agentleFS
dynamicartdynamicart/ai-docs/CLAUDE.md

ai-docs

CLAUDE.md2 starsChanged 4 days agoMITView on GitHub

This project uses the AI Docs framework. Its own rules, skills, and workflow commands live outside this file, in .agents/, and are not part of your native auto-loading — treat this section as your entry point into them: Installed for: claude-code | Installed: 2026-09-23 <!-- AI_DOCS_BRIDGE_END -->

The file

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

3 rules. About 0 are common, 0 are distinctive, and 3 are 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    First-time setup: if _docs/PROJECT-OVERVIEW.md doesn't exist yet, run /project-sync first (its first run asks the user about the project).

    line 10
  2. Very specific:

    Load on demand: every .agents/skills/*/SKILL.md whose "When to use this skill?" section matches the current task, before acting on that …

    line 14
  3. Very specific:

    Never edit _docs/BOARD.md, _docs/index.md, _docs/PROJECT-OVERVIEW.md, _docs/log.md, or agent.md above its boundary by hand — they're …

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
<!-- AI_DOCS_BRIDGE_START -->

AI Docs framework (bridge — do not remove)

<!-- Native import (Claude Code / Gemini CLI only): loads agent.md and its @_docs/index.md map. -->

@agent.md

This project uses the AI Docs framework. Its own rules, skills, and workflow commands live outside this file, in .agents/, and are not part of your native auto-loading — treat this section as your entry point into them:

  • At the start of every session, read agent.md (repo root) unless it was already imported above — it is the "Shared Brain": a generated digest of the stable facts about this project (what it is, tech stack, where things live, the conventions you must follow), ending with an @_docs/index.md import that maps the whole knowledge bundle.
  • First-time setup: if _docs/PROJECT-OVERVIEW.md doesn't exist yet, run /project-sync first (its first run asks the user about the project); if agent.md doesn't exist yet, run /agent-sync after that. The order matters: /agent-sync takes the project description from PROJECT-OVERVIEW.md.
  • For the current project status — active tasks, recent journals, key decisions, open questions — open _docs/PROJECT-OVERVIEW.md (or the files _docs/index.md points at). This is deliberately not duplicated in agent.md.
  • _docs/modules/*.md are durable, human-approved module references: read them for context, but only ever update one through an explicit /module-sync invocation.
  • Always apply .agents/rules/style-guide.md as an always-on rule for this project (documentation conventions, OKF _docs/ rules, coding/commenting conventions).
  • Load on demand every .agents/skills/*/SKILL.md whose "When to use this skill?" section matches the current task, before acting on that task.
  • Treat every file in .agents/workflows/*.md as a /-command definition. When the user types /<filename-without-extension> (with or without arguments), read that exact file and execute its instructions as written — do not paraphrase or skip steps. Do not invoke a workflow the user didn't ask for.
  • Never edit _docs/BOARD.md, _docs/index.md, _docs/PROJECT-OVERVIEW.md, _docs/log.md, or agent.md above its boundary by hand — they're generated/maintained by the workflows above.

Installed for: claude-code | Installed: 2026-09-23

<!-- AI_DOCS_BRIDGE_END -->

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.