Karpathy Agentic Engineering

What it does

When your agent uses it

• The user wants to set up an agent-driven workflow
• Needs to write a CLAUDE.md
• Wants to orchestrate agents with clear success criteria
• Says things like agent loop

Example prompts

• “agent loop”
• “let the agent handle it”
• “agentic coding”
• “/karpathy-agentic-engineering”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Stuff context — Load entire project into context (files-to-prompt, relevant docs, recent diffs)
2. 2Discuss plan — Ask agent for high-level approaches with pros/cons before any code
3. 3Request first draft — Pick one approach, get a minimal first implementation
4. 4Inline learning — Manually review the diff; ask agent to explain any API you don't recognize
5. 5Test — Run tests, check outputs, verify success criteria
6. 6Commit — Only commit what you understand and have verified
7. 7Ask for next — Let agent suggest the next incremental step

What it can do on your machine

Read from SKILL.md and the folder at commit 9e46dec. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • x.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Karpathy Agentic Engineering loads about 1.2k tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 306 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~110

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LearnPrompt/andrej-karpathy-skills at commit 9e46dec, republished under its MIT licence (© LearnPrompt). 306 words, ~1,224 tokens.

name

karpathy-agentic-engineering

description

Apply Karpathy-style agentic engineering to any coding or building task. Use this skill when the user wants to set up an agent-driven workflow, needs to write a CLAUDE.md or AGENTS.md, wants to orchestrate agents with clear success criteria, or says things like "agent loop", "let the agent handle it", "agentic coding", "set up agent workflow". Includes the 7-step inner loop from Karpathy claude coding notes.

disable-model-invocation

false

user-invocable

true

related_skills

karpathy-idea-files, karpathy-minimalism, karpathy-supply-chain-hygiene, karpathy-vibe-to-agentic, karpathy-understanding-first

# Agent Instructions for [Project Name]

## Behavior Rules
- Make one incremental change at a time. Do NOT refactor unrelated code.
- Always explain WHY you're making a change before the diff.
- If unsure about intent, ASK before implementing.
- Do NOT add new dependencies without explicit approval.
- Prefer simple, readable solutions over clever ones.

## Success Criteria (task-specific — fill in per session)
- [ ] Tests pass: `[test command]`
- [ ] No new lint errors: `[lint command]`
- [ ] Behavior matches: [description of expected output]

## Project Context
- Stack: [language, framework, key libs]
- Entry point: [file]
- Test command: [command]
- Forbidden: [list things agent must never do]

You are an agentic engineer on this project.

Project context: [paste relevant files or use files-to-prompt output]

Task: [specific, unambiguous description]

Success criteria (ALL must be true when done):
1. [verifiable check 1]
2. [verifiable check 2]
3. [verifiable check 3]

Constraints:
- Only change files relevant to this task
- No new dependencies without asking
- Output: one incremental diff at a time

Start by proposing a high-level plan with 2-3 options and trade-offs. Wait for approval before writing code.

You are an agentic engineer. Project context: <files, constraints, current state>. Task: <specific goal>. Success criteria: <verifiable checklist>. First propose a high-level plan with tradeoffs. Then make only the next incremental change. After each change, run the relevant verification and report: changed files, evidence of success, remaining risk, and next step.

© LearnPrompt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in karpathy-agentic-engineering of LearnPrompt/andrej-karpathy-skills.

Open the folder on GitHubat commit 9e46dec