agentleFS
crystal-autobotcrystal-autobot/autobot/CLAUDE.md

autobot

CLAUDE.md47 starsChanged 8 months agoMITView on GitHub

IMPORTANT: Always follow Ameba linter rules. All code must pass ameba checks without warnings or failures before committing. If you encounter a complexity warning, refactor by extracting methods rather than ignoring the rule. Run these checks before committing:

The file

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

8 rules. About 0 are common, 7 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When making changes, ensure the docs/ also reflect it.

    line 5
  2. Very specific:

    Upstream Alignment: Always branch off the latest commit of the upstream main branch (crystal-autobot/autobot:main).

    line 8
  3. Distinctive:

    IMPORTANT: Always follow Ameba linter rules.

    line 12
  4. Distinctive:

    No cyclomatic complexity violations: - Keep methods simple (max complexity: 10), follow it at the beginning to avoid refactoring

    line 16
  5. Distinctive:

    No style violations: - Follow Crystal style guide

    line 17
  6. Distinctive:

    No naming violations: - Use proper naming conventions

    line 18
  7. Distinctive:

    If you encounter a complexity warning, refactor by extracting methods rather than ignoring the rule.

    line 20
  8. Distinctive:

    Run these checks before committing:

    line 24

≈ “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

Autobot

Rules

  1. When making changes, ensure the docs/ also reflect it.
  2. Coding Agents & Assistants (Jules, Claude, Gemini, ChatGPT, Cursor):
    • Scope Boundary: Modify only files directly related to your task. Do not perform global formatting or style cleanups that alter unrelated files (e.g. stripping trailing commas).
    • Upstream Alignment: Always branch off the latest commit of the upstream main branch (crystal-autobot/autobot:main). Sync fork branches before starting.

Code Quality Standards

IMPORTANT: Always follow Ameba linter rules. All code must pass ameba checks without warnings or failures before committing.

Ameba Rules

  • No formatting warnings - Code must be formatted with crystal tool format
  • No cyclomatic complexity violations - Keep methods simple (max complexity: 10), follow it at the beginning to avoid refactoring
  • No style violations - Follow Crystal style guide
  • No naming violations - Use proper naming conventions

If you encounter a complexity warning, refactor by extracting methods rather than ignoring the rule.

Verification Checks

Run these checks before committing:

crystal spec      # All tests must pass
./bin/ameba       # No warnings or failures
make release      # Build must succeed

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.