agentleFS
Sign inStart free
chuanglibschuanglibs/Claude-Code-Game-Studios-Codex/src/CLAUDE.md

Claude-Code-Game-Studios-Codex / src

CLAUDE.md1 starsChanged 59 days agoMITView on GitHub

When writing or editing game code in this directory, follow these standards. The LLM's training data predates the pinned engine version. Always check docs/engine-reference/ before using any engine API. Do not guess at post-cutoff API signatures — look them up first. Match the engine-specialist agent to the file type being written. See CLAUDE.md → Technical Preferences → Engine Specialists → File Extension Routing. When in doubt, use the primary engine specialist configured in CLAUDE.md. Tests live in tests/ — not…

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

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

9 rules. About 0 are common, 7 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When writing or editing game code in this directory, follow these standards.

    line 3
  2. Distinctive:

    Do not guess at post-cutoff API signatures — look them up first.

    line 9
  3. Distinctive:

    All public APIs require doc comments

    line 13
  4. Distinctive:

    Prefer dependency injection over singletons for testability

    line 15
  5. Very specific:

    Every new system needs a corresponding ADR in docs/architecture/

    line 16
  6. Distinctive:

    When in doubt, use the primary engine specialist configured in CLAUDE.md.

    line 24
  7. Very specific:

    Run /test-setup to scaffold the test framework if it doesn't exist yet.

    line 29
  8. Distinctive:

    Every gameplay system should have unit tests covering its formulas and edge cases.

    line 30
  9. Distinctive:

    Write tests first when adding gameplay systems.

    line 34

≈ “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

Source Directory

When writing or editing game code in this directory, follow these standards.

Engine Version Warning

The LLM's training data predates the pinned engine version. Always check docs/engine-reference/ before using any engine API. Do not guess at post-cutoff API signatures — look them up first.

Coding Standards

  • All public APIs require doc comments
  • Gameplay values must be data-driven (external config files), never hardcoded
  • Prefer dependency injection over singletons for testability
  • Every new system needs a corresponding ADR in docs/architecture/
  • Commits must reference the relevant story ID or design document

File Routing

Match the engine-specialist agent to the file type being written. See CLAUDE.md → Technical Preferences → Engine Specialists → File Extension Routing.

When in doubt, use the primary engine specialist configured in CLAUDE.md.

Tests

Tests live in tests/ — not in src/. Run /test-setup to scaffold the test framework if it doesn't exist yet. Every gameplay system should have unit tests covering its formulas and edge cases.

Verification-Driven Development

Write tests first when adding gameplay systems. For UI changes, verify with screenshots. Compare expected output to actual output before marking work complete.

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