num, lines
+
+    return None, 0, 0
+
+
+def get_current_session(index_file: Path) -> int:
+    """Get current session number from index.md."""
+    if not index_file.is_file():
+        return 0
+
+    content = index_file.read_text(encoding="utf-8")
+    for line in content.splitlines():
+        if "Total Sessions" in line:
+            match = re.search(r":\s*(\d+)", line)
+            if match:
+                return int(match.group(1))
+    return 0
+
+
+def _extract_journal_num(filename: str) -> int:
+    """Extract journal number from filename for sorting."""
+    match = re.search(r"(\d+)", filename)
+    return int(match.group(1)) if match else 0
+
+
+def count_journal_files(dev_dir: Path, active_num: int) -> str:
+    """Count journal files and return table rows."""
+    active_file = f"{FILE_JOURNAL_PREFIX}{active_num}.md"
+    result_lines = []
+
+    files = sorted(
+        [f for f in dev_dir.glob(f"{FILE_JOURNAL_PREFIX}*.md") if f.is_file()],
+        key=lambda f: _extract_journal_num(f.stem),
+        reverse=True
+    )
+
+    for f in files:
+        filename = f.name
+        lines = len(f.read_text(encoding="utf-8").splitlines())
+        status = "Active" if filename == active_file else "Archived"
+        result_lines.append(f"| `{filename}` | ~{lines} | {status} |")
+
+    return "\n".join(result_lines)
+
+
+def create_new_journal_file(
+    dev_dir: Path, num: int, developer: str, today: str, max_lines: int = 2000,
+) -> Path:
+    """Create a new journal file."""
+    prev_num = num - 1
+    new_file = dev_dir / f"{FILE_JOURNAL_PREFIX}{num}.md"
+
+    content = f"""# Journal - {developer} (Part {num})
+
+> Continuation from `{FILE_JOURNAL_PREFIX}{prev_num}.md` (archived at ~{max_lines} lines)
+> Started: {today}
+
+---
+
+"""
+    new_file.write_text(content, encoding="utf-8")
+    return new_file
+
+
+def generate_session_content(
+    session_num: int,
+    title: str,
+    commit: str,
+    summary: str,
+    extra_content: str,
+    today: str,
+    package: str | None = None,
+    branch: str | None = None,
+) -> str:
+    """Generate session content."""
+    if commit and commit != "-":
+        commit_table = """| Hash | Message |
+|------|---------|"""
+        for c in commit.split(","):
+            c = c.strip()
+            commit_table += f"\n| `{c}` | (see git log) |"
+    else:
+        commit_table = "(No commits - planning session)"
+
+    package_line = f"\n**Package**: {package}" if package else ""
+    branch_line = f"\n**Branch**: `{branch}`" if branch else ""
+
+    return f"""
+
+## Session {session_num}: {title}
+
+**Date**: {today}
+**Task**: {title}{package_line}{branch_line}
+
+### Summary
+
+{summary}
+
+### Main Changes
+
+{extra_content}
+
+### Git Commits
+
+{commit_table}
+
+### Testing
+
+- [OK] (Add test results)
+
+### Status
+
+[OK] **Completed**
+
+### Next Steps
+
+- None - task complete
+"""
+
+
+def update_index(
+    index_file: Path,
+    dev_dir: Path,
+    title: str,
+    commit: str,
+    new_session: int,
+    active_file: str,
+    today: str,
+    branch: str | None = None,
+) -> bool:
+    """Update index.md with new session info."""
+    # Format commit for display
+    commit_display = "-"
+    if commit and commit != "-":
+        commit_display = re.sub(r"([a-f0-9]{7,})", r"`\1`", commit.replace(",", ", "))
+
+    # Get file number from active_file name
+    match = re.search(r"(\d+)", active_file)
+    active_num = int(match.group(1)) if match else 0
+    files_table = count_journal_files(dev_dir, active_num)
+
+    print(f"Updating index.md for session {new_session}...")
+    print(f"  Title: {title}")
+    print(f"  Commit: {commit_display}")
+    print(f"  Active File: {active_file}")
+    print()
+
+    content = index_file.read_text(encoding="utf-8")
+
+    if "@@@auto:current-status" not in content:
+        print("Error: Markers not found in index.md. Please ensure markers exist.", file=sys.stderr)
+        return False
+
+    # Process sections
+    lines = content.splitlines()
+    new_lines = []
+
+    in_current_status = False
+    in_active_documents = False
+    in_session_history = False
+    header_written = False
+
+    for line in lines:
+        if "@@@auto:current-status" in line:
+            new_lines.append(line)
+            in_current_status = True
+            new_lines.append(f"- **Active File**: `{active_file}`")
+            new_lines.append(f"- **Total Sessions**: {new_session}")
+            new_lines.append(f"- **Last Active**: {today}")
+            continue
+
+        if "@@@/auto:current-status" in line:
+            in_current_status = False
+            new_lines.append(line)
+            continue
+
+        if "@@@auto:active-documents" in line:
+            new_lines.append(line)
+            in_active_documents = True
+            new_lines.append("| File | Lines | Status |")
+            new_lines.append("|------|-------|--------|")
+            new_lines.append(files_table)
+            continue
+
+        if "@@@/auto:active-documents" in line:
+            in_active_documents = False
+            new_lines.append(line)
+            continue
+
+        if "@@@auto:session-history" in line:
+            new_lines.append(line)
+            in_session_history = True
+            header_written = False
+            continue
+
+        if "@@@/auto:session-history" in line:
+            in_session_history = False
+            new_lines.append(line)
+            continue
+
+        if in_current_status:
+            continue
+
+        if in_active_documents:
+            continue
+
+        if in_session_history:
+            # Migrate old 4/6-column headers to 5-column Branch-only history.
+            if re.match(
+                r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*Branch\s*\|\s*Base Branch\s*\|\s*$",
+                line,
+            ):
+                new_lines.append("| # | Date | Title | Commits | Branch |")
+                continue
+            if re.match(r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*Branch\s*\|\s*$", line):
+                new_lines.append("| # | Date | Title | Commits | Branch |")
+                continue
+            if re.match(r"^\|\s*#\s*\|\s*Date\s*\|\s*Title\s*\|\s*Commits\s*\|\s*$", line):
+                new_lines.append("| # | Date | Title | Commits | Branch |")
+                continue
+            if re.match(r"^\|[-| ]+\|\s*$", line) and not header_written:
+                new_lines.append("|---|------|-------|---------|--------|")
+                new_lines.append(f"| {new_session} | {today} | {title} | {commit_display} | `{branch or '-'}` |")
+                header_written = True
+                continue
+            new_lines.append(line)
+            continue
+
+        new_lines.append(line)
+
+    index_file.write_text("\n".join(new_lines), encoding="utf-8")
+    print("[OK] Updated index.md successfully!")
+    return True
+
+
+# =============================================================================
+# Main Function
+# =============================================================================
+
+def _auto_commit_workspace(repo_root: Path) -> None:
+    """Stage Trellis-owned workspace + task paths and commit.
+
+    Path scope is restricted to specific products (journal files, index.md,
+    active task dirs, the archive subtree). We never `git add` the whole
+    `.trellis/` tree, and if `.gitignore` blocks the specific paths we
+    warn + skip — never retry with ``-f``.
+
+    Honors ``session_auto_commit`` in ``.trellis/config.yaml``: when set to
+    ``false``, this function returns immediately without touching git
+    (journal/index files are still written to disk by the caller).
+    """
+    if not get_session_auto_commit(repo_root):
+        print(
+            "[OK] session_auto_commit: false — skipping git stage/commit.",
+            file=sys.stderr,
+        )
+        return
+
+    commit_msg = get_session_commit_message(repo_root)
+    paths = safe_trellis_paths_to_add(repo_root)
+    if not paths:
+        print("[OK] No workspace changes to commit.", file=sys.stderr)
+        return
+
+    success, _, err = safe_git_add(paths, repo_root)
+    if not success:
+        if err and "ignored by" in err.lower():
+            print_gitignore_warning(paths)
+        else:
+            print(
+                f"[WARN] git add failed: {err.strip() if err else 'unknown error'}",
+                file=sys.stderr,
+            )
+        return
+
+    # Check if there are staged changes for the paths we just staged.
+    rc, _, _ = run_git(
+        ["diff", "--cached", "--quiet", "--", *paths], cwd=repo_root
+    )
+    if rc == 0:
+        print("[OK] No workspace changes to commit.", file=sys.stderr)
+        return
+
+    rc, _, commit_err = run_git(["commit", "-m", commit_msg], cwd=repo_root)
+    if rc == 0:
+        print(f"[OK] Auto-committed: {commit_msg}", file=sys.stderr)
+    else:
+        print(
+            f"[WARN] Auto-commit failed: {commit_err.strip()}",
+            file=sys.stderr,
+        )
+
+
+def add_session(
+    title: str,
+    commit: str = "-",
+    summary: str = "(Add summary)",
+    extra_content: str = "(Add details)",
+    auto_commit: bool = True,
+    package: str | None = None,
+    branch: str | None = None,
+) -> int:
+    """Add a new session."""
+    repo_root = get_repo_root()
+    ensure_developer(repo_root)
+
+    developer = get_developer(repo_root)
+    if not developer:
+        print("Error: Developer not initialized", file=sys.stderr)
+        return 1
+
+    dev_dir = get_workspace_dir(repo_root)
+    if not dev_dir:
+        print("Error: Workspace directory not found", file=sys.stderr)
+        return 1
+
+    max_lines = get_max_journal_lines(repo_root)
+
+    index_file = dev_dir / "index.md"
+    today = datetime.now().strftime("%Y-%m-%d")
+
+    journal_file, current_num, current_lines = get_latest_journal_info(dev_dir)
+    current_session = get_current_session(index_file)
+    new_session = current_session + 1
+
+    session_content = generate_session_content(
+        new_session, title, commit, summary, extra_content, today, package,
+        branch,
+    )
+    content_lines = len(session_content.splitlines())
+
+    print("========================================", file=sys.stderr)
+    print("ADD SESSION", file=sys.stderr)
+    print("========================================", file=sys.stderr)
+    print("", file=sys.stderr)
+    print(f"Session: {new_session}", file=sys.stderr)
+    print(f"Title: {title}", file=sys.stderr)
+    print(f"Commit: {commit}", file=sys.stderr)
+    print("", file=sys.stderr)
+    print(f"Current journal file: {FILE_JOURNAL_PREFIX}{current_num}.md", file=sys.stderr)
+    print(f"Current lines: {current_lines}", file=sys.stderr)
+    print(f"New content lines: {content_lines}", file=sys.stderr)
+    print(f"Total after append: {current_lines + content_lines}", file=sys.stderr)
+    print("", file=sys.stderr)
+
+    target_file = journal_file
+    target_num = current_num
+
+    if current_lines + content_lines > max_lines:
+        target_num = current_num + 1
+        print(f"[!] Exceeds {max_lines} lines, creating {FILE_JOURNAL_PREFIX}{target_num}.md", file=sys.stderr)
+        target_file = create_new_journal_file(dev_dir, target_num, developer, today, max_lines)
+        print(f"Created: {target_file}", file=sys.stderr)
+
+    # Append session content
+    if target_file:
+        with target_file.open("a", encoding="utf-8") as f:
+            f.write(session_content)
+        print(f"[OK] Appended session to {target_file.name}", file=sys.stderr)
+
+    print("", file=sys.stderr)
+
+    # Update index.md
+    active_file = f"{FILE_JOURNAL_PREFIX}{target_num}.md"
+    if not update_index(
+        index_file,
+        dev_dir,
+        title,
+        commit,
+        new_session,
+        active_file,
+        today,
+        branch,
+    ):
+        return 1
+
+    print("", file=sys.stderr)
+    print("========================================", file=sys.stderr)
+    print(f"[OK] Session {new_session} added successfully!", file=sys.stderr)
+    print("========================================", file=sys.stderr)
+    print("", file=sys.stderr)
+    print("Files updated:", file=sys.stderr)
+    print(f"  - {target_file.name if target_file else 'journal'}", file=sys.stderr)
+    print("  - index.md", file=sys.stderr)
+
+    # Auto-commit workspace changes
+    if auto_commit:
+        print("", file=sys.stderr)
+        _auto_commit_workspace(repo_root)
+
+    return 0
+
+
+# =============================================================================
+# Main Entry
+# =============================================================================
+
+def main() -> int:
+    """CLI entry point."""
+    parser = argparse.ArgumentParser(
+        description="Add a new session to journal file and update index.md"
+    )
+    parser.add_argument("--title", required=True, help="Session title")
+    parser.add_argument("--commit", default="-", help="Comma-separated commit hashes")
+    parser.add_argument("--summary", default="(Add summary)", help="Brief summary")
+    parser.add_argument("--content-file", help="Path to file with detailed content")
+    parser.add_argument("--package", help="Package name tag (e.g., cli, docs-site)")
+    parser.add_argument("--branch", help="Branch name (auto-detected if omitted)")
+    parser.add_argument("--no-commit", action="store_true",
+                        help="Skip auto-commit of workspace changes")
+    parser.add_argument("--stdin", action="store_true",
+                        help="Read extra content from stdin (explicit opt-in)")
+
+    args = parser.parse_args()
+
+    extra_content = "(Add details)"
+    if args.content_file:
+        content_path = Path(args.content_file)
+        if content_path.is_file():
+            extra_content = content_path.read_text(encoding="utf-8")
+    elif args.stdin:
+        extra_content = sys.stdin.read()
+
+    # Load active task once — shared by package and branch resolution
+    repo_root = get_repo_root()
+    current = get_current_task(repo_root)
+    task_data = load_task(repo_root / current) if current else None
+
+    package = args.package
+    if package:
+        # CLI source: fail-fast in monorepo, ignore in single-repo
+        if not is_monorepo(repo_root):
+            print("Warning: --package ignored in single-repo project", file=sys.stderr)
+            package = None
+        elif not validate_package(package, repo_root):
+            packages = get_packages(repo_root)
+            available = ", ".join(sorted(packages.keys())) if packages else "(none)"
+            print(f"Error: unknown package '{package}'. Available: {available}", file=sys.stderr)
+            return 1
+    else:
+        # Inferred: active task's task.json.package → default_package → None
+        task_package = task_data.package if task_data else None
+        package = resolve_package(task_package, repo_root)
+
+    # Resolve branch: CLI → task.json → git auto-detect → None
+    branch = args.branch
+
+    if not branch:
+        if task_data and task_data.raw.get("branch"):
+            branch = task_data.raw["branch"]
+        else:
+            _, branch_out, _ = run_git(["branch", "--show-current"], cwd=repo_root)
+            detected = branch_out.strip()
+            if detected:
+                branch = detected
+
+    return add_session(
+        args.title, args.commit, args.summary, extra_content,
+        auto_commit=not args.no_commit,
+        package=package,
+        branch=branch,
+    )
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.trellis/scripts/common/__init__.py

@@ -0,0 +1,92 @@
+"""
+Common utilities for Trellis workflow scripts.
+
+This module provides shared functionality used by other Trellis scripts.
+"""
+
+import io
+import sys
+
+# =============================================================================
+# Windows Encoding Fix (MUST be at top, before any other output)
+# =============================================================================
+# On Windows, stdout defaults to the system code page (often GBK/CP936).
+# This causes UnicodeEncodeError when printing non-ASCII characters.
+#
+# Any script that imports from common will automatically get this fix.
+# =============================================================================
+
+
+def _configure_stream(stream: object) -> object:
+    """Configure a stream for UTF-8 encoding on Windows."""
+    # Try reconfigure() first (Python 3.7+, more reliable)
+    if hasattr(stream, "reconfigure"):
+        stream.reconfigure(encoding="utf-8", errors="replace")  # type: ignore[union-attr]
+        return stream
+    # Fallback: detach and rewrap with TextIOWrapper
+    elif hasattr(stream, "detach"):
+        return io.TextIOWrapper(
+            stream.detach(),  # type: ignore[union-attr]
+            encoding="utf-8",
+            errors="replace",
+        )
+    return stream
+
+
+if sys.platform == "win32":
+    sys.stdout = _configure_stream(sys.stdout)  # type: ignore[assignment]
+    sys.stderr = _configure_stream(sys.stderr)  # type: ignore[assignment]
+    sys.stdin = _configure_stream(sys.stdin)  # type: ignore[assignment]
+
+
+def configure_encoding() -> None:
+    """
+    Configure stdout/stderr/stdin for UTF-8 encoding on Windows.
+
+    This is automatically called when importing from common,
+    but can be called manually for scripts that don't import common.
+
+    Safe to call multiple times.
+    """
+    global sys
+    if sys.platform == "win32":
+        sys.stdout = _configure_stream(sys.stdout)  # type: ignore[assignment]
+        sys.stderr = _configure_stream(sys.stderr)  # type: ignore[assignment]
+        sys.stdin = _configure_stream(sys.stdin)  # type: ignore[assignment]
+
+
+from .paths import (
+    DIR_WORKFLOW,
+    DIR_WORKSPACE,
+    DIR_TASKS,
+    DIR_ARCHIVE,
+    DIR_SPEC,
+    DIR_SCRIPTS,
+    FILE_DEVELOPER,
+    FILE_CURRENT_TASK,
+    FILE_TASK_JSON,
+    FILE_JOURNAL_PREFIX,
+    get_repo_root,
+    get_developer,
+    check_developer,
+    get_tasks_dir,
+    get_workspace_dir,
+    get_active_journal_file,
+    count_lines,
+    get_current_task,
+    get_current_task_abs,
+    normalize_task_ref,
+    resolve_task_ref,
+    set_current_task,
+    clear_current_task,
+    has_current_task,
+    generate_task_date_prefix,
+)
+
+from .active_task import (
+    ActiveTask,
+    clear_active_task,
+    resolve_active_task,
+    resolve_context_key,
+    set_active_task,
+)

.trellis/scripts/common/active_task.py

@@ -0,0 +1,626 @@
+#!/usr/bin/env python3
+"""Session-scoped active task resolution.
+
+The user-facing concept is a single "active task". Trellis stores that pointer
+per AI session/window under `.trellis/.runtime/sessions/`; without a stable
+session key there is no active task.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import json
+import os
+import re
+import sys
+import time
+from dataclasses import dataclass
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any
+
+DIR_WORKFLOW = ".trellis"
+DIR_TASKS = "tasks"
+DIR_RUNTIME = ".runtime"
+DIR_SESSIONS = "sessions"
+DIR_CURSOR_SHELL = "cursor-shell"
+CURSOR_SHELL_TICKET_TTL_SECONDS = 30
+TASK_SESSION_COMMANDS = {"start", "current", "finish"}
+
+_SESSION_KEYS = ("session_id", "sessionId", "sessionID")
+_CONVERSATION_KEYS = ("conversation_id", "conversationId", "conversationID")
+_TRANSCRIPT_KEYS = ("transcript_path", "transcriptPath", "transcript")
+_NESTED_KEYS = ("input", "properties", "event", "hook_input", "hookInput")
+_KNOWN_PLATFORMS = {
+    "claude",
+    "codex",
+    "cursor",
+    "opencode",
+    "gemini",
+    "droid",
+    "qoder",
+    "codebuddy",
+    "kiro",
+    "copilot",
+    "pi",
+}
+
+_ENV_SESSION_KEYS: tuple[tuple[str, tuple[str, ...]], ...] = (
+    ("claude", ("CLAUDE_SESSION_ID", "CLAUDE_CODE_SESSION_ID")),
+    ("codex", ("CODEX_SESSION_ID", "CODEX_THREAD_ID")),
+    ("cursor", ("CURSOR_SESSION_ID",)),
+    ("opencode", ("OPENCODE_SESSION_ID", "OPENCODE_SESSIONID", "OPENCODE_RUN_ID")),
+    ("gemini", ("GEMINI_SESSION_ID",)),
+    ("droid", ("FACTORY_SESSION_ID", "DROID_SESSION_ID")),
+    ("qoder", ("QODER_SESSION_ID",)),
+    ("codebuddy", ("CODEBUDDY_SESSION_ID",)),
+    ("kiro", ("KIRO_SESSION_ID",)),
+    ("copilot", ("COPILOT_SESSION_ID", "COPILOT_SESSIONID")),
+    ("pi", ("PI_SESSION_ID", "PI_SESSIONID")),
+)
+_ENV_CONVERSATION_KEYS: tuple[tuple[str, tuple[str, ...]], ...] = (
+    ("cursor", ("CURSOR_CONVERSATION_ID", "CURSOR_CONVERSATIONID")),
+)
+_ENV_TRANSCRIPT_KEYS: tuple[tuple[str, tuple[str, ...]], ...] = (
+    ("claude", ("CLAUDE_TRANSCRIPT_PATH",)),
+    ("codex", ("CODEX_TRANSCRIPT_PATH",)),
+    ("cursor", ("CURSOR_TRANSCRIPT_PATH",)),
+    ("gemini", ("GEMINI_TRANSCRIPT_PATH",)),
+    ("droid", ("FACTORY_TRANSCRIPT_PATH", "DROID_TRANSCRIPT_PATH")),
+    ("qoder", ("QODER_TRANSCRIPT_PATH",)),
+    ("codebuddy", ("CODEBUDDY_TRANSCRIPT_PATH",)),
+)
+_ENV_PLATFORM_ALIASES = {
+    "claude-code": "claude",
+    "factory": "droid",
+    "factory-ai": "droid",
+    "github-copilot": "copilot",
+}
+
+
+@dataclass(frozen=True)
+class ActiveTask:
+    """Resolved active task state."""
+
+    task_path: str | None
+    source_type: str
+    context_key: str | None = None
+    stale: bool = False
+
+    @property
+    def source(self) -> str:
+        """Human-readable source label."""
+        if self.source_type == "session" and self.context_key:
+            return f"session:{self.context_key}"
+        if self.source_type == "session-fallback" and self.context_key:
+            return f"session-fallback:{self.context_key}"
+        return self.source_type
+
+
+def normalize_task_ref(task_ref: str) -> str:
+    """Normalize a task ref for stable storage and comparison."""
+    normalized = task_ref.strip()
+    if not normalized:
+        return ""
+
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return str(path_obj)
+
+    normalized = normalized.replace("\\", "/")
+    while normalized.startswith("./"):
+        normalized = normalized[2:]
+
+    if normalized.startswith(f"{DIR_TASKS}/"):
+        return f"{DIR_WORKFLOW}/{normalized}"
+
+    return normalized
+
+
+def resolve_task_ref(task_ref: str, repo_root: Path) -> Path | None:
+    """Resolve a task ref to an absolute task directory."""
+    normalized = normalize_task_ref(task_ref)
+    if not normalized:
+        return None
+
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return path_obj
+
+    if normalized.startswith(f"{DIR_WORKFLOW}/"):
+        return repo_root / path_obj
+
+    return repo_root / DIR_WORKFLOW / DIR_TASKS / path_obj
+
+
+def _runtime_sessions_dir(repo_root: Path) -> Path:
+    return repo_root / DIR_WORKFLOW / DIR_RUNTIME / DIR_SESSIONS
+
+
+def _sanitize_key(raw: str) -> str:
+    safe = re.sub(r"[^A-Za-z0-9._-]+", "_", raw.strip())
+    safe = safe.strip("._-")
+    return safe[:160] if safe else ""
+
+
+def _hash_value(raw: str) -> str:
+    return hashlib.sha256(raw.encode("utf-8")).hexdigest()[:24]
+
+
+def _as_dict(value: Any) -> dict[str, Any] | None:
+    return value if isinstance(value, dict) else None
+
+
+def _string_value(value: Any) -> str | None:
+    if isinstance(value, str):
+        stripped = value.strip()
+        return stripped or None
+    return None
+
+
+def _lookup_string(data: dict[str, Any], keys: tuple[str, ...]) -> str | None:
+    for key in keys:
+        value = _string_value(data.get(key))
+        if value:
+            return value
+
+    for nested_key in _NESTED_KEYS:
+        nested = _as_dict(data.get(nested_key))
+        if not nested:
+            continue
+        value = _lookup_string(nested, keys)
+        if value:
+            return value
+
+    return None
+
+
+def _detect_platform(platform_input: dict[str, Any] | None, platform: str | None) -> str:
+    if platform:
+        return _sanitize_key(platform) or "session"
+    if platform_input:
+        for key in ("_trellis_platform", "trellis_platform", "platform", "source"):
+            value = _string_value(platform_input.get(key))
+            if value:
+                return _sanitize_key(value) or "session"
+        if _string_value(platform_input.get("cursor_version")):
+            return "cursor"
+    return "session"
+
+
+def _context_key(platform_name: str, kind: str, value: str) -> str:
+    if kind == "transcript":
+        return f"{platform_name}_transcript_{_hash_value(value)}"
+    safe_value = _sanitize_key(value)
+    if safe_value:
+        return f"{platform_name}_{safe_value}"
+    return f"{platform_name}_{_hash_value(value)}"
+
+
+def _iter_env_keys(
+    env_keys: tuple[tuple[str, tuple[str, ...]], ...],
+    platform_name: str | None,
+) -> tuple[tuple[str, tuple[str, ...]], ...]:
+    if not platform_name:
+        return env_keys
+    matched = tuple((name, keys) for name, keys in env_keys if name == platform_name)
+    return matched
+
+
+def _env_platform_name(platform_name: str | None) -> str | None:
+    if not platform_name or platform_name == "session":
+        return None
+    return _ENV_PLATFORM_ALIASES.get(platform_name, platform_name)
+
+
+def _lookup_env_context_key(platform_name: str | None) -> str | None:
+    """Resolve a context key from platform-provided environment variables.
+
+    Hooks pass `TRELLIS_CONTEXT_ID` to subprocesses they launch, but an AI-run
+    shell command can only see session identity if the host platform exports it
+    in the command environment. These names are best-effort adapters; if none
+    are present, there is no session-scoped active task.
+    """
+    env_platform_name = _env_platform_name(platform_name)
+
+    for name, keys in _iter_env_keys(_ENV_SESSION_KEYS, env_platform_name):
+        for key in keys:
+            value = _string_value(os.environ.get(key))
+            if value:
+                return _context_key(name, "session", value)
+
+    for name, keys in _iter_env_keys(_ENV_CONVERSATION_KEYS, env_platform_name):
+        for key in keys:
+            value = _string_value(os.environ.get(key))
+            if value:
+                return _context_key(name, "conversation", value)
+
+    for name, keys in _iter_env_keys(_ENV_TRANSCRIPT_KEYS, env_platform_name):
+        for key in keys:
+            value = _string_value(os.environ.get(key))
+            if value:
+                return _context_key(name, "transcript", value)
+
+    return None
+
+
+def _find_repo_root_from_cwd() -> Path | None:
+    current = Path.cwd().resolve()
+    while True:
+        if (current / DIR_WORKFLOW).is_dir():
+            return current
+        if current == current.parent:
+            return None
+        current = current.parent
+
+
+def _cursor_shell_ticket_dir(repo_root: Path) -> Path:
+    return repo_root / DIR_WORKFLOW / DIR_RUNTIME / DIR_CURSOR_SHELL
+
+
+def _remove_file(path: Path) -> bool:
+    try:
+        path.unlink()
+        return True
+    except OSError:
+        return False
+
+
+def _task_refs_match(left: str | None, right: str | None, repo_root: Path) -> bool:
+    if not left or not right:
+        return False
+    left_path = resolve_task_ref(left, repo_root)
+    right_path = resolve_task_ref(right, repo_root)
+    if left_path is not None and right_path is not None:
+        return left_path == right_path
+    return normalize_task_ref(left) == normalize_task_ref(right)
+
+
+def _pending_ticket_matches_args(ticket: dict[str, Any], repo_root: Path) -> bool:
+    if Path(sys.argv[0]).name != "task.py":
+        return False
+    args = tuple(sys.argv[1:])
+    if not args:
+        return False
+
+    command_name = args[0]
+    if command_name not in TASK_SESSION_COMMANDS:
+        return False
+
+    subcommands = ticket.get("subcommands")
+    if not isinstance(subcommands, list):
+        return False
+
+    for subcommand in subcommands:
+        if not isinstance(subcommand, dict):
+            continue
+        if _string_value(subcommand.get("name")) != command_name:
+            continue
+        if command_name != "start":
+            return True
+        task_ref = args[1] if len(args) > 1 else None
+        if _task_refs_match(_string_value(subcommand.get("task_ref")), task_ref, repo_root):
+            return True
+
+    return False
+
+
+def _ticket_is_fresh(ticket: dict[str, Any], ticket_path: Path, now: float) -> bool:
+    expires_at = ticket.get("expires_at_epoch")
+    if isinstance(expires_at, (int, float)) and expires_at < now:
+        _remove_file(ticket_path)
+        return False
+
+    created_at = ticket.get("created_at_epoch")
+    if isinstance(created_at, (int, float)):
+        if now - created_at <= CURSOR_SHELL_TICKET_TTL_SECONDS:
+            return True
+        _remove_file(ticket_path)
+        return False
+    return True
+
+
+def _ticket_cwd_matches_repo(ticket: dict[str, Any], repo_root: Path) -> bool:
+    cwd = _string_value(ticket.get("cwd"))
+    if not cwd:
+        return True
+    try:
+        Path(cwd).resolve().relative_to(repo_root)
+    except ValueError:
+        return False
+    return True
+
+
+def _matching_cursor_ticket_context_key(
+    ticket_path: Path,
+    repo_root: Path,
+    now: float,
+) -> str | None:
+    ticket = _read_json(ticket_path)
+    if ticket is None or ticket.get("platform") != "cursor":
+        return None
+    if not _ticket_is_fresh(ticket, ticket_path, now):
+        return None
+    if not _ticket_cwd_matches_repo(ticket, repo_root):
+        return None
+    if not _pending_ticket_matches_args(ticket, repo_root):
+        return None
+    return _string_value(ticket.get("context_key"))
+
+
+def _lookup_cursor_shell_ticket_context_key() -> str | None:
+    """Resolve Cursor conversation identity from a short-lived shell ticket.
+
+    Cursor exposes `conversation_id` to `beforeShellExecution`, but does not
+    export it into the shell command environment. The Cursor hook writes a
+    short-lived ticket just before `task.py` runs. We accept a ticket only when
+    the current `task.py` subcommand matches and exactly one fresh context key
+    matches, which avoids cross-window pointer contamination.
+    """
+    repo_root = _find_repo_root_from_cwd()
+    if repo_root is None:
+        return None
+
+    ticket_dir = _cursor_shell_ticket_dir(repo_root)
+    if not ticket_dir.is_dir():
+        return None
+
+    now = time.time()
+    candidates: set[str] = set()
+    for ticket_path in ticket_dir.glob("*.json"):
+        context_key = _matching_cursor_ticket_context_key(ticket_path, repo_root, now)
+        if context_key:
+            candidates.add(context_key)
+
+    if len(candidates) == 1:
+        return next(iter(candidates))
+    return None
+
+
+def resolve_context_key(
+    platform_input: dict[str, Any] | None = None,
+    platform: str | None = None,
+) -> str | None:
+    """Resolve a stable session/window context key, if one is available.
+
+    `TRELLIS_CONTEXT_ID` is an explicit context-key override used by CLI
+    scripts and subprocesses. It does not store the task itself.
+    """
+    override = _string_value(os.environ.get("TRELLIS_CONTEXT_ID"))
+    if override:
+        return _sanitize_key(override) or _hash_value(override)
+
+    data = _as_dict(platform_input)
+    platform_name = _detect_platform(data, platform) if data or platform else None
+
+    if data:
+        session_id = _lookup_string(data, _SESSION_KEYS)
+        if session_id:
+            return _context_key(platform_name or "session", "session", session_id)
+
+        conversation_id = _lookup_string(data, _CONVERSATION_KEYS)
+        if conversation_id:
+            return _context_key(platform_name or "session", "conversation", conversation_id)
+
+        transcript_path = _lookup_string(data, _TRANSCRIPT_KEYS)
+        if transcript_path:
+            return _context_key(platform_name or "session", "transcript", transcript_path)
+
+    env_context_key = _lookup_env_context_key(platform_name)
+    if env_context_key:
+        return env_context_key
+
+    if platform_name in (None, "session", "cursor"):
+        return _lookup_cursor_shell_ticket_context_key()
+    return None
+
+
+def _read_json(path: Path) -> dict[str, Any] | None:
+    try:
+        data = json.loads(path.read_text(encoding="utf-8"))
+    except (FileNotFoundError, json.JSONDecodeError, OSError):
+        return None
+    return data if isinstance(data, dict) else None
+
+
+def _write_json(path: Path, data: dict[str, Any]) -> bool:
+    try:
+        path.parent.mkdir(parents=True, exist_ok=True)
+        path.write_text(
+            json.dumps(data, indent=2, ensure_ascii=False) + "\n",
+            encoding="utf-8",
+        )
+        return True
+    except OSError:
+        return False
+
+
+def _canonical_task_ref(task_path: str, repo_root: Path) -> str | None:
+    normalized = normalize_task_ref(task_path)
+    if not normalized:
+        return None
+    full_path = resolve_task_ref(normalized, repo_root)
+    if full_path is None or not full_path.is_dir():
+        return None
+    try:
+        return full_path.relative_to(repo_root).as_posix()
+    except ValueError:
+        return str(full_path)
+
+
+def _active_from_ref(
+    task_ref: str | None,
+    repo_root: Path,
+    source_type: str,
+    context_key: str | None = None,
+) -> ActiveTask | None:
+    if not task_ref:
+        return None
+    resolved = resolve_task_ref(task_ref, repo_root)
+    stale = resolved is None or not resolved.is_dir()
+    return ActiveTask(task_ref, source_type, context_key, stale)
+
+
+def _context_path(repo_root: Path, context_key: str) -> Path:
+    return _runtime_sessions_dir(repo_root) / f"{context_key}.json"
+
+
+def resolve_active_task(
+    repo_root: Path,
+    platform_input: dict[str, Any] | None = None,
+    platform: str | None = None,
+) -> ActiveTask:
+    """Resolve the active task from session runtime state only.
+
+    A stale session task is returned as stale. Missing context identity or a
+    missing/empty session context falls back to single-session inference: if
+    exactly one session file exists in the runtime, return its task with
+    source_type="session-fallback" — covers class-2 platform sub-agents (codex,
+    copilot, gemini, qoder) that don't inherit the parent's session id. ≥2
+    files or 0 files yield ActiveTask(None) — refuses to guess across windows.
+    """
+    context_key = resolve_context_key(platform_input, platform)
+    if context_key:
+        context = _read_json(_context_path(repo_root, context_key)) or {}
+        task_ref = _string_value(context.get("current_task"))
+        active = _active_from_ref(task_ref, repo_root, "session", context_key)
+        if active:
+            return active
+
+    fallback = _resolve_single_session_fallback(repo_root)
+    if fallback is not None:
+        return fallback
+
+    return ActiveTask(None, "none", context_key)
+
+
+def _resolve_single_session_fallback(repo_root: Path) -> ActiveTask | None:
+    """Return the task pointed at by the sole session file, if exactly one exists.
+
+    Used when context-key resolution fails (typical for class-2 platform
+    sub-agents). Returns None if 0 or ≥2 session files are present — refuses
+    to pick across windows so 04-21's multi-session isolation contract holds.
+    """
+    sessions_dir = _runtime_sessions_dir(repo_root)
+    if not sessions_dir.is_dir():
+        return None
+
+    session_files = sorted(sessions_dir.glob("*.json"))
+    if len(session_files) != 1:
+        return None
+
+    session_file = session_files[0]
+    context = _read_json(session_file) or {}
+    task_ref = _string_value(context.get("current_task"))
+    if not task_ref:
+        return None
+
+    fallback_key = session_file.stem
+    return _active_from_ref(task_ref, repo_root, "session-fallback", fallback_key)
+
+
+def _utc_now() -> str:
+    return datetime.now(timezone.utc).replace(microsecond=0).isoformat().replace("+00:00", "Z")
+
+
+def _context_metadata(
+    platform_input: dict[str, Any] | None,
+    platform: str | None,
+    context_key: str | None = None,
+) -> dict[str, Any]:
+    data = _as_dict(platform_input) or {}
+    platform_name = _detect_platform(data, platform)
+    if platform_name == "session" and context_key:
+        prefix = context_key.split("_", 1)[0]
+        if prefix in _KNOWN_PLATFORMS:
+            platform_name = prefix
+    metadata: dict[str, Any] = {
+        "platform": platform_name,
+        "last_seen_at": _utc_now(),
+    }
+    for key in (*_SESSION_KEYS, *_CONVERSATION_KEYS, *_TRANSCRIPT_KEYS):
+        value = _lookup_string(data, (key,))
+        if value:
+            metadata[key] = value
+    return metadata
+
+
+def set_active_task(
+    task_path: str,
+    repo_root: Path,
+    platform_input: dict[str, Any] | None = None,
+    platform: str | None = None,
+) -> ActiveTask | None:
+    """Set the active task in session scope.
+
+    Returns None when no context key is available; callers should surface a
+    user-facing error that explains how to provide session identity.
+    """
+    canonical = _canonical_task_ref(task_path, repo_root)
+    if canonical is None:
+        return None
+
+    context_key = resolve_context_key(platform_input, platform)
+    if not context_key:
+        return None
+
+    context_path = _context_path(repo_root, context_key)
+    context = _read_json(context_path) or {}
+    context.update(_context_metadata(platform_input, platform, context_key))
+    context["current_task"] = canonical
+    context.setdefault("current_run", None)
+    if not _write_json(context_path, context):
+        return None
+    return ActiveTask(canonical, "session", context_key)
+
+
+def clear_active_task(
+    repo_root: Path,
+    platform_input: dict[str, Any] | None = None,
+    platform: str | None = None,
+) -> ActiveTask:
+    """Clear the active task by deleting the current session context file."""
+    context_key = resolve_context_key(platform_input, platform)
+    if not context_key:
+        return ActiveTask(None, "none")
+
+    previous = resolve_active_task(repo_root, platform_input, platform)
+    context_path = _context_path(repo_root, context_key)
+    if context_path.is_file():
+        _remove_file(context_path)
+    return previous
+
+
+def clear_task_from_sessions(task_path: str, repo_root: Path) -> int:
+    """Delete all session runtime files that point at a task."""
+    target = _canonical_task_ref(task_path, repo_root) or normalize_task_ref(task_path)
+    if not target:
+        return 0
+
+    cleared = 0
+    sessions_dir = _runtime_sessions_dir(repo_root)
+    if not sessions_dir.is_dir():
+        return cleared
+
+    for session_path in sessions_dir.glob("*.json"):
+        context = _read_json(session_path) or {}
+        current = _string_value(context.get("current_task"))
+        if not current:
+            continue
+        current_ref = _canonical_task_ref(current, repo_root) or normalize_task_ref(current)
+        if current_ref != target:
+            continue
+        if session_path.is_file() and _remove_file(session_path):
+            cleared += 1
+
+    return cleared
+
+
+def get_current_task_source(
+    repo_root: Path,
+    platform_input: dict[str, Any] | None = None,
+    platform: str | None = None,
+) -> tuple[str, str | None, str | None]:
+    """Return (`source_type`, `context_key`, `task_path`) for compatibility."""
+    active = resolve_active_task(repo_root, platform_input, platform)
+    return active.source_type, active.context_key, active.task_path

.trellis/scripts/common/cli_adapter.py

@@ -0,0 +1,811 @@
+"""
+CLI Adapter for Multi-Platform Support.
+
+Abstracts differences between Claude Code, OpenCode, Cursor, iFlow, Codex, Kilo, Kiro Code, Gemini CLI, Antigravity, Windsurf, Qoder, CodeBuddy, GitHub Copilot, Factory Droid, and Pi Agent interfaces.
+
+Supported platforms:
+- claude: Claude Code (default)
+- opencode: OpenCode
+- cursor: Cursor IDE
+- iflow: iFlow CLI
+- codex: Codex CLI (skills-based)
+- kilo: Kilo CLI
+- kiro: Kiro Code (skills-based)
+- gemini: Gemini CLI
+- antigravity: Antigravity (workflow-based)
+- windsurf: Windsurf (workflow-based)
+- qoder: Qoder
+- codebuddy: CodeBuddy
+- copilot: GitHub Copilot (VS Code)
+- droid: Factory Droid (commands-based)
+- pi: Pi Agent (extension-backed)
+
+Usage:
+    from common.cli_adapter import CLIAdapter
+
+    adapter = CLIAdapter("opencode")
+    cmd = adapter.build_run_command(
+        agent="dispatch",
+        session_id="abc123",
+        prompt="Start the pipeline"
+    )
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import ClassVar, Literal
+
+Platform = Literal[
+    "claude",
+    "opencode",
+    "cursor",
+    "iflow",
+    "codex",
+    "kilo",
+    "kiro",
+    "gemini",
+    "antigravity",
+    "windsurf",
+    "qoder",
+    "codebuddy",
+    "copilot",
+    "droid",
+    "pi",
+]
+
+
+@dataclass
+class CLIAdapter:
+    """Adapter for different AI coding CLI tools."""
+
+    platform: Platform
+
+    # =========================================================================
+    # Agent Name Mapping
+    # =========================================================================
+
+    # OpenCode has built-in agents that cannot be overridden
+    # See: https://github.com/sst/opencode/issues/4271
+    # Note: Class-level constant, not a dataclass field
+    _AGENT_NAME_MAP: ClassVar[dict[Platform, dict[str, str]]] = {
+        "claude": {},  # No mapping needed
+        "opencode": {
+            "plan": "trellis-plan",  # 'plan' is built-in in OpenCode
+        },
+    }
+
+    def get_agent_name(self, agent: str) -> str:
+        """Get platform-specific agent name.
+
+        Args:
+            agent: Original agent name (e.g., 'plan', 'dispatch')
+
+        Returns:
+            Platform-specific agent name (e.g., 'trellis-plan' for OpenCode)
+        """
+        mapping = self._AGENT_NAME_MAP.get(self.platform, {})
+        return mapping.get(agent, agent)
+
+    # =========================================================================
+    # Agent Path
+    # =========================================================================
+
+    @property
+    def config_dir_name(self) -> str:
+        """Get platform-specific config directory name.
+
+        Returns:
+            Directory name ('.claude', '.opencode', '.cursor', '.iflow', '.codex', '.kilocode', '.kiro', '.gemini', '.agent', '.windsurf', '.qoder', '.codebuddy', '.github/copilot', '.factory', or '.pi')
+        """
+        if self.platform == "opencode":
+            return ".opencode"
+        elif self.platform == "cursor":
+            return ".cursor"
+        elif self.platform == "iflow":
+            return ".iflow"
+        elif self.platform == "codex":
+            return ".codex"
+        elif self.platform == "kilo":
+            return ".kilocode"
+        elif self.platform == "kiro":
+            return ".kiro"
+        elif self.platform == "gemini":
+            return ".gemini"
+        elif self.platform == "antigravity":
+            return ".agent"
+        elif self.platform == "windsurf":
+            return ".windsurf"
+        elif self.platform == "qoder":
+            return ".qoder"
+        elif self.platform == "codebuddy":
+            return ".codebuddy"
+        elif self.platform == "copilot":
+            return ".github/copilot"
+        elif self.platform == "droid":
+            return ".factory"
+        elif self.platform == "pi":
+            return ".pi"
+        else:
+            return ".claude"
+
+    def get_config_dir(self, project_root: Path) -> Path:
+        """Get platform-specific config directory.
+
+        Args:
+            project_root: Project root directory
+
+        Returns:
+            Path to config directory (.claude, .opencode, .cursor, .iflow, .codex, .kilocode, .kiro, .gemini, .agent, .windsurf, .qoder, .codebuddy, .github/copilot, .factory, or .pi)
+        """
+        return project_root / self.config_dir_name
+
+    def get_agent_path(self, agent: str, project_root: Path) -> Path:
+        """Get path to agent definition file.
+
+        Args:
+            agent: Agent name (original, before mapping)
+            project_root: Project root directory
+
+        Returns:
+            Path to agent definition file (.md for most platforms, .toml for Codex)
+        """
+        mapped_name = self.get_agent_name(agent)
+        if self.platform == "codex":
+            return self.get_config_dir(project_root) / "agents" / f"{mapped_name}.toml"
+        return self.get_config_dir(project_root) / "agents" / f"{mapped_name}.md"
+
+    def get_commands_path(self, project_root: Path, *parts: str) -> Path:
+        """Get path to commands directory or specific command file.
+
+        Args:
+            project_root: Project root directory
+            *parts: Additional path parts (e.g., 'trellis', 'finish-work.md')
+
+        Returns:
+            Path to commands directory or file
+
+        Note:
+            Cursor uses prefix naming: .cursor/commands/trellis-<name>.md
+            Antigravity uses workflow directory: .agent/workflows/<name>.md
+            Windsurf uses workflow directory: .windsurf/workflows/trellis-<name>.md
+            Copilot uses prompt files: .github/prompts/<name>.prompt.md
+            Pi uses prompt templates: .pi/prompts/trellis-<name>.md
+            Claude/OpenCode use subdirectory: .claude/commands/trellis/<name>.md
+        """
+        if self.platform == "pi":
+            prompts_dir = self.get_config_dir(project_root) / "prompts"
+            if not parts:
+                return prompts_dir
+            if len(parts) >= 2 and parts[0] == "trellis":
+                filename = parts[-1]
+                if filename.endswith(".md"):
+                    filename = filename[:-3]
+                return prompts_dir / f"trellis-{filename}.md"
+            return prompts_dir / Path(*parts)
+
+        if self.platform == "windsurf":
+            workflow_dir = self.get_config_dir(project_root) / "workflows"
+            if not parts:
+                return workflow_dir
+            if len(parts) >= 2 and parts[0] == "trellis":
+                filename = parts[-1]
+                return workflow_dir / f"trellis-{filename}"
+            return workflow_dir / Path(*parts)
+
+        if self.platform in ("antigravity", "kilo"):
+            workflow_dir = self.get_config_dir(project_root) / "workflows"
+            if not parts:
+                return workflow_dir
+            if len(parts) >= 2 and parts[0] == "trellis":
+                filename = parts[-1]
+                return workflow_dir / filename
+            return workflow_dir / Path(*parts)
+
+        if self.platform == "copilot":
+            prompts_dir = project_root / ".github" / "prompts"
+            if not parts:
+                return prompts_dir
+            if len(parts) >= 2 and parts[0] == "trellis":
+                filename = parts[-1]
+                if filename.endswith(".md"):
+                    filename = filename[:-3]
+                return prompts_dir / f"{filename}.prompt.md"
+            return prompts_dir / Path(*parts)
+
+        if not parts:
+            return self.get_config_dir(project_root) / "commands"
+
+        # Cursor uses prefix naming instead of subdirectory
+        if self.platform == "cursor" and len(parts) >= 2 and parts[0] == "trellis":
+            # Convert trellis/<name>.md to trellis-<name>.md
+            filename = parts[-1]
+            return (
+                self.get_config_dir(project_root) / "commands" / f"trellis-{filename}"
+            )
+
+        return self.get_config_dir(project_root) / "commands" / Path(*parts)
+
+    def get_trellis_command_path(self, name: str) -> str:
+        """Get relative path to a trellis command file.
+
+        Args:
+            name: Command name without extension (e.g., 'finish-work', 'check')
+
+        Returns:
+            Relative path string for use in JSONL entries
+
+        Note:
+            Cursor: .cursor/commands/trellis-<name>.md
+            Codex: .agents/skills/trellis-<name>/SKILL.md
+            Kiro: .kiro/skills/trellis-<name>/SKILL.md
+            Gemini: .gemini/commands/trellis/<name>.toml
+            Antigravity: .agent/workflows/<name>.md
+            Windsurf: .windsurf/workflows/trellis-<name>.md
+            Pi: .pi/prompts/trellis-<name>.md
+            Others: .{platform}/commands/trellis/<name>.md
+        """
+        if self.platform == "cursor":
+            return f".cursor/commands/trellis-{name}.md"
+        elif self.platform == "codex":
+            # 0.5.0-beta.0 renamed all skill dirs to add the `trellis-` prefix
+            # (see that release's manifest for the 60+ rename entries).
+            return f".agents/skills/trellis-{name}/SKILL.md"
+        elif self.platform == "kiro":
+            return f".kiro/skills/trellis-{name}/SKILL.md"
+        elif self.platform == "gemini":
+            return f".gemini/commands/trellis/{name}.toml"
+        elif self.platform == "antigravity":
+            return f".agent/workflows/{name}.md"
+        elif self.platform == "windsurf":
+            return f".windsurf/workflows/trellis-{name}.md"
+        elif self.platform == "kilo":
+            return f".kilocode/workflows/{name}.md"
+        elif self.platform == "copilot":
+            return f".github/prompts/{name}.prompt.md"
+        elif self.platform == "droid":
+            return f".factory/commands/trellis/{name}.md"
+        elif self.platform == "pi":
+            return f".pi/prompts/trellis-{name}.md"
+        else:
+            return f"{self.config_dir_name}/commands/trellis/{name}.md"
+
+    # =========================================================================
+    # Environment Variables
+    # =========================================================================
+
+    def get_non_interactive_env(self) -> dict[str, str]:
+        """Get environment variables for non-interactive mode.
+
+        Returns:
+            Dict of environment variables to set
+        """
+        if self.platform == "opencode":
+            return {"OPENCODE_NON_INTERACTIVE": "1"}
+        elif self.platform == "iflow":
+            return {"IFLOW_NON_INTERACTIVE": "1"}
+        elif self.platform == "codex":
+            return {"CODEX_NON_INTERACTIVE": "1"}
+        elif self.platform == "kiro":
+            return {"KIRO_NON_INTERACTIVE": "1"}
+        elif self.platform == "gemini":
+            return {}  # Gemini CLI doesn't have a non-interactive env var
+        elif self.platform == "antigravity":
+            return {}
+        elif self.platform == "windsurf":
+            return {}
+        elif self.platform == "qoder":
+            return {}
+        elif self.platform == "codebuddy":
+            return {}
+        elif self.platform == "copilot":
+            return {}
+        elif self.platform == "droid":
+            return {}
+        elif self.platform == "pi":
+            return {}
+        else:
+            return {"CLAUDE_NON_INTERACTIVE": "1"}
+
+    # =========================================================================
+    # CLI Command Building
+    # =========================================================================
+
+    def build_run_command(
+        self,
+        agent: str,
+        prompt: str,
+        session_id: str | None = None,
+        skip_permissions: bool = True,
+        verbose: bool = True,
+        json_output: bool = True,
+    ) -> list[str]:
+        """Build CLI command for running an agent.
+
+        Args:
+            agent: Agent name (will be mapped if needed)
+            prompt: Prompt to send to the agent
+            session_id: Optional session ID (Claude Code only for creation)
+            skip_permissions: Whether to skip permission prompts
+            verbose: Whether to enable verbose output
+            json_output: Whether to use JSON output format
+
+        Returns:
+            List of command arguments
+        """
+        mapped_agent = self.get_agent_name(agent)
+
+        if self.platform == "opencode":
+            cmd = ["opencode", "run"]
+            cmd.extend(["--agent", mapped_agent])
+
+            # Note: OpenCode 'run' mode is non-interactive by default
+            # No equivalent to Claude Code's --dangerously-skip-permissions
+            # See: https://github.com/anomalyco/opencode/issues/9070
+
+            if json_output:
+                cmd.extend(["--format", "json"])
+
+            if verbose:
+                cmd.extend(["--log-level", "DEBUG", "--print-logs"])
+
+            # Note: OpenCode doesn't support --session-id on creation
+            # Session ID must be extracted from logs after startup
+
+            cmd.append(prompt)
+
+        elif self.platform == "iflow":
+            cmd = ["iflow", "-y", "-p"]
+            cmd.append(f"${mapped_agent} {prompt}")
+        elif self.platform == "codex":
+            cmd = ["codex", "exec"]
+            cmd.append(prompt)
+        elif self.platform == "kiro":
+            cmd = ["kiro", "run", prompt]
+        elif self.platform == "gemini":
+            cmd = ["gemini"]
+            cmd.append(prompt)
+        elif self.platform == "antigravity":
+            raise ValueError(
+                "Antigravity workflows are UI slash commands; CLI agent run is not supported."
+            )
+        elif self.platform == "windsurf":
+            raise ValueError(
+                "Windsurf workflows are UI slash commands; CLI agent run is not supported."
+            )
+        elif self.platform == "qoder":
+            cmd = ["qodercli", "-p", prompt]
+        elif self.platform == "codebuddy":
+            raise ValueError(
+                "CodeBuddy does not support non-interactive mode (no CLI agent)"
+            )
+        elif self.platform == "copilot":
+            raise ValueError(
+                "GitHub Copilot is IDE-only; CLI agent run is not supported."
+            )
+        elif self.platform == "droid":
+            raise ValueError(
+                "Factory Droid CLI agent run is not yet supported."
+            )
+        elif self.platform == "pi":
+            cmd = ["pi", "-p", prompt]
+
+        else:  # claude
+            cmd = ["claude", "-p"]
+            cmd.extend(["--agent", mapped_agent])
+
+            if session_id:
+                cmd.extend(["--session-id", session_id])
+
+            if skip_permissions:
+                cmd.append("--dangerously-skip-permissions")
+
+            if json_output:
+                cmd.extend(["--output-format", "stream-json"])
+
+            if verbose:
+                cmd.append("--verbose")
+
+            cmd.append(prompt)
+
+        return cmd
+
+    def build_resume_command(self, session_id: str) -> list[str]:
+        """Build CLI command for resuming a session.
+
+        Args:
+            session_id: Session ID to resume (ignored for iFlow)
+
+        Returns:
+            List of command arguments
+        """
+        if self.platform == "opencode":
+            return ["opencode", "run", "--session", session_id]
+        elif self.platform == "iflow":
+            # iFlow uses -c to continue most recent conversation
+            # session_id is ignored as iFlow doesn't support session IDs
+            return ["iflow", "-c"]
+        elif self.platform == "codex":
+            return ["codex", "resume", session_id]
+        elif self.platform == "kiro":
+            return ["kiro", "resume", session_id]
+        elif self.platform == "gemini":
+            return ["gemini", "--resume", session_id]
+        elif self.platform == "antigravity":
+            raise ValueError(
+                "Antigravity workflows are UI slash commands; CLI resume is not supported."
+            )
+        elif self.platform == "windsurf":
+            raise ValueError(
+                "Windsurf workflows are UI slash commands; CLI resume is not supported."
+            )
+        elif self.platform == "qoder":
+            return ["qodercli", "--resume", session_id]
+        elif self.platform == "codebuddy":
+            raise ValueError(
+                "CodeBuddy does not support non-interactive mode (no CLI agent)"
+            )
+        elif self.platform == "copilot":
+            raise ValueError(
+                "GitHub Copilot is IDE-only; CLI resume is not supported."
+            )
+        elif self.platform == "droid":
+            raise ValueError(
+                "Factory Droid CLI resume is not yet supported."
+            )
+        elif self.platform == "pi":
+            return ["pi", "-c", session_id]
+        else:
+            return ["claude", "--resume", session_id]
+
+    def get_resume_command_str(self, session_id: str, cwd: str | None = None) -> str:
+        """Get human-readable resume command string.
+
+        Args:
+            session_id: Session ID to resume
+            cwd: Optional working directory to cd into
+
+        Returns:
+            Command string for display
+        """
+        cmd = self.build_resume_command(session_id)
+        cmd_str = " ".join(cmd)
+
+        if cwd:
+            return f"cd {cwd} && {cmd_str}"
+        return cmd_str
+
+    # =========================================================================
+    # Platform Detection Helpers
+    # =========================================================================
+
+    @property
+    def is_opencode(self) -> bool:
+        """Check if platform is OpenCode."""
+        return self.platform == "opencode"
+
+    @property
+    def is_claude(self) -> bool:
+        """Check if platform is Claude Code."""
+        return self.platform == "claude"
+
+    @property
+    def is_cursor(self) -> bool:
+        """Check if platform is Cursor."""
+        return self.platform == "cursor"
+
+    @property
+    def is_iflow(self) -> bool:
+        """Check if platform is iFlow CLI."""
+        return self.platform == "iflow"
+
+    @property
+    def cli_name(self) -> str:
+        """Get CLI executable name.
+
+        Note: Cursor doesn't have a CLI tool, returns None-like value.
+        """
+        if self.is_opencode:
+            return "opencode"
+        elif self.is_cursor:
+            return "cursor"  # Note: Cursor is IDE-only, no CLI
+        elif self.platform == "iflow":
+            return "iflow"
+        elif self.platform == "kiro":
+            return "kiro"
+        elif self.platform == "gemini":
+            return "gemini"
+        elif self.platform == "antigravity":
+            return "agy"
+        elif self.platform == "windsurf":
+            return "windsurf"
+        elif self.platform == "qoder":
+            return "qodercli"
+        elif self.platform == "codebuddy":
+            return "codebuddy"
+        elif self.platform == "copilot":
+            return "copilot"
+        elif self.platform == "droid":
+            return "droid"
+        elif self.platform == "pi":
+            return "pi"
+        else:
+            return "claude"
+
+    @property
+    def supports_cli_agents(self) -> bool:
+        """Check if platform supports running agents via CLI.
+
+        Claude Code, OpenCode, iFlow, and Codex support CLI agent execution.
+        Cursor is IDE-only and doesn't support CLI agents.
+        """
+        return self.platform in ("claude", "opencode", "iflow", "codex", "pi")
+
+    @property
+    def requires_agent_definition_file(self) -> bool:
+        """Check if platform requires an agent definition file (.md/.toml) to run.
+
+        Claude Code, OpenCode, iFlow: require agent .md files (--agent flag).
+        Codex: auto-discovers agents from .codex/agents/*.toml, no --agent flag.
+        """
+        return self.platform in ("claude", "opencode", "iflow")
+
+    # =========================================================================
+    # Session ID Handling
+    # =========================================================================
+
+    @property
+    def supports_session_id_on_create(self) -> bool:
+        """Check if platform supports specifying session ID on creation.
+
+        Claude Code: Yes (--session-id)
+        OpenCode: No (auto-generated, extract from logs)
+        iFlow: No (no session ID support)
+        """
+        return self.platform == "claude"
+
+    def extract_session_id_from_log(self, log_content: str) -> str | None:
+        """Extract session ID from log output (OpenCode only).
+
+        OpenCode generates session IDs in format: ses_xxx
+
+        Args:
+            log_content: Log file content
+
+        Returns:
+            Session ID if found, None otherwise
+        """
+        import re
+
+        # OpenCode session ID pattern
+        match = re.search(r"ses_[a-zA-Z0-9]+", log_content)
+        if match:
+            return match.group(0)
+        return None
+
+
+# =============================================================================
+# Factory Function
+# =============================================================================
+
+
+def get_cli_adapter(platform: str = "claude") -> CLIAdapter:
+    """Get CLI adapter for the specified platform.
+
+    Args:
+        platform: Platform name ('claude', 'opencode', 'cursor', 'iflow', 'codex', 'kilo', 'kiro', 'gemini', 'antigravity', 'windsurf', 'qoder', 'codebuddy', 'copilot', 'droid', or 'pi')
+
+    Returns:
+        CLIAdapter instance
+
+    Raises:
+        ValueError: If platform is not supported
+    """
+    if platform not in (
+        "claude",
+        "opencode",
+        "cursor",
+        "iflow",
+        "codex",
+        "kilo",
+        "kiro",
+        "gemini",
+        "antigravity",
+        "windsurf",
+        "qoder",
+        "codebuddy",
+        "copilot",
+        "droid",
+        "pi",
+    ):
+        raise ValueError(
+            f"Unsupported platform: {platform} (must be 'claude', 'opencode', 'cursor', 'iflow', 'codex', 'kilo', 'kiro', 'gemini', 'antigravity', 'windsurf', 'qoder', 'codebuddy', 'copilot', 'droid', or 'pi')"
+        )
+
+    return CLIAdapter(platform=platform)  # type: ignore
+
+
+_ALL_PLATFORM_CONFIG_DIRS = (
+    ".claude",
+    ".cursor",
+    ".iflow",
+    ".opencode",
+    ".codex",
+    ".kilocode",
+    ".kiro",
+    ".gemini",
+    ".agent",
+    ".windsurf",
+    ".qoder",
+    ".codebuddy",
+    ".github/copilot",
+    ".factory",
+    ".pi",
+)
+"""Platform-specific config directory names used by detect_platform exclusion
+checks. `.agents/skills/` is NOT listed here: it is a shared cross-platform
+layer (written by Codex, also consumed by Amp/Cline/Warp/etc. via the
+agentskills.io standard), not a single-platform signal. Its presence must not
+block detection of Kiro, Antigravity, Windsurf, or other platforms."""
+
+
+def _has_other_platform_dir(project_root: Path, exclude: set[str]) -> bool:
+    """Check if any platform config dir exists besides those in *exclude*."""
+    return any(
+        (project_root / d).is_dir()
+        for d in _ALL_PLATFORM_CONFIG_DIRS
+        if d not in exclude
+    )
+
+
+def detect_platform(project_root: Path) -> Platform:
+    """Auto-detect platform based on existing config directories.
+
+    Detection order:
+    1. TRELLIS_PLATFORM environment variable (if set)
+    2. .opencode directory exists → opencode
+    3. .iflow directory exists → iflow
+    4. .cursor directory exists (without .claude) → cursor
+    5. .codex exists and no other platform dirs → codex
+    6. .kilocode directory exists → kilo
+    7. .kiro/skills exists and no other platform dirs → kiro
+    8. .gemini directory exists → gemini
+    9. .agent/workflows exists and no other platform dirs → antigravity
+    10. .windsurf/workflows exists and no other platform dirs → windsurf
+    11. .codebuddy directory exists → codebuddy
+    12. .qoder directory exists → qoder
+    13. .pi directory exists → pi
+    14. Default → claude
+
+    Args:
+        project_root: Project root directory
+
+    Returns:
+        Detected platform ('claude', 'opencode', 'cursor', 'iflow', 'codex', 'kilo', 'kiro', 'gemini', 'antigravity', 'windsurf', 'qoder', 'codebuddy', 'copilot', 'droid', 'pi', or default 'claude')
+    """
+    import os
+
+    # Check environment variable first
+    env_platform = os.environ.get("TRELLIS_PLATFORM", "").lower()
+    if env_platform in (
+        "claude",
+        "opencode",
+        "cursor",
+        "iflow",
+        "codex",
+        "kilo",
+        "kiro",
+        "gemini",
+        "antigravity",
+        "windsurf",
+        "qoder",
+        "codebuddy",
+        "copilot",
+        "droid",
+        "pi",
+    ):
+        return env_platform  # type: ignore
+
+    # Check for .opencode directory (OpenCode-specific)
+    if (project_root / ".opencode").is_dir():
+        return "opencode"
+
+    # Check for .iflow directory (iFlow-specific)
+    if (project_root / ".iflow").is_dir():
+        return "iflow"
+
+    # Check for .cursor directory (Cursor-specific)
+    # Only detect as cursor if .claude doesn't exist (to avoid confusion)
+    if (project_root / ".cursor").is_dir() and not (project_root / ".claude").is_dir():
+        return "cursor"
+
+    # Check for .gemini directory (Gemini CLI-specific)
+    if (project_root / ".gemini").is_dir():
+        return "gemini"
+
+    # Check for .codex directory (Codex-specific)
+    # .agents/skills/ alone does NOT trigger codex detection (it's a shared standard)
+    if (project_root / ".codex").is_dir() and not _has_other_platform_dir(
+        project_root, {".codex", ".agents"}
+    ):
+        return "codex"
+
+    # Check for .kilocode directory (Kilo-specific)
+    if (project_root / ".kilocode").is_dir():
+        return "kilo"
+
+    # Check for Kiro skills directory only when no other platform config exists
+    if (project_root / ".kiro" / "skills").is_dir() and not _has_other_platform_dir(
+        project_root, {".kiro"}
+    ):
+        return "kiro"
+
+    # Check for Antigravity workflow directory only when no other platform config exists
+    if (
+        project_root / ".agent" / "workflows"
+    ).is_dir() and not _has_other_platform_dir(
+        project_root, {".agent", ".gemini"}
+    ):
+        return "antigravity"
+
+    # Check for Windsurf workflow directory only when no other platform config exists
+    if (
+        project_root / ".windsurf" / "workflows"
+    ).is_dir() and not _has_other_platform_dir(
+        project_root, {".windsurf"}
+    ):
+        return "windsurf"
+
+    # Check for .codebuddy directory (CodeBuddy-specific)
+    if (project_root / ".codebuddy").is_dir():
+        return "codebuddy"
+
+    # Check for .qoder directory (Qoder-specific)
+    if (project_root / ".qoder").is_dir():
+        return "qoder"
+
+    # Check for .github/copilot directory (GitHub Copilot-specific)
+    if (project_root / ".github" / "copilot").is_dir():
+        return "copilot"
+
+    # Check for .factory directory (Factory Droid-specific)
+    if (project_root / ".factory").is_dir():
+        return "droid"
+
+    # Check for .pi directory (Pi Agent-specific)
+    if (project_root / ".pi").is_dir():
+        return "pi"
+
+    # Fallback: checkout only has the Codex shared-skills layer
+    # (.agents/skills/trellis-* dirs) and no explicit platform config dir.
+    # Happens on fresh clones where .codex/ is gitignored/absent but the
+    # shared skills were committed to git. Must guard against the case
+    # where .claude/ or any other platform dir also exists — .agents/skills/
+    # can legitimately coexist with any platform as a shared consumption
+    # layer for Amp/Cline/Warp/etc.
+    agents_skills = project_root / ".agents" / "skills"
+    if agents_skills.is_dir() and not _has_other_platform_dir(
+        project_root, set()
+    ):
+        try:
+            for entry in agents_skills.iterdir():
+                if entry.is_dir() and entry.name.startswith("trellis-"):
+                    return "codex"
+        except OSError:
+            pass
+
+    return "claude"
+
+
+def get_cli_adapter_auto(project_root: Path) -> CLIAdapter:
+    """Get CLI adapter with auto-detected platform.
+
+    Args:
+        project_root: Project root directory
+
+    Returns:
+        CLIAdapter instance for detected platform
+    """
+    platform = detect_platform(project_root)
+    return CLIAdapter(platform=platform)

.trellis/scripts/common/config.py

@@ -0,0 +1,445 @@
+#!/usr/bin/env python3
+"""
+Trellis configuration reader.
+
+Reads settings from .trellis/config.yaml with sensible defaults.
+"""
+
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+from .paths import DIR_WORKFLOW, get_repo_root
+
+
+# =============================================================================
+# YAML Simple Parser (no dependencies)
+# =============================================================================
+
+
+def _unquote(s: str) -> str:
+    """Remove exactly one layer of matching surrounding quotes.
+
+    Unlike str.strip('"'), this only removes the outermost pair,
+    preserving any nested quotes inside the value.
+
+    Examples:
+        _unquote('"hello"')        -> 'hello'
+        _unquote("'hello'")        -> 'hello'
+        _unquote('"echo \\'hi\\'"')  -> "echo 'hi'"
+        _unquote('hello')          -> 'hello'
+        _unquote('"hello\\'')       -> '"hello\\''  (mismatched, unchanged)
+    """
+    if len(s) >= 2 and s[0] == s[-1] and s[0] in ('"', "'"):
+        return s[1:-1]
+    return s
+
+
+def _strip_inline_comment(value: str) -> str:
+    """Strip ` # …` inline comments while preserving `#` inside quoted strings.
+
+    YAML treats ` #` (space-hash) as a comment opener; bare `#` inside a token
+    is part of the value. Quoted strings are immune.
+
+    Mirrors :func:`common.trellis_config._strip_inline_comment` so both
+    parsers handle ``key: value  # comment`` identically.
+    """
+    in_quote: str | None = None
+    for idx, ch in enumerate(value):
+        if in_quote:
+            if ch == in_quote:
+                in_quote = None
+            continue
+        if ch in ('"', "'"):
+            in_quote = ch
+            continue
+        if ch == "#" and (idx == 0 or value[idx - 1].isspace()):
+            return value[:idx]
+    return value
+
+
+def parse_simple_yaml(content: str) -> dict:
+    """Parse simple YAML with nested dict support (no dependencies).
+
+    Supports:
+        - key: value (string)
+        - key: (followed by list items)
+            - item1
+            - item2
+        - key: (followed by nested dict)
+            nested_key: value
+            nested_key2:
+              - item
+
+    Uses indentation to detect nesting (2+ spaces deeper = child).
+
+    Args:
+        content: YAML content string.
+
+    Returns:
+        Parsed dict (values can be str, list[str], or dict).
+    """
+    lines = content.splitlines()
+    result: dict = {}
+    _parse_yaml_block(lines, 0, 0, result)
+    return result
+
+
+def _parse_yaml_block(
+    lines: list[str], start: int, min_indent: int, target: dict
+) -> int:
+    """Parse a YAML block into target dict, returning next line index."""
+    i = start
+    current_list: list | None = None
+
+    while i < len(lines):
+        line = lines[i]
+        stripped = line.strip()
+
+        # Skip empty lines and comments
+        if not stripped or stripped.startswith("#"):
+            i += 1
+            continue
+
+        # Calculate indentation
+        indent = len(line) - len(line.lstrip())
+
+        # If dedented past our block, we're done
+        if indent < min_indent:
+            break
+
+        if stripped.startswith("- "):
+            if current_list is not None:
+                current_list.append(_unquote(stripped[2:].strip()))
+            i += 1
+        elif ":" in stripped:
+            key, _, value = stripped.partition(":")
+            key = key.strip()
+            value = _strip_inline_comment(value).strip()
+            value = _unquote(value)
+            current_list = None
+
+            if value:
+                # key: value
+                target[key] = value
+                i += 1
+            else:
+                # key: (no value) — peek ahead to determine list vs nested dict
+                next_i, next_line = _next_content_line(lines, i + 1)
+                if next_i >= len(lines):
+                    target[key] = {}
+                    i = next_i
+                elif next_line.strip().startswith("- "):
+                    # It's a list
+                    current_list = []
+                    target[key] = current_list
+                    i += 1
+                else:
+                    next_indent = len(next_line) - len(next_line.lstrip())
+                    if next_indent > indent:
+                        # It's a nested dict
+                        nested: dict = {}
+                        target[key] = nested
+                        i = _parse_yaml_block(lines, i + 1, next_indent, nested)
+                    else:
+                        # Empty value, same or less indent follows
+                        target[key] = {}
+                        i += 1
+        else:
+            i += 1
+
+    return i
+
+
+def _next_content_line(lines: list[str], start: int) -> tuple[int, str]:
+    """Find the next non-empty, non-comment line."""
+    i = start
+    while i < len(lines):
+        stripped = lines[i].strip()
+        if stripped and not stripped.startswith("#"):
+            return i, lines[i]
+        i += 1
+    return i, ""
+
+
+# Defaults
+DEFAULT_SESSION_COMMIT_MESSAGE = "chore: record journal"
+DEFAULT_MAX_JOURNAL_LINES = 2000
+DEFAULT_SESSION_AUTO_COMMIT = True
+
+CONFIG_FILE = "config.yaml"
+
+
+def _is_true_config_value(value: object) -> bool:
+    """Return True when a config value represents an enabled flag."""
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.strip().lower() == "true"
+    return False
+
+
+def _get_config_path(repo_root: Path | None = None) -> Path:
+    """Get path to config.yaml."""
+    root = repo_root or get_repo_root()
+    return root / DIR_WORKFLOW / CONFIG_FILE
+
+
+def _load_config(repo_root: Path | None = None) -> dict:
+    """Load and parse config.yaml. Returns empty dict on any error."""
+    config_file = _get_config_path(repo_root)
+    try:
+        content = config_file.read_text(encoding="utf-8")
+        return parse_simple_yaml(content)
+    except (OSError, IOError):
+        return {}
+
+
+def get_session_commit_message(repo_root: Path | None = None) -> str:
+    """Get the commit message for auto-committing session records."""
+    config = _load_config(repo_root)
+    return config.get("session_commit_message", DEFAULT_SESSION_COMMIT_MESSAGE)
+
+
+def get_max_journal_lines(repo_root: Path | None = None) -> int:
+    """Get the maximum lines per journal file."""
+    config = _load_config(repo_root)
+    value = config.get("max_journal_lines", DEFAULT_MAX_JOURNAL_LINES)
+    try:
+        return int(value)
+    except (ValueError, TypeError):
+        return DEFAULT_MAX_JOURNAL_LINES
+
+
+def get_session_auto_commit(repo_root: Path | None = None) -> bool:
+    """Whether scripts should auto-stage + auto-commit session/task changes.
+
+    Governs both ``add_session.py:_auto_commit_workspace`` and
+    ``task_store.py:_auto_commit_archive``.
+
+    Default: ``True`` (existing behavior — auto-stage + auto-commit).
+    Set ``session_auto_commit: false`` in ``.trellis/config.yaml`` to skip
+    auto-staging entirely; the journal/archive files are still written to
+    disk, but the user manages ``git add`` / ``git commit`` themselves.
+
+    Accepts native YAML booleans (``true`` / ``false``) and the string
+    aliases ``true / false / yes / no / 1 / 0 / on / off`` (case-insensitive).
+    Invalid values fall back to ``True`` with a stderr warning.
+    """
+    config = _load_config(repo_root)
+    raw = config.get("session_auto_commit", DEFAULT_SESSION_AUTO_COMMIT)
+    if isinstance(raw, bool):
+        return raw
+    s = str(raw).strip().lower()
+    if s in ("true", "yes", "1", "on"):
+        return True
+    if s in ("false", "no", "0", "off"):
+        return False
+    print(
+        f"[WARN] invalid session_auto_commit value: {raw!r}; using true (default)",
+        file=sys.stderr,
+    )
+    return DEFAULT_SESSION_AUTO_COMMIT
+
+
+def get_hooks(event: str, repo_root: Path | None = None) -> list[str]:
+    """Get hook commands for a lifecycle event.
+
+    Args:
+        event: Event name (e.g. "after_create", "after_archive").
+        repo_root: Repository root path.
+
+    Returns:
+        List of shell commands to execute, empty if none configured.
+    """
+    config = _load_config(repo_root)
+    hooks = config.get("hooks")
+    if not isinstance(hooks, dict):
+        return []
+    commands = hooks.get(event)
+    if isinstance(commands, list):
+        return [str(c) for c in commands]
+    return []
+
+
+# =============================================================================
+# Monorepo / Packages
+# =============================================================================
+
+
+def get_packages(repo_root: Path | None = None) -> dict[str, dict] | None:
+    """Get monorepo package declarations.
+
+    Returns:
+        Dict mapping package name to its config (path, type, etc.),
+        or None if not configured (single-repo mode).
+
+    Example return:
+        {"cli": {"path": "packages/cli"}, "docs-site": {"path": "docs-site", "type": "submodule"}}
+    """
+    config = _load_config(repo_root)
+    packages = config.get("packages")
+    if not isinstance(packages, dict):
+        return None
+    # Ensure each value is a dict (filter out scalar entries)
+    filtered = {k: v for k, v in packages.items() if isinstance(v, dict)}
+    if not filtered:
+        return None
+    return filtered
+
+
+def get_default_package(repo_root: Path | None = None) -> str | None:
+    """Get the default package name from config.
+
+    Returns:
+        Package name string, or None if not configured.
+    """
+    config = _load_config(repo_root)
+    value = config.get("default_package")
+    return str(value) if value else None
+
+
+def get_submodule_packages(repo_root: Path | None = None) -> dict[str, str]:
+    """Get packages that are git submodules.
+
+    Returns:
+        Dict mapping package name to its path for submodule-type packages.
+        Empty dict if none configured.
+
+    Example return:
+        {"docs-site": "docs-site"}
+    """
+    packages = get_packages(repo_root)
+    if packages is None:
+        return {}
+    return {
+        name: cfg.get("path", name)
+        for name, cfg in packages.items()
+        if cfg.get("type") == "submodule"
+    }
+
+
+def get_git_packages(repo_root: Path | None = None) -> dict[str, str]:
+    """Get packages that have their own independent git repository.
+
+    These are sub-directories with their own .git (not submodules),
+    marked with ``git: true`` in config.yaml.
+
+    Returns:
+        Dict mapping package name to its path for git-repo packages.
+        Empty dict if none configured.
+
+    Example config::
+
+        packages:
+          backend:
+            path: iqs
+            git: true
+
+    Example return::
+
+        {"backend": "iqs"}
+    """
+    packages = get_packages(repo_root)
+    if packages is None:
+        return {}
+    return {
+        name: cfg.get("path", name)
+        for name, cfg in packages.items()
+        if _is_true_config_value(cfg.get("git"))
+    }
+
+
+def is_monorepo(repo_root: Path | None = None) -> bool:
+    """Check if the project is configured as a monorepo (has packages in config)."""
+    return get_packages(repo_root) is not None
+
+
+def get_spec_base(package: str | None = None, repo_root: Path | None = None) -> str:
+    """Get the spec directory base path relative to .trellis/.
+
+    Single-repo: returns "spec"
+    Monorepo with package: returns "spec/<package>"
+    Monorepo without package: returns "spec" (caller should specify package)
+    """
+    if package and is_monorepo(repo_root):
+        return f"spec/{package}"
+    return "spec"
+
+
+def validate_package(package: str, repo_root: Path | None = None) -> bool:
+    """Check if a package name is valid in this project.
+
+    Single-repo (no packages configured): always returns True.
+    Monorepo: returns True only if package exists in config.yaml packages.
+    """
+    packages = get_packages(repo_root)
+    if packages is None:
+        return True  # Single-repo, no validation needed
+    return package in packages
+
+
+def resolve_package(
+    task_package: str | None = None,
+    repo_root: Path | None = None,
+) -> str | None:
+    """Resolve package from inferred sources with validation.
+
+    Checks in order: task_package → default_package.
+    Invalid inferred values print a warning to stderr and are skipped.
+
+    Returns:
+        Resolved package name, or None if no valid package found.
+
+    Note:
+        CLI --package should be validated separately by the caller
+        (fail-fast with available packages list on error).
+    """
+    packages = get_packages(repo_root)
+    if packages is None:
+        return None  # Single-repo, no package needed
+
+    # Try task_package (guard against non-string values from malformed JSON)
+    if task_package and isinstance(task_package, str):
+        if task_package in packages:
+            return task_package
+        print(
+            f"Warning: task.json package '{task_package}' not found in config, skipping",
+            file=sys.stderr,
+        )
+
+    # Try default_package
+    default = get_default_package(repo_root)
+    if default:
+        if default in packages:
+            return default
+        print(
+            f"Warning: default_package '{default}' not found in config, skipping",
+            file=sys.stderr,
+        )
+
+    return None
+
+
+def get_spec_scope(repo_root: Path | None = None) -> list[str] | str | None:
+    """Get session.spec_scope configuration.
+
+    Returns:
+        list[str]: Package names to include in spec scanning.
+        str: "active_task" to use current task's package.
+        None: No scope configured (scan all packages).
+    """
+    config = _load_config(repo_root)
+    session = config.get("session")
+    if not isinstance(session, dict):
+        return None
+
+    scope = session.get("spec_scope")
+    if scope is None:
+        return None
+    if isinstance(scope, str):
+        return scope  # e.g. "active_task"
+    if isinstance(scope, list):
+        return [str(s) for s in scope]
+    return None

.trellis/scripts/common/developer.py

@@ -0,0 +1,190 @@
+#!/usr/bin/env python3
+"""
+Developer management utilities.
+
+Provides:
+    init_developer     - Initialize developer
+    ensure_developer   - Ensure developer is initialized (exit if not)
+    show_developer_info - Show developer information
+"""
+
+from __future__ import annotations
+
+import sys
+from datetime import datetime
+from pathlib import Path
+
+from .paths import (
+    DIR_WORKFLOW,
+    DIR_WORKSPACE,
+    DIR_TASKS,
+    FILE_DEVELOPER,
+    FILE_JOURNAL_PREFIX,
+    get_repo_root,
+    get_developer,
+    check_developer,
+)
+
+
+# =============================================================================
+# Developer Initialization
+# =============================================================================
+
+def init_developer(name: str, repo_root: Path | None = None) -> bool:
+    """Initialize developer.
+
+    Creates:
+        - .trellis/.developer file with developer info
+        - .trellis/workspace/<name>/ directory structure
+        - Initial journal file and index.md
+
+    Args:
+        name: Developer name.
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        True on success, False on error.
+    """
+    if not name:
+        print("Error: developer name is required", file=sys.stderr)
+        return False
+
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    dev_file = repo_root / DIR_WORKFLOW / FILE_DEVELOPER
+    workspace_dir = repo_root / DIR_WORKFLOW / DIR_WORKSPACE / name
+
+    # Create .developer file
+    initialized_at = datetime.now().isoformat()
+    try:
+        dev_file.write_text(
+            f"name={name}\ninitialized_at={initialized_at}\n",
+            encoding="utf-8"
+        )
+    except (OSError, IOError) as e:
+        print(f"Error: Failed to create .developer file: {e}", file=sys.stderr)
+        return False
+
+    # Create workspace directory structure
+    try:
+        workspace_dir.mkdir(parents=True, exist_ok=True)
+    except (OSError, IOError) as e:
+        print(f"Error: Failed to create workspace directory: {e}", file=sys.stderr)
+        return False
+
+    # Create initial journal file
+    journal_file = workspace_dir / f"{FILE_JOURNAL_PREFIX}1.md"
+    if not journal_file.exists():
+        today = datetime.now().strftime("%Y-%m-%d")
+        journal_content = f"""# Journal - {name} (Part 1)
+
+> AI development session journal
+> Started: {today}
+
+---
+
+"""
+        try:
+            journal_file.write_text(journal_content, encoding="utf-8")
+        except (OSError, IOError) as e:
+            print(f"Error: Failed to create journal file: {e}", file=sys.stderr)
+            return False
+
+    # Create index.md with markers for auto-update
+    index_file = workspace_dir / "index.md"
+    if not index_file.exists():
+        index_content = f"""# Workspace Index - {name}
+
+> Journal tracking for AI development sessions.
+
+---
+
+## Current Status
+
+<!-- @@@auto:current-status -->
+- **Active File**: `journal-1.md`
+- **Total Sessions**: 0
+- **Last Active**: -
+<!-- @@@/auto:current-status -->
+
+---
+
+## Active Documents
+
+<!-- @@@auto:active-documents -->
+| File | Lines | Status |
+|------|-------|--------|
+| `journal-1.md` | ~0 | Active |
+<!-- @@@/auto:active-documents -->
+
+---
+
+## Session History
+
+<!-- @@@auto:session-history -->
+| # | Date | Title | Commits | Branch |
+|---|------|-------|---------|--------|
+<!-- @@@/auto:session-history -->
+
+---
+
+## Notes
+
+- Sessions are appended to journal files
+- New journal file created when current exceeds 2000 lines
+- Use `add_session.py` to record sessions
+"""
+        try:
+            index_file.write_text(index_content, encoding="utf-8")
+        except (OSError, IOError) as e:
+            print(f"Error: Failed to create index.md: {e}", file=sys.stderr)
+            return False
+
+    print(f"Developer initialized: {name}")
+    print(f"  .developer file: {dev_file}")
+    print(f"  Workspace dir: {workspace_dir}")
+
+    return True
+
+
+def ensure_developer(repo_root: Path | None = None) -> None:
+    """Ensure developer is initialized, exit if not.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    if not check_developer(repo_root):
+        print("Error: Developer not initialized.", file=sys.stderr)
+        print(f"Run: python ./{DIR_WORKFLOW}/scripts/init_developer.py <your-name>", file=sys.stderr)
+        sys.exit(1)
+
+
+def show_developer_info(repo_root: Path | None = None) -> None:
+    """Show developer information.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    developer = get_developer(repo_root)
+
+    if not developer:
+        print("Developer: (not initialized)")
+    else:
+        print(f"Developer: {developer}")
+        print(f"Workspace: {DIR_WORKFLOW}/{DIR_WORKSPACE}/{developer}/")
+        print(f"Tasks: {DIR_WORKFLOW}/{DIR_TASKS}/")
+
+
+# =============================================================================
+# Main Entry (for testing)
+# =============================================================================
+
+if __name__ == "__main__":
+    show_developer_info()

.trellis/scripts/common/git.py

@@ -0,0 +1,31 @@
+"""
+Git command execution utility.
+
+Single source of truth for running git commands across all Trellis scripts.
+"""
+
+from __future__ import annotations
+
+import subprocess
+from pathlib import Path
+
+
+def run_git(args: list[str], cwd: Path | None = None) -> tuple[int, str, str]:
+    """Run a git command and return (returncode, stdout, stderr).
+
+    Uses UTF-8 encoding with -c i18n.logOutputEncoding=UTF-8 to ensure
+    consistent output across all platforms (Windows, macOS, Linux).
+    """
+    try:
+        git_args = ["git", "-c", "i18n.logOutputEncoding=UTF-8"] + args
+        result = subprocess.run(
+            git_args,
+            cwd=cwd,
+            capture_output=True,
+            text=True,
+            encoding="utf-8",
+            errors="replace",
+        )
+        return result.returncode, result.stdout, result.stderr
+    except Exception as e:
+        return 1, "", str(e)

.trellis/scripts/common/git_context.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Git and Session Context utilities.
+
+Entry shim — delegates to session_context and packages_context.
+
+Provides:
+    output_json - Output context in JSON format
+    output_text - Output context in text format
+"""
+
+from __future__ import annotations
+
+import json
+
+from .git import run_git
+from .session_context import (
+    get_context_json,
+    get_context_text,
+    get_context_record_json,
+    get_context_text_record,
+    output_json,
+    output_text,
+)
+from .packages_context import (
+    get_context_packages_text,
+    get_context_packages_json,
+)
+from .trellis_config import read_trellis_config
+from .workflow_phase import (
+    filter_platform,
+    get_phase_index,
+    get_step,
+    resolve_effective_platform,
+)
+
+# Backward-compatible alias — external modules import this name
+_run_git_command = run_git
+
+
+# =============================================================================
+# Main Entry
+# =============================================================================
+
+def main() -> None:
+    """CLI entry point."""
+    import argparse
+
+    parser = argparse.ArgumentParser(description="Get Session Context for AI Agent")
+    parser.add_argument(
+        "--json",
+        "-j",
+        action="store_true",
+        help="Output in JSON format (works with any --mode)",
+    )
+    parser.add_argument(
+        "--mode",
+        "-m",
+        choices=["default", "record", "packages", "phase"],
+        default="default",
+        help="Output mode: default (full context), record (for record-session), packages (package info only), phase (workflow step extraction)",
+    )
+    parser.add_argument(
+        "--step",
+        help="Step id for --mode phase, e.g. 1.1, 2.2. Omit to get the Phase Index.",
+    )
+    parser.add_argument(
+        "--platform",
+        help="Platform name for --mode phase, e.g. cursor, claude-code. Filters platform-tagged blocks.",
+    )
+
+    args = parser.parse_args()
+
+    if args.mode == "record":
+        if args.json:
+            print(json.dumps(get_context_record_json(), indent=2, ensure_ascii=False))
+        else:
+            print(get_context_text_record())
+    elif args.mode == "packages":
+        if args.json:
+            print(json.dumps(get_context_packages_json(), indent=2, ensure_ascii=False))
+        else:
+            print(get_context_packages_text())
+    elif args.mode == "phase":
+        content = get_step(args.step) if args.step else get_phase_index()
+        if not content.strip():
+            if args.step:
+                parser.exit(2, f"Step not found: {args.step}\n")
+            else:
+                parser.exit(2, "Phase Index section not found in workflow.md\n")
+        if args.platform:
+            effective = resolve_effective_platform(
+                args.platform, read_trellis_config()
+            )
+            content = filter_platform(content, effective)
+        print(content, end="")
+    else:
+        if args.json:
+            output_json()
+        else:
+            output_text()
+
+
+if __name__ == "__main__":
+    main()

.trellis/scripts/common/io.py

@@ -0,0 +1,37 @@
+"""
+JSON file I/O utilities.
+
+Provides read_json and write_json as the single source of truth
+for JSON file operations across all Trellis scripts.
+"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+
+def read_json(path: Path) -> dict | None:
+    """Read and parse a JSON file.
+
+    Returns None if the file doesn't exist, is invalid JSON, or can't be read.
+    """
+    try:
+        return json.loads(path.read_text(encoding="utf-8"))
+    except (FileNotFoundError, json.JSONDecodeError, OSError):
+        return None
+
+
+def write_json(path: Path, data: dict) -> bool:
+    """Write dict to JSON file with pretty formatting.
+
+    Returns True on success, False on error.
+    """
+    try:
+        path.write_text(
+            json.dumps(data, indent=2, ensure_ascii=False),
+            encoding="utf-8",
+        )
+        return True
+    except (OSError, IOError):
+        return False

.trellis/scripts/common/log.py

@@ -0,0 +1,45 @@
+"""
+Terminal output utilities: colors and structured logging.
+
+Single source of truth for Colors and log_* functions
+used across all Trellis scripts.
+"""
+
+from __future__ import annotations
+
+
+class Colors:
+    """ANSI color codes for terminal output."""
+
+    RED = "\033[0;31m"
+    GREEN = "\033[0;32m"
+    YELLOW = "\033[1;33m"
+    BLUE = "\033[0;34m"
+    CYAN = "\033[0;36m"
+    DIM = "\033[2m"
+    NC = "\033[0m"  # No Color / Reset
+
+
+def colored(text: str, color: str) -> str:
+    """Apply ANSI color to text."""
+    return f"{color}{text}{Colors.NC}"
+
+
+def log_info(msg: str) -> None:
+    """Print info-level message with [INFO] prefix."""
+    print(f"{Colors.BLUE}[INFO]{Colors.NC} {msg}")
+
+
+def log_success(msg: str) -> None:
+    """Print success message with [SUCCESS] prefix."""
+    print(f"{Colors.GREEN}[SUCCESS]{Colors.NC} {msg}")
+
+
+def log_warn(msg: str) -> None:
+    """Print warning message with [WARN] prefix."""
+    print(f"{Colors.YELLOW}[WARN]{Colors.NC} {msg}")
+
+
+def log_error(msg: str) -> None:
+    """Print error message with [ERROR] prefix."""
+    print(f"{Colors.RED}[ERROR]{Colors.NC} {msg}")

.trellis/scripts/common/packages_context.py

@@ -0,0 +1,238 @@
+#!/usr/bin/env python3
+"""
+Package discovery and context output.
+
+Provides:
+    get_packages_info           - Get structured package info
+    get_packages_section        - Build PACKAGES text section
+    get_context_packages_text   - Full packages text output (--mode packages)
+    get_context_packages_json   - Full packages JSON output (--mode packages --json)
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from .config import _is_true_config_value, get_default_package, get_packages, get_spec_scope
+from .paths import (
+    DIR_SPEC,
+    DIR_WORKFLOW,
+    get_current_task,
+    get_repo_root,
+)
+from .tasks import load_task
+
+
+# =============================================================================
+# Internal Helpers
+# =============================================================================
+
+def _scan_spec_layers(spec_dir: Path, package: str | None = None) -> list[str]:
+    """Scan spec directory for available layers (subdirectories).
+
+    For monorepo: scans spec/<package>/
+    For single-repo: scans spec/
+    """
+    target = spec_dir / package if package else spec_dir
+    if not target.is_dir():
+        return []
+    return sorted(
+        d.name for d in target.iterdir() if d.is_dir() and d.name != "guides"
+    )
+
+
+def _get_active_task_package(repo_root: Path) -> str | None:
+    """Get the package field from the active task's task.json."""
+    current = get_current_task(repo_root)
+    if not current:
+        return None
+    ct = load_task(repo_root / current)
+    return ct.package if ct and ct.package else None
+
+
+def _resolve_scope_set(
+    packages: dict,
+    spec_scope,
+    task_pkg: str | None,
+    default_pkg: str | None,
+) -> set | None:
+    """Resolve spec_scope to a set of allowed package names, or None for full scan."""
+    if not packages:
+        return None
+
+    if spec_scope is None:
+        return None
+
+    if isinstance(spec_scope, str) and spec_scope == "active_task":
+        if task_pkg and task_pkg in packages:
+            return {task_pkg}
+        if default_pkg and default_pkg in packages:
+            return {default_pkg}
+        return None
+
+    if isinstance(spec_scope, list):
+        valid = {e for e in spec_scope if e in packages}
+        if valid:
+            return valid
+        # All invalid: fallback
+        if task_pkg and task_pkg in packages:
+            return {task_pkg}
+        if default_pkg and default_pkg in packages:
+            return {default_pkg}
+        return None
+
+    return None
+
+
+# =============================================================================
+# Public Functions
+# =============================================================================
+
+def get_packages_info(repo_root: Path) -> list[dict]:
+    """Get structured package info for monorepo projects.
+
+    Returns list of dicts with keys: name, path, type, default, specLayers,
+    isSubmodule, isGitRepo.
+    Returns empty list for single-repo projects.
+    """
+    packages = get_packages(repo_root)
+    if not packages:
+        return []
+
+    default_pkg = get_default_package(repo_root)
+    spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
+    result = []
+
+    for pkg_name, pkg_config in packages.items():
+        pkg_path = pkg_config.get("path", pkg_name) if isinstance(pkg_config, dict) else str(pkg_config)
+        pkg_type = pkg_config.get("type", "local") if isinstance(pkg_config, dict) else "local"
+        pkg_git = pkg_config.get("git", False) if isinstance(pkg_config, dict) else False
+        layers = _scan_spec_layers(spec_dir, pkg_name)
+
+        result.append({
+            "name": pkg_name,
+            "path": pkg_path,
+            "type": pkg_type,
+            "default": pkg_name == default_pkg,
+            "specLayers": layers,
+            "isSubmodule": pkg_type == "submodule",
+            "isGitRepo": _is_true_config_value(pkg_git),
+        })
+
+    return result
+
+
+def get_packages_section(repo_root: Path) -> str:
+    """Build the PACKAGES section for text output."""
+    spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
+    pkg_info = get_packages_info(repo_root)
+
+    lines: list[str] = []
+    lines.append("## PACKAGES")
+
+    if not pkg_info:
+        lines.append("(single-repo mode)")
+        layers = _scan_spec_layers(spec_dir)
+        if layers:
+            lines.append(f"Spec layers: {', '.join(layers)}")
+        return "\n".join(lines)
+
+    default_pkg = get_default_package(repo_root)
+
+    for pkg in pkg_info:
+        layers_str = f"  [{', '.join(pkg['specLayers'])}]" if pkg["specLayers"] else ""
+        submodule_tag = "  (submodule)" if pkg["isSubmodule"] else ""
+        git_repo_tag = "  (git repo)" if pkg["isGitRepo"] else ""
+        default_tag = "  *" if pkg["default"] else ""
+        lines.append(
+            f"- {pkg['name']:<16} {pkg['path']:<20}{layers_str}{submodule_tag}{git_repo_tag}{default_tag}"
+        )
+
+    if default_pkg:
+        lines.append(f"Default package: {default_pkg}")
+
+    return "\n".join(lines)
+
+
+def get_context_packages_text(repo_root: Path | None = None) -> str:
+    """Get packages context as formatted text (for --mode packages)."""
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    pkg_info = get_packages_info(repo_root)
+    lines: list[str] = []
+
+    if not pkg_info:
+        spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
+        lines.append("Single-repo project (no packages configured)")
+        lines.append("")
+        layers = _scan_spec_layers(spec_dir)
+        if layers:
+            lines.append(f"Spec layers: {', '.join(layers)}")
+        return "\n".join(lines)
+
+    # Resolve scope for annotations
+    packages_dict = get_packages(repo_root) or {}
+    default_pkg = get_default_package(repo_root)
+    spec_scope = get_spec_scope(repo_root)
+    task_pkg = _get_active_task_package(repo_root)
+    scope_set = _resolve_scope_set(packages_dict, spec_scope, task_pkg, default_pkg)
+
+    lines.append("## PACKAGES")
+    lines.append("")
+    for pkg in pkg_info:
+        default_tag = " (default)" if pkg["default"] else ""
+        type_tag = f" [{pkg['type']}]" if pkg["type"] != "local" else ""
+        git_tag = " [git repo]" if pkg["isGitRepo"] else ""
+
+        # Scope annotation
+        scope_tag = ""
+        if scope_set is not None and pkg["name"] not in scope_set:
+            scope_tag = " (out of scope)"
+
+        lines.append(f"### {pkg['name']}{default_tag}{type_tag}{git_tag}{scope_tag}")
+        lines.append(f"Path: {pkg['path']}")
+        if pkg["specLayers"]:
+            lines.append(f"Spec layers: {', '.join(pkg['specLayers'])}")
+            for layer in pkg["specLayers"]:
+                lines.append(f"  - .trellis/spec/{pkg['name']}/{layer}/index.md")
+        else:
+            lines.append("Spec: not configured")
+        lines.append("")
+
+    # Also show shared guides
+    guides_dir = repo_root / DIR_WORKFLOW / DIR_SPEC / "guides"
+    if guides_dir.is_dir():
+        lines.append("### Shared Guides (always included)")
+        lines.append("Path: .trellis/spec/guides/index.md")
+        lines.append("")
+
+    return "\n".join(lines)
+
+
+def get_context_packages_json(repo_root: Path | None = None) -> dict:
+    """Get packages context as a dictionary (for --mode packages --json)."""
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    pkg_info = get_packages_info(repo_root)
+
+    if not pkg_info:
+        spec_dir = repo_root / DIR_WORKFLOW / DIR_SPEC
+        layers = _scan_spec_layers(spec_dir)
+        return {
+            "mode": "single-repo",
+            "specLayers": layers,
+        }
+
+    default_pkg = get_default_package(repo_root)
+    spec_scope = get_spec_scope(repo_root)
+    task_pkg = _get_active_task_package(repo_root)
+
+    return {
+        "mode": "monorepo",
+        "packages": pkg_info,
+        "defaultPackage": default_pkg,
+        "specScope": spec_scope,
+        "activeTaskPackage": task_pkg,
+    }

.trellis/scripts/common/paths.py

@@ -0,0 +1,447 @@
+#!/usr/bin/env python3
+"""
+Common path utilities for Trellis workflow.
+
+Provides:
+    get_repo_root          - Get repository root directory
+    get_developer          - Get developer name
+    get_workspace_dir      - Get developer workspace directory
+    get_tasks_dir          - Get tasks directory
+    get_active_journal_file - Get current journal file
+"""
+
+from __future__ import annotations
+
+import re
+from datetime import datetime
+from pathlib import Path
+
+
+# =============================================================================
+# Path Constants (change here to rename directories)
+# =============================================================================
+
+# Directory names
+DIR_WORKFLOW = ".trellis"
+DIR_WORKSPACE = "workspace"
+DIR_TASKS = "tasks"
+DIR_ARCHIVE = "archive"
+DIR_SPEC = "spec"
+DIR_SCRIPTS = "scripts"
+
+# File names
+FILE_DEVELOPER = ".developer"
+FILE_CURRENT_TASK = ".current-task"
+FILE_TASK_JSON = "task.json"
+FILE_JOURNAL_PREFIX = "journal-"
+
+
+# =============================================================================
+# Repository Root
+# =============================================================================
+
+def get_repo_root(start_path: Path | None = None) -> Path:
+    """Find the nearest directory containing .trellis/ folder.
+
+    This handles nested git repos correctly (e.g., test project inside another repo).
+
+    Args:
+        start_path: Starting directory to search from. Defaults to current directory.
+
+    Returns:
+        Path to repository root, or current directory if no .trellis/ found.
+    """
+    current = (start_path or Path.cwd()).resolve()
+
+    while current != current.parent:
+        if (current / DIR_WORKFLOW).is_dir():
+            return current
+        current = current.parent
+
+    # Fallback to current directory if no .trellis/ found
+    return Path.cwd().resolve()
+
+
+# =============================================================================
+# Developer
+# =============================================================================
+
+def get_developer(repo_root: Path | None = None) -> str | None:
+    """Get developer name from .developer file.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        Developer name or None if not initialized.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    dev_file = repo_root / DIR_WORKFLOW / FILE_DEVELOPER
+
+    if not dev_file.is_file():
+        return None
+
+    try:
+        content = dev_file.read_text(encoding="utf-8")
+        for line in content.splitlines():
+            if line.startswith("name="):
+                return line.split("=", 1)[1].strip()
+    except (OSError, IOError):
+        pass
+
+    return None
+
+
+def check_developer(repo_root: Path | None = None) -> bool:
+    """Check if developer is initialized.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        True if developer is initialized.
+    """
+    return get_developer(repo_root) is not None
+
+
+# =============================================================================
+# Tasks Directory
+# =============================================================================
+
+def get_tasks_dir(repo_root: Path | None = None) -> Path:
+    """Get tasks directory path.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        Path to tasks directory.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+    return repo_root / DIR_WORKFLOW / DIR_TASKS
+
+
+# =============================================================================
+# Workspace Directory
+# =============================================================================
+
+def get_workspace_dir(repo_root: Path | None = None) -> Path | None:
+    """Get developer workspace directory.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        Path to workspace directory or None if developer not set.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    developer = get_developer(repo_root)
+    if developer:
+        return repo_root / DIR_WORKFLOW / DIR_WORKSPACE / developer
+    return None
+
+
+# =============================================================================
+# Journal File
+# =============================================================================
+
+def get_active_journal_file(repo_root: Path | None = None) -> Path | None:
+    """Get the current active journal file.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        Path to active journal file or None if not found.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    workspace_dir = get_workspace_dir(repo_root)
+    if workspace_dir is None or not workspace_dir.is_dir():
+        return None
+
+    latest: Path | None = None
+    highest = 0
+
+    for f in workspace_dir.glob(f"{FILE_JOURNAL_PREFIX}*.md"):
+        if not f.is_file():
+            continue
+
+        # Extract number from filename
+        name = f.stem  # e.g., "journal-1"
+        match = re.search(r"(\d+)$", name)
+        if match:
+            num = int(match.group(1))
+            if num > highest:
+                highest = num
+                latest = f
+
+    return latest
+
+
+def count_lines(file_path: Path) -> int:
+    """Count lines in a file.
+
+    Args:
+        file_path: Path to file.
+
+    Returns:
+        Number of lines, or 0 if file doesn't exist.
+    """
+    if not file_path.is_file():
+        return 0
+
+    try:
+        return len(file_path.read_text(encoding="utf-8").splitlines())
+    except (OSError, IOError):
+        return 0
+
+
+# =============================================================================
+# Current Task Management
+# =============================================================================
+
+def normalize_task_ref(task_ref: str) -> str:
+    """Normalize a task ref for stable runtime storage.
+
+    Stored refs should prefer repo-relative POSIX paths like
+    `.trellis/tasks/03-27-my-task`, even on Windows. Absolute paths are preserved
+    unless they can later be converted back to repo-relative form by callers.
+    """
+    normalized = task_ref.strip()
+    if not normalized:
+        return ""
+
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return str(path_obj)
+
+    normalized = normalized.replace("\\", "/")
+    while normalized.startswith("./"):
+        normalized = normalized[2:]
+
+    if normalized.startswith(f"{DIR_TASKS}/"):
+        return f"{DIR_WORKFLOW}/{normalized}"
+
+    return normalized
+
+
+def resolve_task_ref(task_ref: str, repo_root: Path | None = None) -> Path | None:
+    """Resolve a task ref to an absolute task directory path."""
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    normalized = normalize_task_ref(task_ref)
+    if not normalized:
+        return None
+
+    path_obj = Path(normalized)
+    if path_obj.is_absolute():
+        return path_obj
+
+    if normalized.startswith(f"{DIR_WORKFLOW}/"):
+        return repo_root / path_obj
+
+    return repo_root / DIR_WORKFLOW / DIR_TASKS / path_obj
+
+
+def get_current_task(
+    repo_root: Path | None = None,
+    platform_input: dict | None = None,
+    platform: str | None = None,
+) -> str | None:
+    """Get current task directory path (relative to repo_root).
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        Relative path to current task directory or None.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    from .active_task import resolve_active_task
+
+    return resolve_active_task(repo_root, platform_input, platform).task_path
+
+
+def get_current_task_abs(
+    repo_root: Path | None = None,
+    platform_input: dict | None = None,
+    platform: str | None = None,
+) -> Path | None:
+    """Get current task directory absolute path.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        Absolute path to current task directory or None.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    relative = get_current_task(repo_root, platform_input, platform)
+    if relative:
+        return resolve_task_ref(relative, repo_root)
+    return None
+
+
+def get_current_task_source(
+    repo_root: Path | None = None,
+    platform_input: dict | None = None,
+    platform: str | None = None,
+) -> tuple[str, str | None, str | None]:
+    """Get active task source as (`source`, `context_key`, `task_path`)."""
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    from .active_task import get_current_task_source as _get_source
+
+    return _get_source(repo_root, platform_input, platform)
+
+
+def set_current_task(
+    task_path: str,
+    repo_root: Path | None = None,
+    platform_input: dict | None = None,
+    platform: str | None = None,
+) -> bool:
+    """Set current task in session scope.
+
+    Args:
+        task_path: Task directory path (relative to repo_root).
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        True on success, False on error.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    from .active_task import set_active_task
+
+    return set_active_task(
+        task_path,
+        repo_root,
+        platform_input=platform_input,
+        platform=platform,
+    ) is not None
+
+
+def clear_current_task(
+    repo_root: Path | None = None,
+    platform_input: dict | None = None,
+    platform: str | None = None,
+) -> bool:
+    """Clear current task in session scope.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        True on success.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    from .active_task import clear_active_task
+
+    clear_active_task(
+        repo_root,
+        platform_input=platform_input,
+        platform=platform,
+    )
+    return True
+
+
+def has_current_task(repo_root: Path | None = None) -> bool:
+    """Check if has current task.
+
+    Args:
+        repo_root: Repository root path. Defaults to auto-detected.
+
+    Returns:
+        True if current task is set.
+    """
+    return get_current_task(repo_root) is not None
+
+
+# =============================================================================
+# Task ID Generation
+# =============================================================================
+
+def generate_task_date_prefix() -> str:
+    """Generate task ID based on date (MM-DD format).
+
+    Returns:
+        Date prefix string (e.g., "01-21").
+    """
+    return datetime.now().strftime("%m-%d")
+
+
+# =============================================================================
+# Monorepo / Package Paths
+# =============================================================================
+
+
+def get_spec_dir(package: str | None = None, repo_root: Path | None = None) -> Path:
+    """Get the spec directory path.
+
+    Single-repo: .trellis/spec
+    Monorepo with package: .trellis/spec/<package>
+
+    Uses lazy import to avoid circular dependency with config.py.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    from .config import get_spec_base
+
+    base = get_spec_base(package, repo_root)
+    return repo_root / DIR_WORKFLOW / base
+
+
+def get_package_path(package: str, repo_root: Path | None = None) -> Path | None:
+    """Get a package's source directory absolute path from config.
+
+    Returns:
+        Absolute path to the package directory, or None if not found.
+    """
+    if repo_root is None:
+        repo_root = get_repo_root()
+
+    from .config import get_packages
+
+    packages = get_packages(repo_root)
+    if not packages or package not in packages:
+        return None
+
+    info = packages[package]
+    if isinstance(info, dict):
+        rel_path = info.get("path", package)
+    else:
+        rel_path = str(info)
+
+    return repo_root / rel_path
+
+
+# =============================================================================
+# Main Entry (for testing)
+# =============================================================================
+
+if __name__ == "__main__":
+    repo = get_repo_root()
+    print(f"Repository root: {repo}")
+    print(f"Developer: {get_developer(repo)}")
+    print(f"Tasks dir: {get_tasks_dir(repo)}")
+    print(f"Workspace dir: {get_workspace_dir(repo)}")
+    print(f"Journal file: {get_active_journal_file(repo)}")
+    print(f"Current task: {get_current_task(repo)}")