What is karpathy-vibe-to-agentic?

A step-by-step method for turning a rough, quickly made software prototype into reliable, maintainable code through clear requirements and repeated checks.

Use it to inspect a prototype, document what it does, define success criteria, and guide the remaining development work.

It helps reveal hidden assumptions and close the gap between software that merely seems to work and software that can be understood and verified.

karpathy-vibe-to-agentic — Skill for Claude Code by LearnPrompt

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 LearnPrompt/andrej-karpathy-skills --skill karpathy-vibe-to-agentic

Clone the repo

git clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skills

Made for: Claude Code.

Or install karpathy-skills, the plugin that ships this one along with the rest of its 15 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-vibe-to-agentic/github.svg)](https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-vibe-to-agentic)

Your own site

<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.

Your own site · 80×15

<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>

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,420 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.

Model	Per session	Once invoked
Fable 5.1	$0.00108	$0.01420
Opus 5.5	$0.00043	$0.00568
Sonnet 5.5	$0.00022	$0.00284
Haiku 4.5	$0.00011	$0.00142

Measured 2mo ago against content hash bfec3f4b208f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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.

karpathy-vibe-to-agentic/SKILL.md · 165 lines

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.

Read the full file on GitHub · 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.

2mo ago First seen · 165 lines · 108 tokens per session scan A bfec3f4b208f

Subscribe to this mod's changes

karpathy-vibe-to-agentic is a skill published in the GitHub repository LearnPrompt/andrej-karpathy-skills (122 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 1,420 once invoked, about $0.0004 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.

Planning

karpathy-vibe-to-agentic next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
karpathy-vibe-to-agenticLearnPrompt/andrej-karpathy-skills	Skill	122	3mo ago	MIT	A	108	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code