Coordinate large migrations, refactors, and bulk renames by splitting them into independent tasks. After plan approval, 5–30 agents work in separate Git worktrees, isolated working directories, then review, test, and open a pull request for each task.
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
Review the instructions the agent will receive before you install.
You are orchestrating a large, parallelizable change across this codebase.
$ARGUMENTS
Call the EnterPlanMode tool now to enter plan mode, then:
Understand the scope. Launch one or more subagents (in the foreground — you need their results) to deeply research what this instruction touches. Find all the files, patterns, and call sites that need to change. Understand the existing conventions so the migration is consistent.
Decompose into independent units. Break the work into 5–30 self-contained units. Each unit must:
Scale the count to the actual work: few files → closer to 5; hundreds of files → closer to 30. Prefer per-directory or per-module slicing over arbitrary file lists.
Determine the e2e test recipe. Figure out how a worker can verify its change actually works end-to-end — not just that unit tests pass. Look for:
claude-in-chrome skill or browser-automation tool (for UI changes: click through the affected flow, screenshot the result)tmux or CLI-verifier skill (for CLI changes: launch the app interactively, exercise the changed behavior)If you cannot find a concrete e2e path, use the AskUserQuestion tool to ask the user how to verify this change end-to-end. Offer 2–3 specific options based on what you found (e.g., "Screenshot via chrome extension", "Run bun run dev and curl the endpoint", "No e2e — unit tests are sufficient"). Do not skip this — the workers cannot ask the user themselves.
Write the recipe as a short, concrete set of steps that a worker can execute autonomously. Include any setup (start a dev server, build first) and the exact command/interaction to verify.
Write the plan. In your plan file, include:
Call ExitPlanMode to present the plan for approval.
Once the plan is approved, spawn one background agent per work unit using the Agent tool. All agents must use isolation: "worktree" and run_in_background: true. Launch them all in a single message block so they run in parallel.
For each agent, the prompt must be fully self-contained. Include:
After you finish implementing the change:
1. **Code review** — Invoke the `Skill` tool with `skill: "code-review"` to find correctness bugs (it reports findings; it does not edit code). Fix any findings it surfaces before continuing.
2. **Run unit tests** — Run the project's test suite (check for package.json scripts, Makefile targets, or common commands like `npm test`, `bun test`, `pytest`, `go test`). If tests fail, fix them.
3. **Test end-to-end** — Follow the e2e test recipe from the coordinator's prompt (below). If the recipe says to skip e2e for this unit, skip it.
4. **Commit and push** — Commit all changes with a clear message, push the branch, and create a PR with `gh pr create`. Use a descriptive title. If `gh` is not available or the push fails, note it in your final message.
5. **Report** — End with a single line: `PR: <url>` so the coordinator can track it. If no PR was created, end with `PR: none — <reason>`.
Use subagent_type: "general-purpose" unless a more specific agent type fits.
After launching all workers, render an initial status table:
| # | Unit | Status | PR |
|---|---|---|---|
| 1 | <title> | running | — |
| 2 | <title> | running | — |
As background-agent completion notifications arrive, parse the PR: <url> line from each agent's result and re-render the table with updated status (done / failed) and PR links. Keep a brief failure note for any agent that did not produce a PR.
When all agents have reported, render the final table and a one-line summary (e.g., "22/24 units landed as PRs").
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create a 3D object with three.js, inspect it from every angle in an interactive viewer, and download it as OBJ + MTL or GLB for use in other 3D applications.
Maintain a private task list with deadlines, next steps, waiting parties, and blockers. Update progress and dependencies, merge duplicate items, and archive closed tasks so ongoing commitments stay clear and easy to follow.
Coordinate a task from a verifiable goal through completion. Handle work directly or split independent tasks across separate agent sessions, track progress, verify results, and arrange pull request merging when included in the goal.
Create animated HTML pages with smooth scene transitions and playback controls. An editable timeline lets users adjust scene lengths and speeds, with fixed landscape or portrait layouts prepared for video export.
Review synced Apple Health records, including steps, heart rate, sleep, and workouts. Retrieve daily summaries or detailed samples for a chosen period, and check sync status and missing data before interpreting the results.
Create and edit Word documents and templates, reorganize text, replace images, and work with tracked changes or comments. Apply proper headings and lists, then render every page to check its appearance before delivery.