agentleFS
Sign inStart free
khuynh22khuynh22/agent-dev-team/CLAUDE.md

agent-dev-team

CLAUDE.md9 starsChanged 2 months agoMITView on GitHub

Read AGENTS.md in this repository. It is the entry point: roster, tiers, routing table, escalation protocol, and the non-negotiables that apply to every role. /autopilot runs the whole lifecycle unattended for a single ticket. The policy governing an unattended run — where escalations go, what gets tagged as an assumption, and the report it must emit — is references/autonomous-run.md. When working on this repository rather than with it: - skills/*/SKILL.md frontmatter must use only the six Agent Skills spec fields:…

The file

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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Read AGENTS.md in this repository.

    line 3
  2. Distinctive:

    When working on this repository rather than with it:

    line 10
  3. Very specific:

    Run npm test before committing.

    line 20

≈ “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

agent-dev-team

Read AGENTS.md in this repository. It is the entry point: roster, tiers, routing table, escalation protocol, and the non-negotiables that apply to every role.

/autopilot runs the whole lifecycle unattended for a single ticket. The policy governing an unattended run — where escalations go, what gets tagged as an assumption, and the report it must emit — is references/autonomous-run.md.

When working on this repository rather than with it:

  • skills/*/SKILL.md frontmatter must use only the six Agent Skills spec fields: name, description, license, compatibility, metadata, allowed-tools. Any other key is a hard error on claude.ai upload and the Skills API. Claude Code-only fields belong in agents/*.md, which is not a spec file.
  • agents/*.md must carry the tier line: **Tier:** T<n> · **Escalates to:** <agent> · **Terminal:** yes|no. scripts/validate.js parses it.
  • Command shims under .gemini/commands/ and commands/ are generated. Edit .claude/commands/*.md and run node scripts/build-commands.js.
  • Run npm test before committing. It runs static validation and the routing evals.

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