Karpathy-Inspired Coding Agent Guidelines

A single instruction file to improve AI coding agent behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

The Problems

From Andrej's post:

"The models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should."

"They really like to overcomplicate code and APIs, bloat abstractions, don't clean up dead code... implement a bloated construction over 1000 lines when 100 would do."

"They still sometimes change/remove comments and code they don't sufficiently understand as side effects, even if orthogonal to the task."

The Solution

Four principles that directly address these issues:

Principle	Addresses
Think Before Coding	Wrong assumptions, hidden confusion, missing tradeoffs
Simplicity First	Overcomplication, bloated abstractions
Surgical Changes	Orthogonal edits, touching code you shouldn't
Goal-Driven Execution	Leverage through tests-first, verifiable success criteria

Install

Option A: Claude Code Plugin

From within Claude Code, first add the marketplace:

/plugin marketplace add forrestchang/andrej-karpathy-skills

Then install the plugin:

/plugin install andrej-karpathy-skills@karpathy-skills

This installs the guidelines as a Claude Code plugin, making the skill available across all your projects.

Option B: Codex Skill

From within Codex, install the skill:

$skill-installer install from https://github.com/hangsiahong/andrej-karpathy-skills

Or manually copy:

cp -r skills/karpathy-guidelines ~/.codex/skills/

Option C: Project-Level Instructions

For Claude Code — copy or append CLAUDE.md to your project root:

curl -o CLAUDE.md https://raw.githubusercontent.com/hangsiahong/andrej-karpathy-skills/main/CLAUDE.md

For Codex — copy or append AGENTS.md to your project root:

curl -o AGENTS.md https://raw.githubusercontent.com/hangsiahong/andrej-karpathy-skills/main/AGENTS.md

The Four Principles in Detail

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

State assumptions explicitly — If uncertain, ask rather than guess
Present multiple interpretations — Don't pick silently when ambiguity exists
Push back when warranted — If a simpler approach exists, say so
Stop when confused — Name what's unclear and ask for clarification

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 200 lines could be 50, rewrite it

The test: 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.

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

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Instead of...	Transform to...
"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"

How to Know It's Working

Fewer unnecessary changes in diffs — Only requested changes appear
Fewer rewrites due to overcomplication — Code is simple the first time
Clarifying questions come before implementation — Not after mistakes
Clean, minimal PRs — No drive-by refactoring or "improvements"

Key Insight

From Andrej:

"LLMs are exceptionally good at looping until they meet specific goals... Don't tell it what to do, give it success criteria and watch it go."

Agent Compatibility

Agent	Plugin System	Project Instructions	Skill Format
Claude Code	`.claude-plugin/`	`CLAUDE.md`	`skills/*/SKILL.md`
Codex	`.codex-plugin/` + `.agents/plugins/`	`AGENTS.md`	`skills/*/SKILL.md`

Both agents share the same SKILL.md format. The skill content is universal — only the packaging differs.

Tradeoff Note

These guidelines bias toward caution over speed. For trivial tasks (simple typo fixes, obvious one-liners), use judgment — not every change needs the full rigor.

License

MIT