agentleFS
Sign inStart free
gastonlarap-a11ygastonlarap-a11y/claude-code-setup/CLAUDE.md

claude-code-setup

CLAUDE.md1 starsChanged 3 months agoMITView on GitHub

- Subagent model is pinned by env.CLAUDE_CODE_SUBAGENT_MODEL (Sonnet) in global/settings.json, which overrides any agent's model: frontmatter. Keep global/agents/*.md in sync — scripts/check-subagent-model.sh enforces it in CI.

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
  1. Distinctive:

    After ANY task that changed structure, commands or conventions: check that this file — and AGENTS.md if present — still matches reality.

    line 10
  2. Very specific:

    After structural changes (new package, framework migration, tooling swap), re-run /setup-project audit.

    line 19

≈ “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

@AGENTS.md

Claude Code specifics

  • Subagent model is pinned by env.CLAUDE_CODE_SUBAGENT_MODEL (Sonnet) in global/settings.json, which overrides any agent's model: frontmatter. Keep global/agents/*.md in sync — scripts/check-subagent-model.sh enforces it in CI.

Config maintenance

  • After ANY task that changed structure, commands or conventions: check that this file — and AGENTS.md if present — still matches reality; propose the exact edit in the same session.
  • Same-session fix also when a documented command fails, a stated convention contradicts the code, or the user corrects the same thing twice.
  • New repeated procedure → propose a .claude/skills/ entry; new language/area convention → a paths:-scoped rule in .claude/rules/ — never more always-loaded lines.
  • New technology appears in the repo (dependency, SDK, platform, infra — e.g. a cloud provider or a new datastore) → offer the matching plugins/skills/rules in the same session; ask first, never add silently.
  • After structural changes (new package, framework migration, tooling swap), re-run /setup-project audit.

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