agentleFS
Sign inStart free
SauravSrivastavSauravSrivastav/claude-code-production-starter/CLAUDE.md

claude-code-production-starter

CLAUDE.md0 starsChanged 5 months agoMITView on GitHub

Maintain a minimal Node.js status service that demonstrates a production-minded Claude Code project configuration. Optimize for correctness, safety, and clear handoffs. See docs/ARCHITECTURE.md for boundaries and extension guidance.

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

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep changes scoped to the user's request.

    line 12
  2. Distinctive:

    Do not expose, read, or modify secrets.

    line 13
  3. Distinctive:

    Never push, deploy, publish, or release without explicit user approval.

    line 14
  4. Distinctive:

    Do not bypass failing tests or weaken safeguards to make verification pass.

    line 15
  5. Distinctive:

    Add or update tests when behavior changes.

    line 16
  6. Distinctive:

    Prefer standard-library solutions unless a dependency provides clear value.

    line 17
  7. Distinctive:

    No credentials or local-only files are added.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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 Code Production Starter

Goal

Maintain a minimal Node.js status service that demonstrates a production-minded Claude Code project configuration. Optimize for correctness, safety, and clear handoffs.

Working Agreement

  • Inspect existing code and tests before editing.
  • Keep changes scoped to the user's request.
  • Do not expose, read, or modify secrets.
  • Never push, deploy, publish, or release without explicit user approval.
  • Do not bypass failing tests or weaken safeguards to make verification pass.
  • Add or update tests when behavior changes.
  • Prefer standard-library solutions unless a dependency provides clear value.
  • Report verification commands and their outcomes.

Architecture

  • src/status.js: domain logic for constructing service status.
  • src/server.js: HTTP boundary and request handling.
  • test/: Node test-runner coverage.
  • scripts/: deterministic validation and release helpers.
  • .claude/: Claude Code automation and project guidance.

See docs/ARCHITECTURE.md for boundaries and extension guidance.

Commands

npm start          # Run the service on PORT or 3000
npm test           # Run the test suite
npm run lint       # Run repository checks
npm run format     # Validate JSON formatting
npm run verify     # Run the complete production gate

Definition of Done

  • Requested behavior is implemented.
  • Relevant tests cover success and failure paths.
  • npm run verify passes.
  • No credentials or local-only files are added.
  • The final response states what changed and how it was verified.

Context Map

  • API work: read .claude/rules/api.md.
  • Tests: read .claude/rules/testing.md.
  • Security-sensitive work: read .claude/rules/security.md.
  • Release preparation: use /ship.
  • Code review: delegate to code-reviewer or use /review-change.
  • Failure diagnosis: delegate to debugger or use /debug-failure.

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