# Karpathy Guidelines

> 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.

- **Type:** Skill
- **Install:** `agentstack add skill-glyphs-ai-glyph-karpathy-guidelines`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [glyphs-ai](https://agentstack.voostack.com/s/glyphs-ai)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [glyphs-ai](https://github.com/glyphs-ai)
- **Source:** https://github.com/glyphs-ai/glyph/tree/main/first-party/skills/karpathy-guidelines

## Install

```sh
agentstack add skill-glyphs-ai-glyph-karpathy-guidelines
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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.

---

## Attribution

This skill was vendored into the glyph first-party catalog from an external open-source source. The body content above is reproduced from the upstream under the terms of the MIT License; see the sibling `NOTICE` file for the full license text and the upstream copyright.

- **Upstream source**: https://github.com/multica-ai/andrej-karpathy-skills/blob/main/skills/karpathy-guidelines/SKILL.md
- **Upstream license**: MIT
- **Forked at**: 6a62d0441753157ca6ca50479e490c2948033adb  (use the SHA the file was fetched at)
- **First-party entry maintained at**: https://github.com/glyphs-ai/glyph/tree/main/first-party/skills/karpathy-guidelines

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [glyphs-ai](https://github.com/glyphs-ai)
- **Source:** [glyphs-ai/glyph](https://github.com/glyphs-ai/glyph)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-glyphs-ai-glyph-karpathy-guidelines
- Seller: https://agentstack.voostack.com/s/glyphs-ai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.