john/claude-engineering-plugin
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

refactor: consolidate todo storage under .context/compound-engineering/todos/ (#361)

Browse Source
This commit is contained in:
Trevin Chow
2026-03-24 09:54:30 -07:00
committed by GitHub
parent 18d22afde2
commit 65e5621dbe
11 changed files with 306 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
plugins/compound-engineering/skills/ce-review-beta/SKILL.md
View File

@@ -32,13 +32,13 @@ Check `$ARGUMENTS` for `mode:autonomous` or `mode:report-only`. If either token
- **Skip all user questions.** Never pause for approval or clarification once scope has been established.
- **Apply only `safe_auto -> review-fixer` findings.** Leave `gated_auto`, `manual`, `human`, and `release` work unresolved.
- **Write a run artifact** under `.context/compound-engineering/ce-review-beta/<run-id>/` summarizing findings, applied fixes, residual actionable work, and advisory outputs.
- **Create durable `todos/` items only for unresolved actionable findings** whose final owner is `downstream-resolver`.
- **Create durable todo files only for unresolved actionable findings** whose final owner is `downstream-resolver`. Load the `file-todos` skill for the canonical directory path and naming convention.
- **Never commit, push, or create a PR** from autonomous mode. Parent workflows own those decisions.
### Report-only mode rules
- **Skip all user questions.** Infer intent conservatively if the diff metadata is thin.
- **Never edit files or externalize work.** Do not write `.context/compound-engineering/ce-review-beta/<run-id>/`, do not create `todos/`, and do not commit, push, or create a PR.
- **Never edit files or externalize work.** Do not write `.context/compound-engineering/ce-review-beta/<run-id>/`, do not create todo files, and do not commit, push, or create a PR.
- **Safe for parallel read-only verification.** `mode:report-only` is the only mode that is safe to run concurrently with browser testing on the same checkout.
- **Do not switch the shared checkout.** If the caller passes an explicit PR or branch target, `mode:report-only` must run in an isolated checkout/worktree or stop instead of running `gh pr checkout` / `git checkout`.
- **Do not overlap mutating review with browser testing on the same checkout.** If a future orchestrator wants fixes, run the mutating review phase after browser testing or in an isolated checkout/worktree.
@@ -476,7 +476,7 @@ After presenting findings and verdict (Stage 6), route the next steps by mode. R
- applied fixes
- residual actionable work
- advisory-only outputs
- In autonomous mode, create durable `todos/` items only for unresolved actionable findings whose final owner is `downstream-resolver`. Load the `file-todos` skill for the naming convention, YAML frontmatter structure, and template. Each todo should map the finding's severity to the todo priority (`P0`/`P1` -> `p1`, `P2` -> `p2`, `P3` -> `p3`) and set `status: ready` since these findings have already been triaged by synthesis.
- In autonomous mode, create durable todo files only for unresolved actionable findings whose final owner is `downstream-resolver`. Load the `file-todos` skill for the canonical directory path, naming convention, YAML frontmatter structure, and template. Each todo should map the finding's severity to the todo priority (`P0`/`P1` -> `p1`, `P2` -> `p2`, `P3` -> `p3`) and set `status: ready` since these findings have already been triaged by synthesis.
- Do not create todos for `advisory` findings, `owner: human`, `owner: release`, or protected-artifact cleanup suggestions.
- If only advisory outputs remain, create no todos.
- Interactive mode may offer to externalize residual actionable work after fixes, but it is not required to finish the review.

12
plugins/compound-engineering/skills/ce-review/SKILL.md
View File

@@ -241,7 +241,7 @@ Run the Task compound-engineering:review:code-simplicity-reviewer() to see if we
### 5. Findings Synthesis and Todo Creation Using file-todos Skill
<critical_requirement> ALL findings MUST be stored in the todos/ directory using the file-todos skill. Create todo files immediately after synthesis - do NOT present findings for user approval first. Use the skill for structured todo management. </critical_requirement>
<critical_requirement> ALL findings MUST be stored as todo files using the file-todos skill. Load the `file-todos` skill for the canonical directory path, naming convention, and template. Create todo files immediately after synthesis - do NOT present findings for user approval first. </critical_requirement>
#### Step 1: Synthesize All Findings
@@ -272,7 +272,7 @@ Remove duplicates, prioritize by severity and impact.
- Create todo files directly using Write tool
- All findings in parallel for speed
- Use standard template from `.claude/skills/file-todos/assets/todo-template.md`
- Use standard template from the `file-todos` skill's [todo-template.md](../file-todos/assets/todo-template.md)
- Follow naming convention: `{issue_id}-pending-{priority}-{description}.md`
**Option B: Sub-Agents in Parallel (Recommended for Scale)** For large PRs with 15+ findings, use sub-agents to create finding files in parallel:
@@ -320,7 +320,7 @@ Sub-agents can:
The skill provides:
- Template location: `.claude/skills/file-todos/assets/todo-template.md`
- Template location: the `file-todos` skill's [todo-template.md](../file-todos/assets/todo-template.md)
- Naming convention: `{issue_id}-{status}-{priority}-{description}.md`
- YAML frontmatter structure: status, priority, issue_id, tags, dependencies
- All required sections: Problem Statement, Findings, Solutions, etc.
@@ -340,7 +340,7 @@ Sub-agents can:
004-pending-p3-unused-parameter.md
```
5. Follow template structure from file-todos skill: `.claude/skills/file-todos/assets/todo-template.md`
5. Follow template structure from file-todos skill: the `file-todos` skill's [todo-template.md](../file-todos/assets/todo-template.md)
**Todo File Structure (from template):**
@@ -432,7 +432,7 @@ After creating all todo files, present comprehensive summary:
2. **Triage All Todos**:
```bash
ls todos/*-pending-*.md # View all pending todos
ls .context/compound-engineering/todos/*-pending-*.md todos/*-pending-*.md 2>/dev/null # View all pending todos
/triage # Use slash command for interactive triage
```
@@ -445,7 +445,7 @@ After creating all todo files, present comprehensive summary:
4. **Track Progress**:
- Rename file when status changes: pending → ready → complete
- Update Work Log as you work
- Commit todos: `git add todos/ && git commit -m "refactor: add code review findings"`
- Commit review findings and status updates
### Severity Breakdown:

2
plugins/compound-engineering/skills/deepen-plan-beta/SKILL.md
View File

@@ -382,7 +382,7 @@ If the user explicitly requests a separate file, append `-deepened` before `.md`
- `docs/plans/2026-03-15-001-feat-example-plan-deepened.md`
If artifact-backed mode was used and the user did not ask to inspect the scratch files:
- clean up the temporary scratch directory after the plan is safely written
- delete the specific per-run scratch directory (e.g., `.context/compound-engineering/deepen-plan-beta/<run-id>/`) after the plan is safely written. Do not delete any other `.context/` subdirectories.
- if cleanup is not practical on the current platform, say where the artifacts were left and that they are temporary workflow output
## Post-Enhancement Options

167
plugins/compound-engineering/skills/file-todos/SKILL.md
View File

@@ -1,6 +1,6 @@
---
name: file-todos
description: This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.
description: This skill should be used when managing the file-based todo tracking system in the .context/compound-engineering/todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with code review processes.
disable-model-invocation: true
---
@@ -8,26 +8,35 @@ disable-model-invocation: true
## Overview
The `todos/` directory contains a file-based tracking system for managing code review feedback, technical debt, feature requests, and work items. Each todo is a markdown file with YAML frontmatter and structured sections.
The `.context/compound-engineering/todos/` directory contains a file-based tracking system for managing code review feedback, technical debt, feature requests, and work items. Each todo is a markdown file with YAML frontmatter and structured sections.
> **Legacy support:** During the transition period, always check both `.context/compound-engineering/todos/` (canonical) and `todos/` (legacy) when reading or searching for todos. Write new todos only to the canonical path. Unlike per-run scratch directories, `.context/compound-engineering/todos/` has a multi-session lifecycle -- do not clean it up as part of post-run scratch cleanup.
This skill should be used when:
- Creating new todos from findings or feedback
- Managing todo lifecycle (pending → ready → complete)
- Managing todo lifecycle (pending -> ready -> complete)
- Triaging pending items for approval
- Checking or managing dependencies
- Converting PR comments or code findings into tracked work
- Updating work logs during todo execution
## File Naming Convention
## Directory Paths
Todo files follow this naming pattern:
| Purpose | Path |
|---------|------|
| **Canonical (write here)** | `.context/compound-engineering/todos/` |
| **Legacy (read-only)** | `todos/` |
When searching or listing todos, always search both paths. When creating new todos, always write to the canonical path.
## File Naming Convention
```
{issue_id}-{status}-{priority}-{description}.md
```
**Components:**
- **issue_id**: Sequential number (001, 002, 003...) - never reused
- **issue_id**: Sequential number (001, 002, 003...) -- never reused
- **status**: `pending` (needs triage), `ready` (approved), `complete` (done)
- **priority**: `p1` (critical), `p2` (important), `p3` (nice-to-have)
- **description**: kebab-case, brief description
@@ -44,17 +53,17 @@ Todo files follow this naming pattern:
Each todo is a markdown file with YAML frontmatter and structured sections. Use the template at [todo-template.md](./assets/todo-template.md) as a starting point when creating new todos.
**Required sections:**
- **Problem Statement** - What is broken, missing, or needs improvement?
- **Findings** - Investigation results, root cause, key discoveries
- **Proposed Solutions** - Multiple options with pros/cons, effort, risk
- **Recommended Action** - Clear plan (filled during triage)
- **Acceptance Criteria** - Testable checklist items
- **Work Log** - Chronological record with date, actions, learnings
- **Problem Statement** -- What is broken, missing, or needs improvement?
- **Findings** -- Investigation results, root cause, key discoveries
- **Proposed Solutions** -- Multiple options with pros/cons, effort, risk
- **Recommended Action** -- Clear plan (filled during triage)
- **Acceptance Criteria** -- Testable checklist items
- **Work Log** -- Chronological record with date, actions, learnings
**Optional sections:**
- **Technical Details** - Affected files, related components, DB changes
- **Resources** - Links to errors, tests, PRs, documentation
- **Notes** - Additional context or decisions
- **Technical Details** -- Affected files, related components, DB changes
- **Resources** -- Links to errors, tests, PRs, documentation
- **Notes** -- Additional context or decisions
**YAML frontmatter fields:**
```yaml
@@ -69,20 +78,21 @@ dependencies: ["001"] # Issue IDs this is blocked by
## Common Workflows
> **Tool preference:** Use native file-search (e.g., Glob in Claude Code) and content-search (e.g., Grep in Claude Code) tools instead of shell commands for finding and reading todo files. This avoids unnecessary permission prompts in sub-agent workflows. Use shell only for operations that have no native equivalent (e.g., `mv` for renames, `mkdir -p` for directory creation).
### Creating a New Todo
**To create a new todo from findings or feedback:**
1. Determine next issue ID: `ls todos/ | grep -o '^[0-9]\+' | sort -n | tail -1`
2. Copy template: `cp assets/todo-template.md todos/{NEXT_ID}-pending-{priority}-{description}.md`
3. Edit and fill required sections:
1. Ensure directory exists: `mkdir -p .context/compound-engineering/todos/`
2. Determine next issue ID by searching both canonical and legacy paths for files matching `[0-9]*-*.md` using the native file-search/glob tool. Extract the numeric prefix from each filename, find the highest, and increment by one. Zero-pad to 3 digits (e.g., `007`).
3. Read the template at [todo-template.md](./assets/todo-template.md), then write it to `.context/compound-engineering/todos/{NEXT_ID}-pending-{priority}-{description}.md` using the native file-write tool.
4. Edit and fill required sections:
- Problem Statement
- Findings (if from investigation)
- Proposed Solutions (multiple options)
- Acceptance Criteria
- Add initial Work Log entry
4. Determine status: `pending` (needs triage) or `ready` (pre-approved)
5. Add relevant tags for filtering
5. Determine status: `pending` (needs triage) or `ready` (pre-approved)
6. Add relevant tags for filtering
**When to create a todo:**
- Requires more than 15-20 minutes of work
@@ -101,21 +111,19 @@ dependencies: ["001"] # Issue IDs this is blocked by
### Triaging Pending Items
**To triage pending todos:**
1. List pending items: `ls todos/*-pending-*.md`
1. Find pending items using the native file-search/glob tool with pattern `*-pending-*.md` in both directory paths.
2. For each todo:
- Read Problem Statement and Findings
- Review Proposed Solutions
- Make decision: approve, defer, or modify priority
3. Update approved todos:
- Rename file: `mv {file}-pending-{pri}-{desc}.md {file}-ready-{pri}-{desc}.md`
- Update frontmatter: `status: pending` → `status: ready`
- Update frontmatter: `status: pending` -> `status: ready`
- Fill "Recommended Action" section with clear plan
- Adjust priority if different from initial assessment
4. Deferred todos stay in `pending` status
**Use slash command:** `/triage` for interactive approval workflow
Load the `triage` skill for an interactive approval workflow.
### Managing Dependencies
@@ -126,31 +134,20 @@ dependencies: ["002", "005"] # This todo blocked by issues 002 and 005
dependencies: [] # No blockers - can work immediately
```
**To check what blocks a todo:**
```bash
grep "^dependencies:" todos/003-*.md
```
**To check what blocks a todo:** Use the native content-search tool (e.g., Grep in Claude Code) to search for `^dependencies:` in the todo file.
**To find what a todo blocks:**
```bash
grep -l 'dependencies:.*"002"' todos/*.md
```
**To find what a todo blocks:** Search both directory paths for files containing `dependencies:.*"002"` using the native content-search tool.
**To verify blockers are complete before starting:**
```bash
for dep in 001 002 003; do
[ -f "todos/${dep}-complete-*.md" ] || echo "Issue $dep not complete"
done
```
**To verify blockers are complete before starting:** For each dependency ID, use the native file-search/glob tool to look for `{dep_id}-complete-*.md` in both directory paths. Any missing matches indicate incomplete blockers.
### Updating Work Logs
**When working on a todo, always add a work log entry:**
When working on a todo, always add a work log entry:
```markdown
### YYYY-MM-DD - Session Title
**By:** Claude Code / Developer Name
**By:** Agent name / Developer Name
**Actions:**
- Specific changes made (include file:line references)
@@ -172,82 +169,62 @@ Work logs serve as:
### Completing a Todo
**To mark a todo as complete:**
1. Verify all acceptance criteria checked off
2. Update Work Log with final session and results
3. Rename file: `mv {file}-ready-{pri}-{desc}.md {file}-complete-{pri}-{desc}.md`
4. Update frontmatter: `status: ready` → `status: complete`
5. Check for unblocked work: `grep -l 'dependencies:.*"002"' todos/*-ready-*.md`
4. Update frontmatter: `status: ready` -> `status: complete`
5. Check for unblocked work: search both directory paths for `*-ready-*.md` files containing `dependencies:.*"{issue_id}"` using the native content-search tool
6. Commit with issue reference: `feat: resolve issue 002`
## Integration with Development Workflows
| Trigger | Flow | Tool |
|---------|------|------|
| Code review | `/ce:review` → Findings → `/triage` → Todos | Review agent + skill |
| Beta autonomous review | `/ce:review-beta mode:autonomous` → Downstream-resolver residual todos → `/resolve-todo-parallel` | Review skill + todos |
| PR comments | `/resolve_pr_parallel` → Individual fixes → Todos | gh CLI + skill |
| Code TODOs | `/resolve-todo-parallel` → Fixes + Complex todos | Agent + skill |
| Planning | Brainstorm → Create todo → Work → Complete | Skill |
| Feedback | Discussion → Create todo → Triage → Work | Skill + slash |
| Code review | `/ce:review` -> Findings -> `/triage` -> Todos | Review agent + skill |
| Beta autonomous review | `/ce:review-beta mode:autonomous` -> Downstream-resolver residual todos -> `/resolve-todo-parallel` | Review skill + todos |
| PR comments | `/resolve_pr_parallel` -> Individual fixes -> Todos | gh CLI + skill |
| Code TODOs | `/resolve-todo-parallel` -> Fixes + Complex todos | Agent + skill |
| Planning | Brainstorm -> Create todo -> Work -> Complete | Skill |
| Feedback | Discussion -> Create todo -> Triage -> Work | Skill |
## Quick Reference Commands
## Quick Reference Patterns
Use the native file-search/glob tool (e.g., Glob in Claude Code) and content-search tool (e.g., Grep in Claude Code) for these operations. Search both canonical and legacy directory paths.
**Finding work:**
```bash
# List highest priority unblocked work
grep -l 'dependencies: \[\]' todos/*-ready-p1-*.md
# List all pending items needing triage
ls todos/*-pending-*.md
# Find next issue ID
ls todos/ | grep -o '^[0-9]\+' | sort -n | tail -1 | awk '{printf "%03d", $1+1}'
# Count by status
for status in pending ready complete; do
echo "$status: $(ls -1 todos/*-$status-*.md 2>/dev/null | wc -l)"
done
```
| Goal | Tool | Pattern |
|------|------|---------|
| List highest priority unblocked work | Content-search | `dependencies: \[\]` in `*-ready-p1-*.md` |
| List all pending items needing triage | File-search | `*-pending-*.md` |
| Find next issue ID | File-search | `[0-9]*-*.md`, extract highest numeric prefix |
| Count by status | File-search | `*-pending-*.md`, `*-ready-*.md`, `*-complete-*.md` |
**Dependency management:**
```bash
# What blocks this todo?
grep "^dependencies:" todos/003-*.md
# What does this todo block?
grep -l 'dependencies:.*"002"' todos/*.md
```
| Goal | Tool | Pattern |
|------|------|---------|
| What blocks this todo? | Content-search | `^dependencies:` in the specific todo file |
| What does this todo block? | Content-search | `dependencies:.*"{id}"` across all todo files |
**Searching:**
```bash
# Search by tag
grep -l "tags:.*rails" todos/*.md
# Search by priority
ls todos/*-p1-*.md
# Full-text search
grep -r "payment" todos/
```
| Goal | Tool | Pattern |
|------|------|---------|
| Search by tag | Content-search | `tags:.*{tag}` across all todo files |
| Search by priority | File-search | `*-p1-*.md` (or p2, p3) |
| Full-text search | Content-search | `{keyword}` across both directory paths |
## Key Distinctions
**File-todos system (this skill):**
- Markdown files in `todos/` directory
- Development/project tracking
- Markdown files in `.context/compound-engineering/todos/` (legacy: `todos/`)
- Development/project tracking across sessions and agents
- Standalone markdown files with YAML frontmatter
- Used by humans and agents
- Persisted to disk, cross-agent accessible
**Rails Todo model:**
- Database model in `app/models/todo.rb`
- User-facing feature in the application
- Active Record CRUD operations
- Different from this file-based system
**TodoWrite tool:**
**In-session task tracking (e.g., TaskCreate/TaskUpdate in Claude Code, update_plan in Codex):**
- In-memory task tracking during agent sessions
- Temporary tracking for single conversation
- Not persisted to disk
- Different from both systems above
- Not persisted to disk after session ends
- Different purpose: use for tracking steps within a session, not for durable cross-session work items

6
plugins/compound-engineering/skills/resolve-todo-parallel/SKILL.md
View File

@@ -10,7 +10,7 @@ Resolve all TODO comments using parallel processing, document lessons learned, t
### 1. Analyze
Get all unresolved TODOs from the /todos/*.md directory
Get all unresolved TODOs from `.context/compound-engineering/todos/*.md` and legacy `todos/*.md`
Residual actionable work may come from `ce:review-beta mode:autonomous` after its in-skill `safe_auto` pass. Treat those todos as normal unresolved work items; the review skill has already decided they should not be auto-fixed inline.
@@ -54,9 +54,9 @@ GATE: STOP. Verify that the compound skill produced a solution document in `docs
### 6. Clean Up Completed Todos
List all todos and identify those with `done` or `resolved` status, then delete them to keep the todo list clean and actionable.
Search both `.context/compound-engineering/todos/` and legacy `todos/` for files with `done`, `resolved`, or `complete` status, then delete them to keep the todo list clean and actionable.
If a scratch directory was used and the user did not ask to inspect it, clean it up after todo cleanup succeeds.
If a per-run scratch directory was created at `.context/compound-engineering/resolve-todo-parallel/<run-id>/`, and the user did not ask to inspect it, delete that specific `<run-id>/` directory after todo cleanup succeeds. Do not delete any other `.context/` subdirectories.
After cleanup, output a summary:

4
plugins/compound-engineering/skills/test-browser/SKILL.md
View File

@@ -225,12 +225,12 @@ When a test fails:
How to proceed?
1. Fix now - I'll help debug and fix
2. Create todo - Add to todos/ for later
2. Create todo - Add a todo for later (using the file-todos skill)
3. Skip - Continue testing other pages
```
3. **If "Fix now":** investigate, propose a fix, apply, re-run the failing test
4. **If "Create todo":** create `{id}-pending-p1-browser-test-{description}.md`, continue
4. **If "Create todo":** load the `file-todos` skill and create a todo with priority p1 and description `browser-test-{description}`, continue
5. **If "Skip":** log as skipped, continue
### 10. Test Summary

4
plugins/compound-engineering/skills/test-xcode/SKILL.md
View File

@@ -139,12 +139,12 @@ When a test fails:
How to proceed?
1. Fix now - I'll help debug and fix
2. Create todo - Add to todos/ for later
2. Create todo - Add a todo for later (using the file-todos skill)
3. Skip - Continue testing other screens
```
3. **If "Fix now":** investigate, propose a fix, rebuild and retest
4. **If "Create todo":** create `{id}-pending-p1-xcode-{description}.md`, continue
4. **If "Create todo":** load the `file-todos` skill and create a todo with priority p1 and description `xcode-{description}`, continue
5. **If "Skip":** log as skipped, continue
### 8. Test Summary

14
plugins/compound-engineering/skills/triage/SKILL.md
View File

@@ -6,7 +6,7 @@ disable-model-invocation: true
---
- First set the /model to Haiku
- Then read all pending todos in the todos/ directory
- Then read all pending todos from `.context/compound-engineering/todos/` and legacy `todos/` directories
Present all findings, decisions, or issues here one by one for triage. The goal is to go through each item and decide whether to add it to the CLI todo system.
@@ -149,7 +149,7 @@ Do you want to add this to the todo list?
**When user says "next":**
- **Delete the todo file** - Remove it from todos/ directory since it's not relevant
- **Delete the todo file** - Remove it from its current location since it's not relevant
- Skip to the next item
- Track skipped items for summary
@@ -182,22 +182,22 @@ After all items processed:
### Skipped Items (Deleted):
- Item #5: [reason] - Removed from todos/
- Item #12: [reason] - Removed from todos/
- Item #5: [reason] - Removed
- Item #12: [reason] - Removed
### Summary of Changes Made:
During triage, the following status updates occurred:
- **Pending → Ready:** Filenames and frontmatter updated to reflect approved status
- **Deleted:** Todo files for skipped findings removed from todos/ directory
- **Deleted:** Todo files for skipped findings removed
- Each approved file now has `status: ready` in YAML frontmatter
### Next Steps:
1. View approved todos ready for work:
```bash
ls todos/*-ready-*.md
ls .context/compound-engineering/todos/*-ready-*.md todos/*-ready-*.md 2>/dev/null
```
````
@@ -272,7 +272,7 @@ Do you want to add this to the todo list?
4. Confirm: "✅ Approved: `{filename}` (Issue #{issue_id}) - Status: **ready**"
**When "next" is selected:**
1. Delete the todo file from todos/ directory
1. Delete the todo file from its current location
2. Skip to next item
3. No file remains in the system