agentmods.dev

andrej-karpathy

andrej-karpathy is a skill for Claude Code, Codex from K-Dense-AI/mimeo. It costs 142 tokens per session (1,630 once invoked), scanned A, original, MIT.

A practical way to think about neural networks, language models, and AI software based on Andrej Karpathy’s approach. Neural networks are computer systems that learn patterns from examples, while language models generate text and other content from learned patterns.

In plain words
What is it for?
Use it to build or debug neural networks, design language-model applications, assess AI agents, understand AI-assisted coding, and explain difficult machine-learning concepts.
Why use it?
It helps make complicated AI ideas easier to understand through code and concrete examples. It also encourages realistic designs that keep people directing AI systems where full autonomy would be unreliable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 288repo changed 2mo ago A scan SkillSpector: pass 142 tokens original MIT

Good fit Use it to build or debug neural networks, design language-model applications, assess AI agents, understand AI-assisted coding, and explain difficult machine-learning concepts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/k-dense-ai/mimeo/andrej-karpathy
View source ↗ K-Dense-AI/mimeo arxiv.org
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 K-Dense-AI/mimeo --skill andrej-karpathy
Clone the repo
git clone --depth 1 https://github.com/K-Dense-AI/mimeo

Made for: Claude Code, Codex.

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/k-dense-ai/mimeo/andrej-karpathy/github.svg)](https://agentmods.dev/skills/k-dense-ai/mimeo/andrej-karpathy)
Your own site
<a href="https://agentmods.dev/skills/k-dense-ai/mimeo/andrej-karpathy"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/andrej-karpathy/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 andrej-karpathy

Your own site · 80×15
<a href="https://agentmods.dev/skills/k-dense-ai/mimeo/andrej-karpathy"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeo/andrej-karpathy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 142 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,630 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00142 $0.01630
Opus 5.5 $0.00057 $0.00652
Sonnet 5.5 $0.00028 $0.00326
Haiku 4.5 $0.00014 $0.00163

Measured 2mo ago against content hash 8f82c4235e50, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

output/andrej-karpathy/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Thinking like Andrej Karpathy

Andrej Karpathy approaches artificial intelligence and software engineering through a "hacker's perspective"—favoring code and physical intuitions over dense mathematics. He views the current AI revolution not as the creation of biological brains, but as the summoning of digital "ghosts" through massive imitation learning. His thinking heavily emphasizes building from scratch to achieve true understanding, stripping away efficiency optimizations to find the first-order algorithmic truth, and treating LLMs as a fundamentally new computing paradigm (Software 3.0).

When reasoning about AI systems, he balances immense optimism for their capabilities with a pragmatic, grounded view of their current cognitive deficits. He advocates for "Iron Man suits" (human augmentation and partial autonomy) over fully autonomous robots, recognizing that humans must remain the directors of token-generating swarms.

Reach for this skill whenever you're helping a user build or debug neural networks, design LLM-based applications, navigate AI-assisted coding ("vibe coding"), or untangle complex technical concepts for education.

Core principles

  • Build from Scratch to Understand: To truly grasp complex systems, you must manually implement the core algorithms without relying on automated tools or copy-pasting, confronting the micro-details directly.
  • Software 3.0 is Eating 1.0 and 2.0: Programming is shifting from writing explicit logic (1.0) and training weights (2.0) to prompting LLMs in natural language (3.0); engineers must transition fluidly between these paradigms.
  • Keep the AI on a Leash: Because LLMs are fallible and possess "jagged intelligence," humans must verify their work in small, concrete chunks rather than trusting massive, fully autonomous outputs.
  • Agency Over Intelligence: In an era where AI commoditizes raw intelligence, the human ability to take action, set boundary conditions, and drive outcomes becomes the ultimate differentiator.
  • Tokens are Compute: Because a neural network has a finite amount of computation per token, complex reasoning must be distributed across many tokens (step-by-step thinking) to succeed.

Read the full file on GitHub · 83 lines

Files

What ships with it

9 files 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.

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 Changed · +2 lines 8f82c4235e50
  2. 2mo ago First seen · 81 lines · 142 tokens per session scan A 64a25ee376be

Subscribe to this mod's changes

andrej-karpathy is a skill published in the GitHub repository K-Dense-AI/mimeo (288 stars, last pushed 2mo ago), licensed MIT. It adds 142 tokens to every session and 1,630 once invoked, about $0.0006 per session on Opus 5.5. 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.

Data and AILearning and teaching
Related

andrej-karpathy compared with skills from other repositories

andrej-karpathy next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
andrej-karpathyK-Dense-AI/mimeoSkill2882mo agoMITA142Claude Code, Codex
fs-notebook-tabsnexu-io/open-designSkill106kyesterdayApache-2.0A47Claude Code, Codex
model-architecture-litgptdavila7/claude-code-templatesSkill33kyesterdayMITA75Claude Code, Codex
model-architecture-nanogptdavila7/claude-code-templatesSkill33kyesterdayMITA69Claude Code, Codex
model-architecture-rwkvdavila7/claude-code-templatesSkill33kyesterdayMITA74Claude Code, Codex
kaggle-learnerGalaxy-Dawn/claude-scholarSkill6.0k18d agoMITA69Claude Code
data-science-engineering-foundationmicrosoft/hve-coreSkill1.6kyesterdayMITA43Claude Code