agentleFS
Sign inStart free
miptah21miptah21/skills/.cursor/rules/karpathy-guidelines.mdc

skills / rules

Cursor rule2 starsChanged 5 months agoMITView on GitHub

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.

We split this karpathy-guidelines.mdc into the rules it gives an agent

15 rules. About 0 are common, 14 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈14

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If multiple interpretations exist, present them - don't pick silently.

    line 18
  2. Distinctive:

    If a simpler approach exists, say so.

    line 19
  3. Distinctive:

    If something is unclear, stop.

    line 20
  4. Distinctive:

    No features beyond what was asked.

    line 26
  5. Distinctive:

    No abstractions for single-use code.

    line 27
  6. Distinctive:

    No error handling for impossible scenarios.

    line 29
  7. Distinctive:

    If you write 200 lines and it could be 50, rewrite it.

    line 30
  8. Distinctive:

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

    line 32
  9. Distinctive:

    When editing existing code:

    line 38
  10. Distinctive:

    Don't "improve" adjacent code, comments, or formatting.

    line 39
  11. Distinctive:

    Don't refactor things that aren't broken.

    line 40
  12. Distinctive:

    If you notice unrelated dead code, mention it - don't delete it.

    line 42
  13. Distinctive:

    When your changes create orphans:

    line 44
  14. Very specific:

    Remove imports/variables/functions that YOUR changes made unused.

    line 45
  15. Distinctive:

    Don't remove pre-existing dead code unless asked.

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 6,350 Cursor rule files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
karpathy-guidelines.mdc
---
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.
alwaysApply: true
---

# Karpathy behavioral guidelines

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]
```

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free