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.
npx skills add LearnPrompt/andrej-karpathy-skills --skill karpathy-methodologygit clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skillsWrote 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.
[](https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-methodology)<a href="https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-methodology"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-methodology/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.
<a href="https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-methodology"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.01580 |
| Opus 5 | $0.00060 | $0.00790 |
| Sonnet 5 | $0.00024 | $0.00316 |
| Haiku 4.5 | $0.00012 | $0.00158 |
Grade A, and why
karpathy-methodology 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Karpathy Methodology — 14 Core Skills
Distilled from Andrej Karpathy's most-liked posts on X (2023–2026), his LLM Wiki Gist, and the multica-ai/andrej-karpathy-skills repo. Source: https://x.com/karpathy | https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f
This skill is the master index. When invoked, either:
- Apply the specific sub-methodology relevant to the user's current task, or
- Guide the user to the right one from the 14 below.
The 14 Methodologies
| # | Skill Name | One-line Essence |
|---|---|---|
| 1 | karpathy-agentic-engineering |
Orchestrate agents with clear tasks and verifiable success criteria |
| 2 | karpathy-llm-wiki |
Let LLM maintain your knowledge base; you do the exploring |
| 3 | karpathy-llm-simulator |
Ask LLM to simulate expert debate, not give one opinion |
| 4 | karpathy-minimalism |
200 lines of pure Python beats 50 npm packages |
| 5 | karpathy-vibe-to-agentic |
Vibe coding raises the floor; agentic engineering raises the ceiling |
| 6 | karpathy-autoresearch |
Agent loops on git branches; you only change the prompt |
| 7 | karpathy-output-evolution |
Text → Markdown → HTML → rendered; always demand structure |
| 8 | karpathy-understanding-first |
Outsource thinking, never understanding |
| 9 | karpathy-idea-files |
Ship the Gist (abstract + criteria), not the code |
| 10 | karpathy-meta-reflection |
Monthly audit: what's atrophying, what's exploding |
| 11 | karpathy-supply-chain-hygiene |
Every dependency is an attack surface |
| 12 | karpathy-education-first |
Make everything teachable; nano-projects over monoliths |
| 13 | karpathy-system-prompt-learning |
Write strategy into the system prompt like a textbook |
| 14 | karpathy-practice-environments |
Build gyms where agents can try, fail, and learn |
Meta-Principle (the one that unifies all 14)
"You can outsource your thinking but you cannot outsource your understanding." — Karpathy, ~46k likes, 2026
What ships with it
1 file beside SKILL.md 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.
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.
- 12d ago First seen · 115 lines · 119 tokens per session scan A 69d07916090b
karpathy-methodology is a skill published in the GitHub repository LearnPrompt/andrej-karpathy-skills (97 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 1,580 once invoked, about $0.0006 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…