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-vibe-to-agenticgit 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-vibe-to-agentic)<a href="https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-vibe-to-agentic"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-vibe-to-agentic/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-vibe-to-agentic"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-vibe-to-agentic.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 | $0.00108 | $0.01420 |
| Opus 5 | $0.00054 | $0.00710 |
| Sonnet 5 | $0.00022 | $0.00284 |
| Haiku 4.5 | $0.00011 | $0.00142 |
Grade A, and why
karpathy-vibe-to-agentic 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 5: Vibe Coding → Agentic Leap（Vibe编码 → 代理跃迁）
Source: https://x.com/karpathy/status/2004607146781278521 | https://x.com/karpathy/status/2026731645169185220 "I've never felt this much behind as a programmer" — 56k likes
Core Principle
Vibe coding raises the floor. Agentic engineering raises the ceiling.
They're not the same thing and you need both:
| Vibe Coding | Agentic Engineering | |
|---|---|---|
| Goal | Fast prototype, explore ideas | Reliable, maintainable, verifiable |
| How | Natural language → run it | Task specs + success criteria + loops |
| When | First 20% (exploration) | Last 80% (execution) |
| Risk | You don't understand what you built | Agent doesn't understand what you want |
| Karpathy says | "raises the floor" | "raises the ceiling" |
The Transition Protocol
When you have a vibe-coded prototype and need to level it up:
Step 1: Audit What You Built
I vibe-coded this [project/script/app]. I need to understand what I actually have before leveling it up.
[PASTE CODE OR DESCRIBE IT]
Please:
1. Describe exactly what this does in plain English (3-5 sentences)
2. List every assumption baked in (hardcoded values, expected input format, etc.)
3. Identify the 3 most likely failure modes
4. List what's missing for this to be production-ready
5. What would break if I ran this on a different machine / with different data?
Be blunt. I'm about to invest more time in this and need to know if it's worth it.
Step 2: Define Success Criteria
Based on this audit of my prototype:
[AUDIT OUTPUT FROM STEP 1]
Help me define clear, verifiable success criteria for the "production-ready" version.
Format each criterion as a testable assertion:
- GIVEN [input/condition]
- WHEN [action]
- THEN [expected output/behavior]
List 5-7 criteria. Start with the most important.
Step 3: Agentic Cleanup Loop
You are a senior engineer reviewing this prototype. Your job is to systematically improve it.
Prototype: [CODE]
Success criteria: [FROM STEP 2]
Work incrementally:
1. First fix: address the most critical issue only (one diff)
2. After I approve each fix, suggest the next
3. Never refactor unrelated code
4. For each fix, explain: WHAT changed, WHY this matters, RISK of this change
Start with fix #1.
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 · 165 lines · 108 tokens per session scan A bfec3f4b208f
karpathy-vibe-to-agentic is a skill published in the GitHub repository LearnPrompt/andrej-karpathy-skills (97 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 1,420 once invoked, about $0.0005 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…
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…