git:20260611.23f0065 to git:20260623.c6692d9

---

name: karpathy-guidelines

description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

license: MIT

---

# Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.

**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 dead code, clean it up. Otherwise, leave it.

## 4. Goal-Driven Execution

**Define done before starting. Use tests to verify, not to guess.**

Before coding:

- Define what "done" looks like in concrete terms.

- Write a test or verification step first when possible.

- After implementing, verify against your definition. Don't just hope it works.

- If the goal shifts during implementation, stop. Restate the new goal. Get confirmation.

**The test:** Can someone verify your work succeeded without reading the code? If not, your success criteria aren't concrete enough.