Skip to content

Instantly share code, notes, and snippets.

@priancho
Last active February 2, 2026 09:51
Show Gist options
  • Select an option

  • Save priancho/f9dc243bfd40c8b2102e2ebf0f6832e2 to your computer and use it in GitHub Desktop.

Select an option

Save priancho/f9dc243bfd40c8b2102e2ebf0f6832e2 to your computer and use it in GitHub Desktop.
Karpathy 의 CLAUDE.md 파일에 기초한 변형

CLAUDE.md

Behavioral guidelines to reduce common LLM coding mistakes. Merge with project-specific instructions as needed.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them - don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" → "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" → "Write a test that reproduces it, then make it pass"
  • "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

5. Validation

Testing with codes

  • Always create standalone test programs in test_cases/ directory to verify implementations.
  • Test programs should be runnable independently (e.g., python test_cases/test_*.py).
  • Test each component individually before integration testing.
  • Include assertions and clear success/failure output.
  • Mock dependencies (like flash_attn) when they are not available in the test environment.
  • Run them in parallel, if possible.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment