Karpathy Guidelines

Four principles that reduce common LLM coding failure modes. Apply alongside any domain skill. Adapted from multica-ai/andrej-karpathy-skills.

1. Think Before Coding

Surface uncertainty rather than concealing it.

• State your assumptions explicitly. If uncertain, ask.
• If multiple interpretations exist, present them — don't pick silently. (See CLAUDE.md → "Before Significant Tasks" for the 2-3 alternatives rule.)
• 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.

Sanity check: would an experienced engineer call this overcomplicated? If yes, simplify.

3. Surgical Changes

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

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

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

This principle extends to written content (prose, docs, plans) — see rules/code-cleanup-safety.md § "Written Content".

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 up front:

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

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

These guidelines are working if: fewer unnecessary changes in diffs, fewer rewrites due to overcomplication, and clarifying questions come before implementation rather than after mistakes.