karpathy-engineer

karpathy-engineer is a skill for Claude Code, Codex from rumotion/ai-agent-project-template. It costs 32 tokens per session (211 once invoked), scanned A, original, MIT.

A set of senior-engineer working rules for coding, debugging, and refactoring. It emphasizes small changes, clear predictions, simple solutions, and checks that show whether the result works.

In plain words
What is it for?
Use it to plan implementation work, diagnose bugs, refactor code, choose the smallest reliable fix, and verify changes with focused checks.
Why use it?
It reduces unnecessary rewrites and abstractions by focusing each change on the requested problem and testing the expected outcome.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to plan implementation work, diagnose bugs, refactor code, choose the smallest reliable fix, and verify changes with focused checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rumotion/ai-agent-project-template/karpathy-engineer
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 rumotion/ai-agent-project-template --skill karpathy-engineer
Clone the repo
git clone --depth 1 https://github.com/rumotion/ai-agent-project-template

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 karpathy-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/rumotion/ai-agent-project-template/karpathy-engineer/github.svg)](https://agentmods.dev/skills/rumotion/ai-agent-project-template/karpathy-engineer)
Your own site
<a href="https://agentmods.dev/skills/rumotion/ai-agent-project-template/karpathy-engineer"><img src="https://agentmods.dev/badge/skills/rumotion/ai-agent-project-template/karpathy-engineer/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 karpathy-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/rumotion/ai-agent-project-template/karpathy-engineer"><img src="https://agentmods.dev/badge/skills/rumotion/ai-agent-project-template/karpathy-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 211 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.
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 $0.00032 $0.00211
Opus 5 $0.00016 $0.00105
Sonnet 5 $0.00006 $0.00042
Haiku 4.5 $0.00003 $0.00021

Measured 8d ago against content hash 8d37244be213, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

karpathy-engineer 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 8d 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.

.agents/skills/karpathy-engineer/SKILL.md · 21 lines

What it actually says

Karpathy Engineer Skill

Use for coding, debugging, refactoring, and review tasks.

Principles:

  1. Think before coding: formulate a falsifiable prediction (state expected failing baseline vs expected passing outcome).
  2. Simplicity first: solve only the request; avoid speculative abstractions.
  3. Surgical changes: touch only necessary lines; preserve surrounding style.
  4. Escalation ladder: solve at the cheapest reliable tier (surgical edit → scratch script → mock harness → model redesign).
  5. Goal-driven execution: define success criteria and verify with the smallest useful check.
  6. Learn from refutations: record dead hypotheses with killing evidence; never retry disproven approaches.

If a change grows beyond the task, stop and explain the tradeoff.

Chains to: code-reviewer after implementing; test-strategist for test design.

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. 8d ago First seen · 21 lines · 0 tokens per session scan A 8d37244be213

Subscribe to this mod's changes

karpathy-engineer is a skill published in the GitHub repository rumotion/ai-agent-project-template (1 stars, last pushed 19d ago), licensed MIT. It adds 32 tokens to every session and 211 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

saas-builder

Clone, verify, map, and build on top of ixartz/SaaS-Boilerplate for a user's SaaS idea. Use when a user wants to reuse SaaS Boilerplate, evaluate how their product fits it, or build product-specific pages, database schema, roles, permissions, MVP features, and launch scope on top of the boilerplate.

ixartz/SaaS-Boilerplate · 75 tokens

dashboard-builder

Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.

winstonkoh87/Athena-Public · 31 tokens

bionic-decision-engine

Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.

winstonkoh87/Athena-Public · 41 tokens

input-systems

Architect game input — action mapping (abstracting keys into named actions), rebinding with conflict detection and persistence, multi-device support (keyboard, gamepad, touch), analog deadzones, and feel features like input buffering and coyote time, plus accessibility. Engine-neutral. Use when the user mentions input…

gamedev-skills/awesome-gamedev-agent-skills · 88 tokens

roblox-luau

Script a Roblox experience in Luau: get services, create and parent Instances, connect events, run server Scripts vs client LocalScripts, and communicate across the client/server boundary with RemoteEvents/RemoteFunctions (server-authoritative). Use when building or debugging Roblox Studio scripts — when the user…

gamedev-skills/awesome-gamedev-agent-skills · 97 tokens

trading-risk-gate

Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.

winstonkoh87/Athena-Public · 53 tokens