agentleFS
Sign inStart free
florian101010florian101010/awesome-agentic-AI-coding-template/CLAUDE.md

awesome-agentic-AI-coding-template

CLAUDE.md4 starsChanged 12 days agoMITView on GitHub

Project-specific rules for Claude Code. Coding detail rules are in .claude/rules/ (path-scoped, auto-loaded). See @README.md for project overview. [FILL: Project name] — [FILL: 1-sentence description]. [FILL: Tech stack, e.g. "TypeScript, React, Node.js"]. [FILL: List your key build/test/lint commands here, e.g.: When compacting, always preserve: the list of modified files, any pending test results, the current task state, and the active branch name.

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. Very specific:

    Commit via git commit (hooks run automatically) with format type(scope): description

    line 38
  2. Distinctive:

    When compacting, always preserve: the list of modified files, any pending test results, the current task state, and the active branch name.

    line 43

≈ “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

Project-specific rules for Claude Code. Coding detail rules are in .claude/rules/ (path-scoped, auto-loaded). See @README.md for project overview.

<!-- SETUP: Fill in all [FILL: ...] placeholders before using this repo. See README.md. -->

Project

[FILL: Project name] — [FILL: 1-sentence description]. [FILL: Tech stack, e.g. "TypeScript, React, Node.js"].

Critical Constraints

<!-- Add constraints Claude cannot infer from code alone. Examples: -->
  • [FILL: Constraint 1 — e.g. "No runtime dependencies — only stdlib"]
  • [FILL: Constraint 2 — e.g. "All API calls must go through the gateway module"]
  • Git hooks — Active via git config core.hooksPath .githooks. Ensure pre-commit passes before finalizing.

Do NOT

<!-- Hard prohibitions — things that would break the project if done wrong. -->
  • [FILL: Prohibition 1 — e.g. "Use localStorage or sessionStorage"]
  • [FILL: Prohibition 2 — e.g. "Commit directly to main without a PR"]

Available Scripts

[FILL: List your key build/test/lint commands here, e.g.:

  • Build: npm run build
  • Test: npm test
  • Lint: npm run lint

]

After Every Change

  1. Run [FILL: test command, e.g. npm test]
  2. Commit via git commit (hooks run automatically) with format type(scope): description
  3. [FILL: Any additional post-change steps specific to your project]

Context & Compaction

When compacting, always preserve: the list of modified files, any pending test results, the current task state, and the active branch name.

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