agentleFS
PeanutGTPeanutGT/NutsSkills/skills/plan/SKILL.md

plan

Skill3 starsChanged 18 days agoApache-2.0View on GitHub

Use when work has more than a few steps, touches several files, or follows an approved spec, before starting implementation. Breaks the work into small vertical slices that can each be verified on their own.

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

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Core rule: Write the plan so that an engineer with zero context on this codebase could execute it — and no longer than that requires.

    line 14
  2. Very specific:

    Read the spec (or the agreed requirements) and the code areas involved (repo-map helps in a large repo).

    line 17
  3. Distinctive:

    Write the plan with the header and slice template below.

    line 21
  4. Distinctive:

    Run the self-review, fix what it finds, then show the plan to the user.

    line 22
  5. Distinctive:

    If reality differs from the plan, stop and update the plan before continuing.

    line 60
  6. Distinctive:

    Do not quietly expand scope.

    line 61

“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 the work

Core rule: Write the plan so that an engineer with zero context on this codebase could execute it — and no longer than that requires.

Process

  1. Read the spec (or the agreed requirements) and the code areas involved (repo-map helps in a large repo).
  2. Note existing patterns, utilities, and tests to reuse. Do not plan new code where suitable code exists.
  3. Split the work into vertical slices: each delivers one working, testable behavior end to end (not "all models, then all controllers").
  4. Order slices so each builds on a working previous one. Put the riskiest or most uncertain slice early.
  5. Write the plan with the header and slice template below.
  6. Run the self-review, fix what it finds, then show the plan to the user.
  7. Execute one slice at a time with tdd and verify.

Plan header

# <Feature> plan
Goal: one sentence.
Approach: two or three sentences.
Spec: docs/specs/<feature>.md
Constraints: rules every slice must respect (no new dependencies, keep API X stable, ...)

Slice template

### Slice N: <behavior>
- Covers: AC1, AC3
- Files: path/to/file.ts (modify), path/to/new.ts (create)
- Interfaces: new or changed signatures, named exactly
- Tests first: <test names / cases>
- Steps:
  1. ...
- Verify: <exact command> → <expected result>

Sizing

  • A slice takes minutes to an hour, not days. More than ~5 steps or ~5 files: split it.
  • Each step is one action with a checkable result: "add test X", "make it pass", "run suite".
  • A step says what to build, not a transcript of the code. Code belongs in the code.

Self-review (before showing the plan)

  • Coverage: every acceptance criterion maps to a slice
  • Failure modes: each error case and edge case in the spec has a test in some slice
  • Consistency: names, types, and signatures used in later slices match where they were defined
  • One thing per step: no step hides a design decision the implementer must invent
  • Proportion: the plan is not several times longer than the spec it implements

While executing

  • Mark a slice done only after its verify command passes.
  • If reality differs from the plan, stop and update the plan before continuing.
  • Do not quietly expand scope. New ideas go into a "Later" list.

Done when

  • Self-review passed
  • Every slice has files, tests, and a verify command
  • User approved the plan

Related: spec, tdd, verify, repo-map.

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.