agentleFS
Sign inStart free
nesnilnehcnesnilnehc/ai-cortex/CLAUDE.md

ai-cortex

CLAUDE.md8 starsChanged 2 months agoMITView on GitHub

A briefing for Claude Code working in this repository. Mostly a markdown asset library: skills, protocols, rules and specs. NEVER try npm test / npm run build — there is no package.json, and no JavaScript toolchain to reach for. There is plenty to run, just not with npm. scripts/ holds the checkers and their tests, CI runs them on every pull request, and CONTRIBUTING.md says which to run for which kind of change. Run them before opening one. The working…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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
  1. Very specific:

    After editing a SKILL.md, the only registry to update is skills/INDEX.md — and it is generated, so run python3 scripts/sync-skills-index.py …

    line 23

≈ “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

A briefing for Claude Code working in this repository.

What this repository is

Mostly a markdown asset library: skills, protocols, rules and specs. NEVER try npm test / npm run build — there is no package.json, and no JavaScript toolchain to reach for.

There is plenty to run, just not with npm. scripts/ holds the checkers and their tests, CI runs them on every pull request, and CONTRIBUTING.md says which to run for which kind of change. Run them before opening one.

The working tree is skills/, protocols/, rules/ and specs/ in markdown, plus scripts/ and tests/fixtures/ in Python.

Where to go next

  • The execution contract, required reading: AGENTS.md — load order, skill matching, failure handling, precedence
  • How to contribute: CONTRIBUTING.md — forking, PRs, version numbers
  • Terminology: docs/architecture/terminology.md — the definitions and boundaries of the 4 asset types
  • Naming: docs/architecture/asset-naming.md — the naming formula and examples for each of the 4 asset types

Traps Claude Code falls into here

  • Skills follow the agentskills.io standard format. This repository no longer maintains a private spec — there is no agent.yaml, no manifest.json, no specs/skill.md
  • After editing a SKILL.md, the only registry to update is skills/INDEX.md — and it is generated, so run python3 scripts/sync-skills-index.py rather than editing it. The indexes under rules/, specs/ and protocols/ are hand-maintained; a new file there means a new row by hand
  • Older ADRs and CHANGELOG entries describe mechanisms that have since been deleted — manifest, agent.yaml, artifact-contract, Stage 0 Norms Resolution and others. Mind the timeline as you read, and do not go looking for files those descriptions name

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