agentleFS
Sign inStart free
CaelumcaCaelumca/claude-codex-skeleton/CLAUDE.md

claude-codex-skeleton

CLAUDE.md0 starsChanged 3 months agoMITView on GitHub

Template. Fill the ALL-CAPS slots on day one; delete lines that don't apply. This file holds what doesn't change. Why → .notes/decisions.md. Now → .notes/working.md. How to work → .claude/skills/. One fact, one home. VIBE — prototypes, experiments, solo scripts, anything disposable. - Work inline. No lanes, no briefs, no review pass. - Only two habits survive: run the tests before claiming done, and drop a D-entry in .notes/decisions.md for anything you'd hate to re-debate. - working.md gets one line…

  • Reads credentials

The file

We split this CLAUDE.md into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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
  • could be automatic: a setting could enforce it
  1. Very specific:

    Only two habits survive: run the tests before claiming done, and drop a D-entry in .notes/decisions.md for anything you'd hate to re-debate.

    line 20
  2. Distinctive:

    All four skills active: fable-orchestration governs delegation, qa-loop keeps it green and safe, review-loop gates every delegated diff, …

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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
CLAUDE.md

CLAUDE.md — project router

Template. Fill the ALL-CAPS slots on day one; delete lines that don't apply. This file holds what doesn't change. Why → .notes/decisions.md. Now → .notes/working.md. How to work → .claude/skills/. One fact, one home.

Project

  • What this is: ONE SENTENCE.
  • Stack: LANGUAGES / FRAMEWORKS / DB.
  • Run: COMMAND
  • Test: COMMAND
  • Lint / typecheck: COMMAND
  • Entry points: src/MAIN, src/...

Mode: [ VIBE | FULL ] ← pick one, switching later is fine

VIBE — prototypes, experiments, solo scripts, anything disposable.

  • Work inline. No lanes, no briefs, no review pass.
  • Only two habits survive: run the tests before claiming done, and drop a D-entry in .notes/decisions.md for anything you'd hate to re-debate.
  • working.md gets one line at session end: where you stopped.
  • Skills active: session-memory (minimal), everything else dormant.

FULL — anything with users, collaborators, or a future.

  • All four skills active: fable-orchestration governs delegation, qa-loop keeps it green and safe, review-loop gates every delegated diff, session-memory carries state across sessions.
  • Boot sequence per session-memory: working.md → decisions.md headers → open issues/findings → code just-in-time.
  • Briefs are files in .briefs/, always.

Promotion rule: a VIBE project that gains a second contributor, a deploy target, or a paying user becomes FULL. Demotion never happens silently — it's a D-entry.

House rules

  • STYLE / FORMATTING CONVENTIONS (one line each, only the non-obvious ones)
  • THINGS THAT ALWAYS APPLY ("never commit .env", "migrations via CLI only")

Do not touch

  • PATHS OR SYSTEMS THAT ARE OFF-LIMITS WITHOUT ASKING

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