agentleFS
Sign inStart free
Bita71Bita71/Agent-Workflow-Kit/CLAUDE.md

Agent-Workflow-Kit

CLAUDE.md1 starsChanged 4 months agoMITView on GitHub

docs/ai is the source of truth for this project. Before working, read: <check> means CHECK_COMMAND from the config. Run it after substantive changes unless it is none. Do not commit or push without an explicit request. Claude is the primary builder and design reviewer, and the orchestrator for the full pipeline. Workflows (slash commands in .claude/commands/, each pointing into docs/ai): - For implementation, follow docs/ai/agents/build.md and docs/ai/skills/build.md. - For design review, follow docs/ai/agents/review-design.md. - Do not plan by hand: planning…

The file

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

4 rules. About 0 are common, 1 is distinctive, and 3 are 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.

  • 3

    Very specific

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

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

    Do not plan by hand: planning is Codex's job — orchestrate it via /codex-plan.

    line 35
  2. Very specific:

    Do not do correctness/security review by hand: that pass is Codex's, inside /review-full.

    line 36
  3. Very specific:

    Run the configured CHECK_COMMAND after substantive changes.

    line 40
  4. Distinctive:

    Do not commit or push without an explicit request.

    line 41

≈ “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 Adapter

docs/ai is the source of truth for this project. Before working, read:

  • .agent-workflow-kit/config.conf — project settings and active profiles.
  • docs/ai/README.md — map of the AI surface.
  • docs/ai/rules/project.md — tool-agnostic invariants.
  • docs/ai/rules/coding-rules.md — this stack's conventions.
  • docs/ai/rules/commit-message.md — Conventional Commits.

<check> means CHECK_COMMAND from the config. Run it after substantive changes unless it is none. Do not commit or push without an explicit request.

Claude's role

Claude is the primary builder and design reviewer, and the orchestrator for the full pipeline.

Workflows (slash commands in .claude/commands/, each pointing into docs/ai):

  • /symphony — drive the whole task through the pipeline.
  • /build — implement a task.
  • /codex-plan — orchestrate planning through Codex.
  • /review-full — parallel correctness/security + design review.
  • /review-design — design review only.
  • /choose-model — recommend a model/effort.
  • /learn — propose durable repo improvements.
  • /ai-audit, /deps-audit, /apply-worktree.

Rules

  • For implementation, follow docs/ai/agents/build.md and docs/ai/skills/build.md.
  • For design review, follow docs/ai/agents/review-design.md.
  • Do not plan by hand: planning is Codex's job — orchestrate it via /codex-plan.
  • Do not do correctness/security review by hand: that pass is Codex's, inside /review-full.
  • Take Codex/Claude CLI invocations only from docs/ai/agents/cli.md — do not invent flags.
  • Run the configured CHECK_COMMAND after substantive changes.
  • Do not commit or push without an explicit request.

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