agentmods.dev

karpathy-skills

karpathy-skills is a plugin for Claude Code from LearnPrompt/andrej-karpathy-skills. Its manifest loads nothing; the 15 skills it bundles cost 1,637 tokens per session together, scanned A, original, MIT.

A collection of working methods inspired by Andrej Karpathy's public writing, packaged as instructions for coding agents. It includes approaches for agent development, research, learning, minimalism, and reviewing ideas.

In plain words
What is it for?
Use it to guide agent design, research experiments, learning tasks, project notes, and iterative improvement.
Why use it?
It gives agents reusable ways to approach ambiguous work instead of relying on an unspecified process.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 122repo +2 3mo ago A scan tokens not measured original MIT

Good fit Use it to guide agent design, research experiments, learning tasks, project notes, and iterative improvement.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add LearnPrompt/andrej-karpathy-skills
/plugin install karpathy-skills
View source ↗ LearnPrompt/andrej-karpathy-skills
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for karpathy-skills

README.md
[![agentmods](https://agentmods.dev/badge/plugins/learnprompt/andrej-karpathy-skills/karpathy-skills/github.svg)](https://agentmods.dev/plugins/learnprompt/andrej-karpathy-skills/karpathy-skills)
Your own site
<a href="https://agentmods.dev/plugins/learnprompt/andrej-karpathy-skills/karpathy-skills"><img src="https://agentmods.dev/badge/plugins/learnprompt/andrej-karpathy-skills/karpathy-skills/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for karpathy-skills

Your own site · 80×15
<a href="https://agentmods.dev/plugins/learnprompt/andrej-karpathy-skills/karpathy-skills"><img src="https://agentmods.dev/badge/plugins/learnprompt/andrej-karpathy-skills/karpathy-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 15 skills cost 1,637 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

karpathy-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json#karpathy-skills · 29 lines

What it actually says

{
  "name": "karpathy-skills",
  "description": "14 Karpathy-inspired working methods + 1 methodology router, distilled from his 2023-2026 public X posts and Gists into executable agent skills: agentic-engineering, vibe-to-agentic, autoresearch, llm-simulator, llm-wiki, minimalism, supply-chain-hygiene, understanding-first, idea-files, output-evolution, education-first, system-prompt-learning, practice-environments, meta-reflection. Every skill cites its original source. Unofficial, not endorsed by Andrej Karpathy.",
  "version": "1.0.0",
  "author": {
    "name": "LearnPrompt",
    "url": "https://github.com/LearnPrompt"
  },
  "source": "./",
  "category": "productivity",
  "homepage": "https://github.com/LearnPrompt/andrej-karpathy-skills",
  "skills": [
    "./karpathy-methodology",
    "./karpathy-agentic-engineering",
    "./karpathy-vibe-to-agentic",
    "./karpathy-autoresearch",
    "./karpathy-llm-simulator",
    "./karpathy-llm-wiki",
    "./karpathy-minimalism",
    "./karpathy-supply-chain-hygiene",
    "./karpathy-understanding-first",
    "./karpathy-idea-files",
    "./karpathy-output-evolution",
    "./karpathy-education-first",
    "./karpathy-system-prompt-learning",
    "./karpathy-practice-environments",
    "./karpathy-meta-reflection"
  ]
}
Contents

What it installs

The manifest is a name and a version. 15 skills travel with it, and installing the plugin installs all of them — 1,637 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#karpathy-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 29 lines scan A 051a816e0dab

Subscribe to this mod's changes

karpathy-skills is a plugin published in the GitHub repository LearnPrompt/andrej-karpathy-skills (122 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agentsLearning and teaching
Related

karpathy-skills compared with plugins from other repositories

karpathy-skills next to 6 plugins from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
karpathy-skillsLearnPrompt/andrej-karpathy-skillsPlugin1223mo agoMITA—Claude Code
edulabwy51ai/edulabPlugin1.8k15d agoApache-2.0A—Claude Code
master-skillxr843/Master-skillPlugin4895d agononeA—Claude Code
explainer-videomelodic-software/claude-code-pluginsPlugin29todayMITA—Claude Code
hyphamycelium-cmbse/mycelium-hyphaPlugin122d agoApache-2.0A—Claude Code
understandingbengous/claude-code-pluginsPlugin6yesterdayMITA—Claude Code
unslopimisic/claude-marketplacePlugin121d agoMITA—Claude Code