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 tranfu-labs/tranfu-skills --skill andrej-karpathy-skillsgit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/andrej-karpathy-skills)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/andrej-karpathy-skills"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/andrej-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.
<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/andrej-karpathy-skills"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/andrej-karpathy-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.01029 |
| Opus 5 | $0.00032 | $0.00515 |
| Sonnet 5 | $0.00013 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
andrej-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 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.
What it actually says
andrej-karpathy-skills (external thin pointer)
这是一个 external 薄指针 —— 仓库里只存 frontmatter 和推荐者补充内容，不存 skill body.
首次 install-skill 时, install 流程会从 source_url 拉最新内容到本地 ~/.claude/skills/andrej-karpathy-skills/, 并把这里的元数据回写为 stub.
- 上游: https://github.com/multica-ai/andrej-karpathy-skills
- License: MIT
更新内容请直接看上游 README / SKILL.md, 别在本仓库改 body.
推荐场景
适用:
- 设计自己的 CLAUDE.md 或项目级指令时，参考 Karpathy 的观察避免常见陷阱
- 作为 Claude Code 的基础行为层，让 AI 更少过度工程、乱改无关代码
- 给新接触 Claude Code 的同事一份行为准则，减少磨合期
不适用: hackathon 快速原型 / throwaway 探索性代码，准则偏保守可能拖慢速度.
同类 Skill 对比
由 publish-skill 起草, 推荐者签字. 帮助阅读者横向决定要装哪个 / 跳到更合适的同类.
公司库内
- openspec — 多轮迭代项目规范管理，用 /opsx 命令拆 change；本 skill 区别: 不管理项目结构，直接约束 AI 行为本身，任何规模的项目都适用
- skill-reverse-engineer — 审计和改进 skill 文件；本 skill 区别: 不是工具，是行为准则，目标受众是终端用户而非 skill 作者
外部世界
- cursorules — 汇集 Cursor IDE 规则；本 skill 区别: 更聚焦 Andrej Karpathy 的编码哲学，不是工具罗列而是原则性约束
- awesome-claude-prompts — Claude 提示词合集；本 skill 区别: 不是提示词模板，而是融入工作流的底层行为准则
本 skill 独特价值
- Andrej Karpathy 亲自观察总结的 LLM 编码陷阱，有权威性背书
- 单文件零依赖，安装即生效，无需学习额外命令
- 直接减少 AI 过度工程、乱改无关代码等高频痛点
使用技巧
由 publish-skill 引导起草 (作者/推荐者答, AI 整合, 推荐者签字). 帮助阅读者纵向上手 — tacit knowledge 在此. 横向同类对比见上方 §同类 Skill 对比.
材料方案
- 考虑过直接复制准则到项目 CLAUDE.md vs 用独立 skill → 选独立 skill 可跨项目复用，避免重复粘贴
- 考虑过配合其他代码规范 skill 使用 → 本 skill 作为底层行为层，其他 skill 作为工具层，互补不冲突
推荐用法
- 安装后自动生效，无需特殊触发语，每次对话自动约束 AI 行为
- 可叠加项目级 CLAUDE.md 使用，在项目级补充领域知识，不重复写行为准则
- 推荐给新接触 Claude Code 的同事，减少"AI 乱改代码"的磨合期
已知限制
- 偏保守风格，hackathon 快速原型或探索性场景可能不适用
- 仅影响 Claude Code，Cursor / Copilot 等其他 AI 工具需单独适配
- 准则本身不解决具体技术问题，需配合领域 skill 使用
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 · 66 lines · 65 tokens per session scan A 71bd5e98c791
andrej-karpathy-skills is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 1,029 once invoked, about $0.0003 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…