agentmods.dev

karpathy-understanding-first

karpathy-understanding-first is a skill for Claude Code from LearnPrompt/andrej-karpathy-skills. It costs 114 tokens per session (1,611 once invoked), scanned A, original, MIT.

A review method for checking what an AI coding agent built, decided, or wrote, and how well you understand it. It also helps identify tasks where language models are dependable or likely to make hidden mistakes.

In plain words
What is it for?
Use it to review an AI-assisted work session, list its important technical choices, and explain the choices you do not understand. It can also help judge whether an AI-generated answer needs careful checking.
Why use it?
It reduces the risk of shipping code you cannot explain or maintain. It shows which decisions are understood, only partly understood, or still a black box.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the karpathy-skills plugin — 15 skills shipped together

not rated 122repo +2 3mo ago A scan SkillSpector: pass 114 tokens original MIT

Good fit Use it to review an AI-assisted work session, list its important technical choices, and explain the choices you do not understand. It can also help judge whether an AI-generated answer needs careful checking.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/learnprompt/andrej-karpathy-skills/karpathy-understanding-first
View source ↗ LearnPrompt/andrej-karpathy-skills
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-understanding-first
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.

agentmods badge for karpathy-understanding-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-understanding-first/github.svg)](https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-understanding-first)
Your own site
<a href="https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-understanding-first"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-understanding-first/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-understanding-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-understanding-first"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-understanding-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.01611
Opus 5.5 $0.00046 $0.00644
Sonnet 5.5 $0.00023 $0.00322
Haiku 4.5 $0.00011 $0.00161

Measured 2mo ago against content hash 8d4fa98dd4ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

karpathy-understanding-first 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-understanding-first/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill 8: Understanding > Outsourcing（理解 > 外包）

Source: https://x.com/karpathy/status/2049907410303865030 "You can outsource your thinking but you cannot outsource your understanding." — 46k likes Also: Jagged Capabilities Modeling (Sequoia conversation)

Core Principle

Outsourcing is fine. Atrophy is not.

Use AI to go 10x faster. But every time you skip understanding something, you're borrowing from your own future. Understanding compounds. Blindly shipping agent output does not.

Karpathy's "jagged capabilities" insight: LLMs are wildly good at some things (verifiable, high-data domains) and silently wrong at others (off-distribution, novel combinations). You need a mental map of which is which.

The Understanding Audit

After every agent-assisted work session, run this:

I just had an AI help me [DESCRIBE WHAT WAS BUILT/WRITTEN/DECIDED].

Help me audit my own understanding:

1. List the 5 key decisions that were made (technical choices, assumptions, trade-offs)
2. For each decision: would I be able to explain WHY this choice was made to a colleague?
   Mark each: UNDERSTOOD / SHALLOW / BLACK BOX
3. For the BLACK BOX items: give me a 3-sentence explanation I can verify
4. What would I need to read/learn to make the SHALLOW items UNDERSTOOD?

Be honest. If I'm shipping something I don't understand, I need to know.

Jagged Capabilities Map

LLMs are NOT uniformly capable. Use this mental model:

HIGH Reliability (on the rails)

These are well-defined, verifiable, data-rich domains:

  • Code in popular languages (Python, JS, SQL)
  • Text summarization and rewriting
  • Structured data extraction
  • Well-known algorithms
  • Common patterns (REST APIs, SQL queries, regex)

MEDIUM Reliability (use carefully, verify)

  • Less popular languages (Rust, Haskell, Elixir)
  • Integrating multiple systems together
  • Anything involving specific versions/APIs after training cutoff
  • Multi-step reasoning chains
  • Math beyond simple arithmetic

LOW Reliability (always verify independently)

  • Cutting-edge research (may hallucinate papers)
  • Novel combinations of technologies
  • Domain-specific knowledge you can't easily verify
  • Legal/medical/financial specifics
  • Anything where being wrong is expensive

Read the full file on GitHub · 168 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.

  1. 2mo ago First seen · 168 lines · 114 tokens per session scan A 8d4fa98dd4ca

Subscribe to this mod's changes

karpathy-understanding-first is a skill published in the GitHub repository LearnPrompt/andrej-karpathy-skills (122 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 1,611 once invoked, about $0.0005 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.

Learning and teaching
Related

karpathy-understanding-first compared with skills from other repositories

karpathy-understanding-first next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
karpathy-understanding-firstLearnPrompt/andrej-karpathy-skillsSkill1223mo agoMITA114Claude Code
hr-onboardingnexu-io/open-designSkill106ktodayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32ktodayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9ktodayApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19kyesterdayMITA81Claude Code
eli5companion-inc/feynmanSkill10k6d agoMITA63Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.4kyesterdayApache-2.0A25Claude Code, Codex