New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Karpathy Review

by hamzafarooq in hamzafarooq/claude-code-starter

Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship.

MITAuto-check passedDevelopment

Install Karpathy Review

skills CLI
$ npx skills add hamzafarooq/claude-code-starter --skill karpathy-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hamzafarooq/claude-code-starter karpathy-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hamzafarooq/claude-code-starter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/karpathy-review .claude/skills/karpathy-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
karpathy-review
GitHub stars
145
Token cost
~560 tokens
SKILL.md length
248 words
Files
1
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship.

  • Works in 4 steps: Think Before Coding — were assumptions… → Simplicity First — is this the minimal… → Surgical Changes — does it stay in its… → …
  • The user wants a sanity check on code
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Code review

What it does

Karpathy Review is an agent skill from hamzafarooq/claude-code-starter. Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship. Use when the user wants a sanity check on code, a plan, or a feature spec.

Its SKILL.md is about 560 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review, Code simplification and PRD writing. The licence is MIT.

When your agent uses it

  • The user wants a sanity check on code
  • Tasks that involve Code review
  • Tasks that involve Code simplification

Example prompts

  • “/karpathy-review”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Think Before Coding — were assumptions stated?
  2. Simplicity First — is this the minimal solution?
  3. Surgical Changes — does it stay in its lane?
  4. Goal-Driven Execution — is success verifiable?

What it can do on your machine

Read from SKILL.md and the folder at commit 172c531. 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.

    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
    • github.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 Review loads about 560 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 248 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~560

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 hamzafarooq/claude-code-starter at commit 172c531, republished under its MIT licence (© hamzafarooq). 248 words, ~560 tokens.

Download SKILL.mdSave it as .claude/skills/karpathy-review/SKILL.md (or your agent's skills folder).
name
karpathy-review
description
Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship. Use when the user wants a sanity check on code, a plan, or a feature spec.

Review the provided code, plan, or spec against Karpathy's four principles. Credit: guidelines distilled from Andrej Karpathy's January 2026 observations, adapted by Forrest Chang.

Ask the user: "Paste the code, plan, or spec you want reviewed."

Then score it against each principle:

Karpathy Review

1. Think Before Coding — were assumptions stated?
  • Did the solution state its assumptions explicitly, or pick silently between interpretations?
  • Are there any unclear requirements that should have triggered a clarifying question?
  • Finding: PASS / FLAG — [specific observation]
2. Simplicity First — is this the minimal solution?
  • Does it add features beyond what was asked?
  • Are there abstractions written for single-use code?
  • Is there "flexibility" or "configurability" that wasn't requested?
  • Could this be meaningfully shorter?
  • Finding: PASS / FLAG — [specific observation, e.g. "This 180-line class could be a 20-line function"]
3. Surgical Changes — does it stay in its lane?
  • Does it modify adjacent code, formatting, or comments that weren't part of the task?
  • Does it refactor things that weren't broken?
  • Does it delete pre-existing code that wasn't asked to be removed?
  • Finding: PASS / FLAG — [specific observation]
4. Goal-Driven Execution — is success verifiable?
  • Is there a clear success criterion?
  • For multi-step work: was a plan stated with checkpoints?
  • Is there a way to verify the output without running it?
  • Finding: PASS / FLAG — [specific observation]
Verdict
PrincipleResult
Think before coding✅ PASS / ⚠️ FLAG
Simplicity first✅ PASS / ⚠️ FLAG
Surgical changes✅ PASS / ⚠️ FLAG
Goal-driven execution✅ PASS / ⚠️ FLAG

One thing to fix: [If any flags, name the single most important change to make]

© hamzafarooq, 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 .claude/skills/karpathy-review of hamzafarooq/claude-code-starter.

Open the folder on GitHubat commit 172c531

Compare with similar skills

Karpathy Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Karpathy Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Karpathy Review this skillhamzafarooq/claude-code-starter145—~560Automated safety check: PassMIT
Over-Engineering ReviewDietrichGebert/ponytail160k—~1.3kAutomated safety check: PassMIT
Astro Code Reviewwithastro/astro63k—~7.6kAutomated safety check: PassCustom licence
Chisle ReviewJayPokale/Chisle640—~362Automated safety check: PassMIT
Spec App Consistency Auditleo-kuang-ai/spec-first107—~4.6kAutomated safety check: PassMIT
Pragmatic Reviewheyitsnoah/claudesidian2.6k—~2.6kAutomated safety check: PassMIT

Similar skills

  • Over-Engineering Review

    DietrichGebert/ponytail

    Reviews a diff only for unnecessary complexity and lists what to delete or shrink, one numbered line per finding with the location, the cut and its replacement.

    160k GitHub stars~1.3k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Astro Code Review

    withastro/astro

    Official

    Perform a static, read-only code review of an Astro pull request or of a local branch, commit range, diff, patch, or working tree being prepared as a pull request.

    63k GitHub stars~7.6k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Chisle Review

    JayPokale/Chisle

    Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink.

    640 GitHub stars~362 tokensUpdated 4 days ago
    DevelopmentAuto-check passed

  • Spec App Consistency Audit

    leo-kuang-ai/spec-first

    Audit mobile App PRD/Figma/local-source consistency across page routes, KMP/Clean Architecture, components, analytics, i18n, engineering quality, and industry lenses before runtime validation; use…

    107 GitHub stars~4.6k tokensUpdated 2 days ago
    DevelopmentAuto-check passed

  • Pragmatic Review

    heyitsnoah/claudesidian

    Interactive pragmatic code review focusing on YAGNI and KISS principles.

    2.6k GitHub stars~2.6k tokensUpdated 6 mo ago
    DevelopmentAuto-check passed

  • Elegance-Focused Code Review

    eric-tramel/moraine

    Looks at a pull request for the smallest good design, hunting for simplifications and architectural moves that remove whole classes of problems.

    117 GitHub stars~473 tokensUpdated today
    DevelopmentAuto-check passed

More from hamzafarooq/claude-code-starter

All 29 skills in this repo

  • Beautiful HTML

    hamzafarooq/claude-code-starter

    Turn any document, proposal, report, or outline into a stunning single-file HTML presentation using 34 pre-built professional templates.

    145 GitHub stars~1.6k tokensUpdated 27 days ago
    Auto-check passed

  • Claude Code Deck

    hamzafarooq/claude-code-starter

    Generate a complete, ready-to-share HTML presentation explaining Claude Code, Skills, Sub Agents, Hooks, and Multi-Agent Systems — designed for product managers.

    145 GitHub stars~972 tokensUpdated 27 days ago
    Auto-check passed

  • Competitor Research

    hamzafarooq/claude-code-starter

    Research 3–5 competitors for any product or feature. An agent skill from hamzafarooq/claude-code-starter.

    145 GitHub stars~1.6k tokensUpdated 27 days ago
    Auto-check passed

  • Frontend Slides

    hamzafarooq/claude-code-starter

    Create stunning, animation-rich single-file HTML presentations from scratch or by converting a PowerPoint (.pptx) file.

    145 GitHub stars~1.4k tokensUpdated 27 days ago
    Auto-check passed

  • Md To PDF

    hamzafarooq/claude-code-starter

    Convert any markdown file to a clean PDF. An agent skill from hamzafarooq/claude-code-starter.

    145 GitHub stars~598 tokensUpdated 27 days ago
    Auto-check passed

  • User Story Writer

    hamzafarooq/claude-code-starter

    Converts feature ideas or rough bullets into user stories with acceptance criteria.

    145 GitHub stars~531 tokensUpdated 27 days ago
    Auto-check passed

Categories

Questions about Karpathy Review

What does Karpathy Review do?

Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship. Karpathy Review is an agent skill from hamzafarooq/claude-code-starter. Review code or a plan against Andrej Karpathy's LLM coding principles — catch over-engineering, silent assumptions, unnecessary abstractions, and scope creep before they ship.

When should I use Karpathy Review?

Karpathy Review fits situations like: the user wants a sanity check on code; tasks that involve Code review; tasks that involve Code simplification.

How do I install Karpathy Review in Claude Code?

Run `npx skills add hamzafarooq/claude-code-starter --skill karpathy-review -a claude-code`. Or copy the skill folder (.claude/skills/karpathy-review in hamzafarooq/claude-code-starter) into .claude/skills/karpathy-review in your project. Claude Code loads it when a task matches its description.

How do I install Karpathy Review in Codex?

Run `npx skills add hamzafarooq/claude-code-starter --skill karpathy-review -a codex`. Or copy the skill folder (.claude/skills/karpathy-review in hamzafarooq/claude-code-starter) into .agents/skills/karpathy-review in your project. Codex loads it when a task matches its description.

Can I use Karpathy Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hamzafarooq/claude-code-starter --skill karpathy-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/karpathy-review, .gemini/skills/karpathy-review, .github/skills/karpathy-review and .opencode/skills/karpathy-review in your project.

What does Karpathy Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Karpathy Review is instructions for the agent only.

Does Karpathy Review access the network?

SKILL.md names 2 domains. As links in the text: x.com and github.com. This is read from the text; nothing was executed.

Is Karpathy Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Karpathy Review use?

Karpathy Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Karpathy Review use?

About 560 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Karpathy Review?

Skills that share tags, products or a category with Karpathy Review: Over-Engineering Review (DietrichGebert/ponytail, 160k stars), Astro Code Review (withastro/astro, 63k stars), Chisle Review (JayPokale/Chisle, 640 stars) and Spec App Consistency Audit (leo-kuang-ai/spec-first, 107 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Karpathy Review?

hamzafarooq (a GitHub user) maintains it in hamzafarooq/claude-code-starter, which has 145 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on September 13, 2026.

Source: hamzafarooq/claude-code-starter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.