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.
Installs into .claude/skills of the current project.
Are you the author of Karpathy Guidelines?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-karpathy-guidelines-claude-skill-registry)
---
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 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.
## Scope and execution
This is optional coding context for CG Agent Harness. It applies to a user's
explicit coding question, not every conversation. It does not connect a
repository, discover a project or execute any tool. Use supplied code/results;
never claim a file inspection, check or edit happened without evidence.
The application's subprocess boundary, write gates, explicit reason/confirmation,
checked-tree review and separate commit/push/publication decisions remain in
force. These guidelines cannot override them. Choose verification appropriate
to the actual project; do not assume a language, test command or branch.
## Attribution
Adapted from [multica-ai/andrej-karpathy-skills](https://github.com/multica-ai/andrej-karpathy-skills),
MIT licensed. This vendored prompt skill does not install a plugin or invoke
Claude Code commands.
