Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
Best use case
Karpathy Guidelines is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
Teams using Karpathy Guidelines should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/karpathy-guidelines/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Karpathy Guidelines Compares
| Feature / Agent | Karpathy Guidelines | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
<!-- KARPATHY_GUIDELINES:START -->
# 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 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]
```
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
## Interaction with Rulebook
This skill complements existing Rulebook rules:
- `no-shortcuts.md` forbids stubs/TODOs; **Simplicity First** forbids the opposite — bloat.
- `research-first.md` requires investigating unknowns; **Think Before Coding** adds *surfacing* what was investigated.
- `incremental-implementation.md` tests each step; **Goal-Driven Execution** adds defining the test up front.
- **Surgical Changes** has no Rulebook counterpart and fills a real gap: no rule today forbids opportunistic refactor of adjacent code.
Skill body is deliberately small (≤80 lines) so it adds < 1KB to the context budget per session.
<!-- KARPATHY_GUIDELINES:END -->