agentleFS
GabrielKqwGabrielKqw/weave-agent-workflow/skills/weave-plan/SKILL.md

weave-plan

Skill5 starsChanged 2 months agoMITView on GitHub

Plan a coding task before touching code: trace the affected flow, write the request contract (goal, scope, done-when), and a minimal step plan, then save both to .weave/state.md so any agent can execute or continue it. Use when the user says "weave plan", "/weave-plan", "plan this", "make a plan first", "planeje", or wants a plan reviewed before implementation. Edits no source files.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. tony/skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Every coding request is already planned automatically by the Weave policy.

    line 15
  2. Distinctive:

    Use this skill when the user wants the plan written down and approved before any code exists.

    line 16
  3. Very specific:

    Read the existing state: If .weave/state.md exists, continue it.

    line 24
  4. Distinctive:

    Trace: Start at the entry point the task names (file, command, error, endpoint).

    line 26
  5. Very specific:

    Save: Write Goal, Constraints, Not requested, Completion criteria, Blocking questions, Working memory, and Plan into .weave/state.md.

    line 39
  6. Distinctive:

    If the task is simple (one concern, small surface), say so, give the one-line contract and the two or three steps, and skip the state file …

    line 60
  7. Distinctive:

    No source edits, no installs, no commits.

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Weave Plan

Every coding request is already planned automatically by the Weave policy. Use this skill when the user wants the plan written down and approved before any code exists.

Plan only. Read code, run read-only commands, write .weave/state.md. Do not edit source files until the user approves the plan.

Steps

  1. Read the existing state. If .weave/state.md exists, continue it; do not overwrite another agent's work.
  2. Trace. Start at the entry point the task names (file, command, error, endpoint). Follow real callers and references outward. Every read answers one question.
  3. Contract. State what the user can do when done, constraints, exclusions, observable acceptance criteria, and the check for each criterion. Ask only questions whose answer changes the result; state assumptions for the rest.
  4. Climb the ladder. For each needed change: does it need to exist, is it already in the repo, does the stdlib or platform cover it, can it land at the shared point all callers use, could code be removed instead.
  5. Plan. Ordered steps, each with the file, change, and verification. Identify dependencies and real risks (security, data, public interface). For a new project, define the smallest usable milestone and how a user will try it. Reject steps without a path to an acceptance criterion.
  6. Save. Write Goal, Constraints, Not requested, Completion criteria, Blocking questions, Working memory, and Plan into .weave/state.md.

Output

Goal: <one line>
Done when: <the check>
Out of scope: <one line, or "none">

Plan:
1. <file> - <change> - verify: <command or test>
2. ...

Reuse: <what existing code or stdlib covers part of this, or "none">
Risks: <only real ones, or "none">
Questions: <blocking only, or "none">

End with Saved to .weave/state.md. Approve to build, or adjust.

If the task is simple (one concern, small surface), say so, give the one-line contract and the two or three steps, and skip the state file unless asked.

Handoff

The saved plan is what weave prompt claude|gemini|codex turns into a task brief for another agent.

Boundaries

No source edits, no installs, no commits. Read-only commands only. Planning does not shortcut reading: a plan built on code you have not opened is a guess.

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.