andrej-karpathy

andrej-karpathy is a skill for Claude Code from satnamrsm/https-github.com-sickn33-antigravity-awesome-skills. It costs 54 tokens per session (12,648 once invoked), scanned A, a copy of andrej-karpathy, MIT.

A teaching-focused conversational guide modeled on Andrej Karpathy’s publicly known work in artificial intelligence and deep learning. Deep learning is a way of training neural networks to learn patterns from data.

In plain words
What is it for?
Use it to learn deep learning, neural networks, large language models, tokenization, scaling laws, AI software, autonomous cars, AI education, and hands-on neural-network implementation.
Why use it?
It gives learners a focused way to explore difficult AI topics from first principles. The supplied material positions it for explanations and practical guidance rather than general-purpose assistance.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex; mentions Gemini CLI.

Part of the antigravity-awesome-skills plugin — 198 skills shipped together

Good fit Use it to learn deep learning, neural networks, large language models, tokenization, scaling laws, AI software, autonomous cars, AI education, and hands-on neural-network implementation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/satnamrsm/https-github.com-sickn33-antigravity-awesome-skills/andrej-karpathy
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.

Any agent
npx skills add satnamrsm/https-github.com-sickn33-antigravity-awesome-skills --skill andrej-karpathy
Clone the repo
git clone --depth 1 https://github.com/satnamrsm/https-github.com-sickn33-antigravity-awesome-skills

Made for: Claude Code.

Or install antigravity-awesome-skills, the plugin that ships this one along with the rest of its 198 skills.

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 andrej-karpathy

README.md
[![agentmods](https://agentmods.dev/badge/skills/satnamrsm/https-github.com-sickn33-antigravity-awesome-skills/andrej-karpathy.svg)](https://agentmods.dev/skills/satnamrsm/https-github.com-sickn33-antigravity-awesome-skills/andrej-karpathy)
Your own site
<a href="https://agentmods.dev/skills/satnamrsm/https-github.com-sickn33-antigravity-awesome-skills/andrej-karpathy"><img src="https://agentmods.dev/badge/skills/satnamrsm/https-github.com-sickn33-antigravity-awesome-skills/andrej-karpathy.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,648 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 95% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.12648
Opus 5 $0.00027 $0.06324
Sonnet 5 $0.00011 $0.02530
Haiku 4.5 $0.00005 $0.01265

Measured 8d ago against content hash 60215c429a71, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

andrej-karpathy 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 8d 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.

Origin

This is a copy

95% identical to andrej-karpathy — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/andrej-karpathy/SKILL.md · 1,165 lines

How it starts

The opening of the file, as written. The whole thing — 1,165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ANDREJ KARPATHY — SKILL COMPLETA v2.0

Overview

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo. Use quando quiser: aprender deep learning do zero, entender LLMs de forma profunda, perspectivas sobre Software 2.0, carros autônomos, educação em IA, como implementar NNs na prática, vibe coding, tokenização, scaling laws.

When to Use This Skill

  • When the user mentions "karpathy" or related topics
  • When the user mentions "andrej" or related topics
  • When the user mentions "andrej karpathy" or related topics
  • When the user mentions "deep learning do zero" or related topics
  • When the user mentions "redes neurais do zero" or related topics
  • When the user mentions "entender LLMs" or related topics

Do Not Use This Skill When

  • The task is unrelated to andrej karpathy
  • A simpler, more specific tool can handle the request
  • The user needs general-purpose assistance without domain expertise

How It Works

Simular Andrej Karpathy como interlocutor: o educador que constrói tudo do zero, o pesquisador que explica com clareza cirúrgica, o entusiasta que genuinamente adora cada detalhe de como as redes neurais funcionam. Quando esta skill for ativada, responder no estilo de Karpathy: técnico mas acessível, com código quando necessário, com analogias precisas, com honestidade sobre incertezas.

O objetivo desta skill não é ser uma enciclopédia sobre Karpathy — é capturar sua forma de pensar, ensinar, e raciocinar sobre problemas de IA.


Quem É Andrej Karpathy

Andrej Karpathy nasceu em 1986 em Bratislava, então Checoslováquia (hoje Eslováquia). A família emigrou para Toronto quando ele era criança. Fez bacharelado em Ciência da Computação e Física na University of Toronto, onde cruzou com o grupo de Geoffrey Hinton — uma das sementes que moldaram sua trajetória.

Doutorado em Stanford (2011–2015) sob orientação de Fei-Fei Li. A tese: "Connecting Images and Natural Language" — trabalho sobre image captioning usando RNNs, resolvendo um problema que a comunidade considerava extremamente difícil na época. Ele estava na intersecção de visão computacional e NLP antes de isso ser mainstream.

Read the full file on GitHub · 1,165 lines

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. 8d ago First seen · 1,165 lines · 54 tokens per session scan A 60215c429a71

Subscribe to this mod's changes

andrej-karpathy is a skill published in the GitHub repository satnamrsm/https-github.com-sickn33-antigravity-awesome-skills (5 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 12,648 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to andrej-karpathy, differing in 4 lines, and is treated as a copy.

Related

Other skills, from other repositories

andrej-karpathy-v2

ANDREJ KARPATHY — SKILL COMPLETA v2.0 workflow skill. Use this skill when the user needs Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo and the operator should preserve the upstream workflow, copied support…

diegosouzapw/awesome-omni-skills · 94 tokens

andrej-karpathy

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

henryalouf/ruflow · 47 tokens

andrej-karpathy

ANDREJ KARPATHY — SKILL COMPLETA v2.0 workflow skill. Use this skill when the user needs Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo and the operator should preserve the upstream workflow, copied support…

diegosouzapw/awesome-omni-skills · 92 tokens

andrej-karpathy

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

pinkpixel-dev/skills-collection-1 · 47 tokens

andrej-karpathy

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

marysatasselshaped667/skills-collection-1 · 47 tokens

andrej-karpathy

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

kench001/antigravity-awesome-skills · 47 tokens