karpathy-guidelines SKILL.md skillA

karpathy-guidelines from alirezarezvani/claudeforge is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add alirezarezvani/claudeforge/karpathy-guidelines@git:20260519.032c5e5

Pins git:20260519.032c5e5 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
alirezarezvani/claudeforge
Path
skill/karpathy-guidelines/SKILL.md
Versions recorded
2
Latest version
git:20260519.032c5e5, committed May 19, 2026
First version recorded
May 18, 2026
Size
4,920 bytes
Repository stars
434
License
MIT

Behavioral guardrails for LLM-assisted coding. Use when writing, reviewing, or refactoring code in any project to avoid overcomplication, keep changes surgical, surface assumptions early, and execute against verifiable success criteria.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Karpathy Guidelines for LLM Coding

Behavioral guardrails for code generation in Claude Code projects, distilled from observations on common LLM coding failure modes. Apply these to every editing, reviewing, and refactoring task.

> Attribution: adapted from the MIT-licensed `karpathy-guidelines` skill by Forrest Chang
> (https://github.com/forrestchang/andrej-karpathy-skills), inspired by Andrej Karpathy's
> commentary on where LLM-generated code typically goes wrong.
> ClaudeForge integrates these principles so every project initialised or enhanced through
> `/enhance-claude-md` ships with them in its CLAUDE.md.

---

## When to Apply

Apply on every non-trivial task: writing new code, editing existing code, code review, refactoring, and bug fixing. They are intentionally conservative — bias toward caution over speed.

---

## 1. Think Before Coding

Surface what is uncertain. Do not paper over confusion with plausible-sounding code.

- State assumptions before implementing; if any are load-bearing and you are not sure, ask.
- If the request admits more than one reasonable interpretation, list them rather than silently picking one.
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_fjxaheju5h7v5jwm/acd92adddfb6dfb73279ec61a53648db3696eb9984474855fc8bd840f4644c0d.json

Then /plugin install karpathy-guidelines@markdownregistry-fjxaheju5h7v5jwm in Claude Code. It installs git:20260519.032c5e5, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add alirezarezvani/claudeforge/karpathy-guidelines@sha256:acd92adddfb6dfb7

The line at the top of this page pins the label git:20260519.032c5e5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fjxaheju5h7v5jwm.svg)](https://markdownregistry.com/a/art_fjxaheju5h7v5jwm)

1 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in alirezarezvani/claudeforge/karpathy-guidelines since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of karpathy-guidelines from somewhere else? Ask it: where did my karpathy-guidelines come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 2 versions of this file, between May 18, 2026 and May 19, 2026, more than one a day.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260519.032c5e5 latest2026-05-19 032c5e5 4,920 BA view · diff
git:20260518.ffff0fc2026-05-18 ffff0fc 4,534 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4920 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

alirezarezvani/claudeforge · 434 stars · license MIT · pushed 2026-05-19 · branch dev

API

GET https://markdownregistry.com/api/v1/artifacts/art_fjxaheju5h7v5jwm
GET https://markdownregistry.com/api/v1/resolve?ref=alirezarezvani/claudeforge/karpathy-guidelines
GET https://markdownregistry.com/api/v1/blob/acd92adddfb6dfb73279ec61a53648db3696eb9984474855fc8bd840f4644c0d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from alirezarezvani/claudeforge

CLAUDE.md CLAUDE.md file
alirezarezvani/claudeforge · CLAUDE.md
git:20260519.032c5e5 · audit A · 434 stars
CLAUDE.md@agent CLAUDE.md file
alirezarezvani/claudeforge · agent/CLAUDE.md
git:20260519.032c5e5 · audit A · 434 stars
CLAUDE.md@command CLAUDE.md file
alirezarezvani/claudeforge · command/CLAUDE.md
git:20260519.032c5e5 · audit A · 434 stars
CLAUDE.md@docs CLAUDE.md file
alirezarezvani/claudeforge · docs/CLAUDE.md
git:20260519.032c5e5 · audit A · 434 stars
CLAUDE.md@skill CLAUDE.md file
alirezarezvani/claudeforge · skill/CLAUDE.md
git:20260519.032c5e5 · audit A · 434 stars
claude-md-enhancer SKILL.md skill
alirezarezvani/claudeforge · skill/SKILL.md · Analyzes, generates, and enhances CLAUDE.md files for any project type using best practices, modular architecture…
git:20260519.032c5e5 · audit A · 434 stars
claude-md-dependency-rescan SKILL.md skill
alirezarezvani/claudeforge · skill/claude-md-dependency-rescan/SKILL.md · Re-detect this project's tech stack from package.json / requirements.txt / pyproject.toml / go.mod / Cargo.toml and…
git:20260519.032c5e5 · audit A · 434 stars
claude-md-drift-audit SKILL.md skill
alirezarezvani/claudeforge · skill/claude-md-drift-audit/SKILL.md · Audit every CLAUDE.md in this project for drift against the last week of git history. Flags sections that reference…
git:20260519.032c5e5 · audit A · 434 stars
claude-md-link-check SKILL.md skill
alirezarezvani/claudeforge · skill/claude-md-link-check/SKILL.md · Verify every @path chain import and every markdown link inside every CLAUDE.md in this project resolves to an existing…
git:20260519.032c5e5 · audit A · 434 stars

Every file in alirezarezvani/claudeforge

Other files named karpathy-guidelines

karpathy-guidelines SKILL.md skill
multica-ai/andrej-karpathy-skills · skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260128.64723a4 · audit A · 234,317 stars
karpathy-guidelines Cursor rule
multica-ai/andrej-karpathy-skills · .cursor/rules/karpathy-guidelines.mdc · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260418.fb7a22c · audit A · 234,317 stars
karpathy-guidelines SKILL.md skill
yikart/aitoearn · project/aitoearn-web/.agents/skills/karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260623.e3abc45 · audit A · 27,948 stars
karpathy-guidelines SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/karpathy-guidelines/SKILL.md · 提供一组面向编码行为的轻量约束,帮助代理在动手前暴露假设、优先简单方案、保持改动外科化,并把任务改写成可验证目标。 当任务容易被误解、过度设计、顺手扩散改动,或需要先锁定成功标准时使用。
git:20260512.6523792 · audit A · 1,584 stars
karpathy-guidelines SKILL.md skill
coco-research/coco · skills/karpathy-guidelines/SKILL.md · Pointer to the upstream skill for behavioural guidelines that reduce common LLM coding mistakes, installed from…
git:20261008.3d24d40 · audit A · 631 stars
karpathy-guidelines SKILL.md skill
cowork-os/cowork-os · resources/skills/karpathy-guidelines/SKILL.md · Surgical execution guardrails for coding, debugging, review, and refactor tasks
v1.0.0 · audit A · 550 stars
karpathy-guidelines SKILL.md skill
mxyhi/ok-skills · karpathy-guidelines/SKILL.md · Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid…
git:20260508.0cab7e8 · audit A · 516 stars
karpathy-guidelines SKILL.md skill
index-login/mobilere-skill · .kilo/skill/karpathy-guidelines/SKILL.md · 减少 LLM 常见编码错误的行为准则。在编写、审查或重构代码时使用,避免过度设计、精准修改、暴露假设、定义可验证的成功标准。
git:20260803.71f8be9 · audit A · 278 stars

Browse by kind, by grade A, or by owner.