agentleFS
huntiehuntie/skills/plan/SKILL.md

plan

Skill0 starsChanged 21 days agoMITView on GitHub

Write a numbered plan under vault/plans/ for work the user wants planned before it is built. Planning only, never implementation. Use only when the user invokes /plan or asks for a plan.

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

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

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read vault/README.md for the layout and conventions, then vault/index.md.

    line 14
  2. Very specific:

    Write overview.md per the README's numbering, naming, Branch:, and Status: conventions.

    line 18
  3. Distinctive:

    Every step is a box naming its evidence, per the README, ordered riskiest unknown first with scaffold and verification before features, and …

    line 19
  4. Distinctive:

    Every alternative weighed is named with the reason it lost.

    line 20
  5. Very specific:

    Add the checkbox to vault/index.md and commit.

    line 24

“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

This is the write path into vault/ for plans. You own the plan, not the code: do not implement, and stop once it is written and presented.

  1. Read vault/README.md for the layout and conventions, then vault/index.md. Read each touched repo's decisions.md and lessons, which are binding constraints, and any plan that overlaps.
  2. Frame before exploring. State done as a falsifiable predicate a reviewer can check on the real artifact. Quantify the scope in rough units. Pick the rigor: a one-way door or a wide blast radius gets gates and evidence, a reversible step gets less.
  3. Settle open questions by running, not asking. A question about behavior, timing, layout, or whether an API works is answered by a throwaway prototype, and the plan records the result. Ask the user only a product or preference call no run can settle, with concrete options. When nobody can answer, write the assumption into the plan.
  4. Explore the affected code, its conventions, tests, and verification commands, delegating to subagents where available. Each checkout's own CLAUDE.md or AGENTS.md applies.
  5. Write overview.md per the README's numbering, naming, Branch:, and Status: conventions; the branch is what scripts/checkout <owner/repo>@<name> --new will create. Scrutinize each part against these, in order:
    • Every step is a box naming its evidence, per the README, ordered riskiest unknown first with scaffold and verification before features, and each lands on its own.
    • Every alternative weighed is named with the reason it lost. No reason, no mention.
    • A design plan writes the caller's usage first and derives the shape from it; the shape never overrides the usage.
    • Risks are listed with the step they land in. Nothing in it is code: name types, functions, and files for a senior engineer, not a compiler.
    • Anything the code or an existing note already says is a link to it, not a restatement.
  6. Add the checkbox to vault/index.md and commit. Add files beside the overview only when they have content.

End with a short summary: the predicate, the steps, the branch, what the prototypes settled and what stays open, and where the overview is.

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.