agentleFS
xiaolongnkxiaolongnk/SuperHarness/skills/plan/SKILL.md

plan

Skill4 starsChanged 48 days agoMITView on GitHub

Turns a request into a short written plan — problem, risks, phases, tasks — before any code is written.

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

Files
SKILL.md

Plan skill

When to use

Invoke for any multi-step task: a feature, a non-trivial bug fix, a refactor, anything where the steps aren't obvious in one line. Plan first, then execute against the plan.

Skip for genuinely trivial one-liners (a typo, a one-line config change) where writing a plan costs more than the change. For a big or risky feature, get the plan reviewed before implementing.

Steps

  1. Restate the request in your own words. One or two sentences. If your restatement and the request disagree, you've found a misunderstanding — resolve it before planning further.
  2. State the problem. What are we actually solving, and for whom? Name the user-visible outcome that means "done."
  3. List the risks and unknowns. What could go wrong, what's uncertain, what might break that's adjacent. Flag anything you'd want a second opinion on. An honest risk list now saves a rewrite later.
  4. Break the work into ordered phases. Each phase is independently checkable — you can stop after it and have something coherent. Order them so the riskiest or most uncertain phase comes early, where a wrong assumption is cheap to correct.
  5. List the concrete tasks inside each phase. Specific enough to execute without re-deciding: which file, which function, what behavior. Note where tests drive the work (write the failing test first).
  6. Define done. The observable outcome and the check that proves it (a test, a command, a behavior in the running app) — this becomes the acceptance bar for /verify.
  7. Write the plan down (a short doc or the task board) and, for a big feature, hand it to a fresh-context reviewer before any code. Record the agreed plan so the implementer executes it rather than re-improvising.

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.