agentleFS
Sign inStart free
w2urw2ur/claude-code-setup/.claude/CLAUDE.md

claude-code-setup

CLAUDE.md2 starsChanged 2 months agoMITView on GitHub

Public repo publishing an anonymized Claude Code configuration. Not an app — a collection of markdown files (commands, agents, skills, hooks) with a Python sync script for maintenance. Markdown (content), Python 3.10+ (sync script), YAML (anonymization config). No build step and no dependency step. sync.py carries PEP 723 inline metadata and a uv run --script shebang, so it builds its own environment: Never invoke it as python3 scripts/sync.py here — see the global CLAUDE.md's uv rules for why that bypasses…

  • Installs packages

The file

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

5 rules. About 0 are common, 2 are distinctive, and 3 are 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not an app — a collection of markdown files (commands, agents, skills, hooks) with a Python sync script for maintenance.

    line 6
  2. Very specific:

    No build step and no dependency step.

    line 19
  3. Very specific:

    Never invoke it as python3 scripts/sync.py here — see the global CLAUDE.md's uv rules for why that bypasses the shebang.

    line 27
  4. Distinctive:

    NEVER commit files containing personal data (real app names, URLs, paths)

    line 34
  5. Very specific:

    After any sync, run ./scripts/sync.py --audit-only before committing

    line 35

≈ “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 — claude-code-setup

Project Overview

Public repo publishing an anonymized Claude Code configuration. Not an app — a collection of markdown files (commands, agents, skills, hooks) with a Python sync script for maintenance.

Tech Stack

Markdown (content), Python 3.10+ (sync script), YAML (anonymization config).

User-Facing Language

English.

Development

No build step and no dependency step. sync.py carries PEP 723 inline metadata and a uv run --script shebang, so it builds its own environment:

./scripts/sync.py --dry-run
uv run --with pytest --with PyYAML pytest scripts/ -q   # tests

Never invoke it as python3 scripts/sync.py here — see the global CLAUDE.md's uv rules for why that bypasses the shebang. The pip install -r scripts/requirements.txt path stays documented in scripts/README.md, for people cloning this public repo without uv.

Project-Specific Rules

  • NEVER commit files containing personal data (real app names, URLs, paths)
  • After any sync, run ./scripts/sync.py --audit-only before committing
  • Everything under commands/, agents/, skills/, hooks/, mods/, claude-scripts/ and the root CLAUDE.md is generated from ~/.claude/ by scripts/sync.py: make the change in the live file and re-run the sync, never in the copy here (the sync exits 2 when a destination matches neither HEAD nor the content it is about to write — that is what a hand edit looks like). README.md, docs/, hooks/README.md, claude-scripts/README.md and this file are the owner-maintained exceptions.
  • This repo does NOT follow the author signature convention (no footer — it's not a web app)

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