From compound-engineering
Batch-resolves approved 'ready' todos: scans directories, plans parallel execution with dependencies, commits changes, documents lessons learned, cleans up files. Reports skipped pendings.
npx claudepluginhub everyinc/compound-engineering-plugin --plugin compound-engineeringThis skill uses the workspace's default tool permissions.
Resolve approved todos using parallel processing, document lessons learned, then clean up.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Resolve approved todos using parallel processing, document lessons learned, then clean up.
Only ready todos are resolved. pending todos are skipped — they haven't been triaged yet. If pending todos exist, list them at the end so the user knows what was left behind.
Scan .context/compound-engineering/todos/*.md and legacy todos/*.md. Partition by status:
ready (status field or -ready- in filename): resolve these.pending: skip. Report them at the end.complete: ignore, already done.If a specific todo ID or pattern was passed as an argument, filter to matching todos only (still must be ready).
Residual actionable work from ce:review mode:autofix after its safe_auto pass will already be ready.
Skip any todo that recommends deleting, removing, or gitignoring files in docs/brainstorms/, docs/plans/, or docs/solutions/ — these are intentional pipeline artifacts.
Create a task list grouped by type (e.g., TaskCreate in Claude Code, update_plan in Codex). Analyze dependencies -- items that others depend on run first. Output a mermaid diagram showing execution order and parallelism.
Spawn a compound-engineering:workflow:pr-comment-resolver agent per item. Prefer parallel; fall back to sequential respecting dependency order.
Batching: 1-4 items: direct parallel returns. 5+ items: batches of 4, each returning only a short status summary (todo handled, files changed, tests run/skipped, blockers).
For large sets, use a scratch directory at .context/compound-engineering/todo-resolve/<run-id>/ for per-resolver artifacts. Return only completion summaries to parent.
Commit changes, mark todos resolved, push to remote.
GATE: STOP. Verify todos resolved and changes committed before proceeding.
Load the ce:compound skill to document what was learned. Todo resolutions often surface patterns and architectural insights worth capturing.
GATE: STOP. Verify the compound skill produced a solution document in docs/solutions/. If none (user declined or no learnings), continue.
Delete completed/resolved todo files from both paths. If a scratch directory was created at .context/compound-engineering/todo-resolve/<run-id>/, delete it (unless user asked to inspect).
Todos resolved: [count]
Pending (skipped): [count, or "none"]
Lessons documented: [path to solution doc, or "skipped"]
Todos cleaned up: [count deleted]
If pending todos were skipped, list them:
Skipped pending todos (run /todo-triage to approve):
- 003-pending-p2-missing-index.md
- 005-pending-p3-rename-variable.md