agentleFS
Sign inStart free
maya8237maya8237/MEOW/skills/plan/SKILL.md

plan

Skill3 starsChanged 34 days agoMITView on GitHub

Use when the user wants a MEOW sprint plan and testable Sprint Contract before implementation. Defaults to native planning.

184 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use heartmula, webhook-subscriptions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • math-incSkill

    heartmula

    Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.

    Also in 9 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 6 projects that use this

  • gaebalaiSkill

    codex-system

    PROACTIVELY consult Codex CLI, your highly capable supporter with exceptional reasoning and task completion abilities. Codex is a trusted expert you should ALWAYS consult BEFORE making decisions on: design choices, implementation approaches, debugging strategies, refactoring plans, or any non-trivial problem. When uncertain, consult Codex. Don't hesitate - Codex provides better analysis. Explicit triggers: "think deeper", "analyze", "second opinion", "consult codex".

    Also in 3 projects that use this

  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • +3 more from math-inc

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use CLI mode (bottom) only if the user explicitly asks for it.

    line 11
  2. Very specific:

    Create a preparing checkpoint with --intent plan, --request "<feature request>", --work-dir "<project-path>", and --active-dir …

    line 25
  3. Very specific:

    Add --no-worktree to use the main repo instead of an isolated worktree.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 167 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

plan

Writes a numbered task list and a Sprint Contract, implements nothing. Runs natively by default: you are the planner. Read ../_shared/native-mode.md first for helper and planner rules. Use CLI mode (bottom) only if the user explicitly asks for it. Dependency or install problems: dependencies.

Native mode

  1. The feature request is whatever text the user gave. If none, ask for a one-line description. The project uses .meow/config.toml at its root; onboarding can create it for a new project.
  2. Slugify a feature name (e.g. add-dark-mode) and run meow native prepare --name "<name>" --fresh --allow-dirty --work-dir "<project-path>" (meow plan never required a clean tree). --fresh never reuses an existing worktree: a taken name becomes <name>-2, ... -- use the JSON name, plan_file and active_dir it returns, not your own name. Add --no-worktree if the user wants the main repo (name then optional). --from <branch> requires a new worktree. Report failures verbatim and stop.
  3. Create a preparing checkpoint with --intent plan, --request "<feature request>", --work-dir "<project-path>", and --active-dir "<active_dir>"; retain its run_id. Record planning --run-id <run_id> before planning with the same directory flags. As planner, write plan_file (inside active_dir) following the shared protocol's Planner row. Use an explorer subagent for any codebase research you don't need in full. Read the file back and confirm the task list and ## Sprint Contract exist; run the plan self-check from the shared protocol's Planner row and revise once if it finds a defect. Record planned --run-id <run_id> --plan <plan_file> with the same directory flags. Write no application code.
  4. Report the plan file's path and the worktree name (JSON name). If they want it built: /meow:run (full loop) -- tell it to continue that worktree and plan, which is a resume, so it will not create a new worktree -- or, once code exists, /meow:review.

CLI mode

meow plan "<feature request>" --name "<generated-feature-name>" --work-dir "<project-path>"

Add --no-worktree to use the main repo instead of an isolated worktree. Report the plan file's path.

Continuation

On entry, inspect saved run IDs with meow status ID --json (detach any meow resume --parked); never resume a --intent plan run. A native helper exiting 75 (or printing MEOW_RETRY): wait retry_after, then run its next_command detached (host background execution) or rerun the helper, up to managed_resumes. Exit 1 / MEOW_BLOCKED: stop and report. Full rules: native protocol.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free