agentmods.dev

karpathy-check

karpathy-check is a command for Claude Code from ricneves-ai/flowgrammers-skills. It costs 62 tokens per session (474 once invoked), scanned A, original, MIT.

A code-review command that examines staged changes or the latest commit using four principles associated with Andrej Karpathy: clear thinking, simplicity, focused changes, and checking the result against the goal.

In plain words
What is it for?
Use it to inspect changed files, detect over-engineering and unrelated edits, and receive specific recommendations for correcting issues in the diff.
Why use it?
It helps catch unnecessary complexity, noisy diffs, hidden assumptions, and missing verification before code is committed or submitted for review.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

not rated 112repo +3 3mo ago A scan 62 tokens original MIT

Good fit Use it to inspect changed files, detect over-engineering and unrelated edits, and receive specific recommendations for correcting issues in the diff.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ricneves-ai/flowgrammers-skills/karpathy-check
View source ↗ ricneves-ai/flowgrammers-skills flowgrammers.com.br
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.

Clone the repo
git clone --depth 1 https://github.com/ricneves-ai/flowgrammers-skills

Made for: Claude Code.

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-check

README.md
[![agentmods](https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/karpathy-check/github.svg)](https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/karpathy-check)
Your own site
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/karpathy-check"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/karpathy-check/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-check

Your own site · 80×15
<a href="https://agentmods.dev/commands/ricneves-ai/flowgrammers-skills/karpathy-check"><img src="https://agentmods.dev/badge/commands/ricneves-ai/flowgrammers-skills/karpathy-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 474 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 $0.00062 $0.00474
Opus 5 $0.00031 $0.00237
Sonnet 5 $0.00012 $0.00095
Haiku 4.5 $0.00006 $0.00047

Measured 8d ago against content hash e6a98c059496, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

karpathy-check 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.

commands/karpathy-check.md · 47 lines

What it actually says

/karpathy-check

Revisa suas alterações em stage (ou o último commit) com base nos 4 princípios de codificação do Karpathy.

Uso

/karpathy-check                 # revisa alterações em stage
/karpathy-check --last-commit   # revisa o commit mais recente

O que executa

  1. Princípio #2 (Simplicidade): scripts/complexity_checker.py em todos os arquivos alterados — detecta over-engineering, abstrações prematuras, aninhamento profundo, funções longas
  2. Princípio #3 (Cirúrgico): scripts/diff_surgeon.py no diff — detecta alterações apenas em comentários, ruído de espaços em branco, desvio de estilo, refatorações oportunistas
  3. Princípios #1 + #4 (Pensar + Objetivos): O agente karpathy-reviewer lê o diff e aplica verificações de julgamento humano — suposições ocultas, verificação ausente

Saída

Um relatório estruturado com veredictos por princípio e recomendações específicas de correção por linha.

Quando executar

  • Antes de commitar (detecta ruído e complicações desnecessárias cedo)
  • Após completar uma feature (verificação de sanidade antes do PR)
  • Quando você suspeita que o LLM produziu código em excesso

Sub-agente

Despacha o agente karpathy-reviewer. Veja agents/karpathy-reviewer.md.

Scripts

  • engineering/karpathy-coder/scripts/complexity_checker.py
  • engineering/karpathy-coder/scripts/diff_surgeon.py
  • engineering/karpathy-coder/scripts/assumption_linter.py
  • engineering/karpathy-coder/scripts/goal_verifier.py

Referência de Skill

→ engineering/karpathy-coder/SKILL.md

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 · 47 lines · 0 tokens per session scan A e6a98c059496

Subscribe to this mod's changes

karpathy-check is a command published in the GitHub repository ricneves-ai/flowgrammers-skills (112 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 474 once invoked, about $0.0003 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 2026-09-03.

Code reviewCommitsGit and workflow
Related

Other commands, from other repositories

review-diff

Review the current working diff for correctness, security, and reuse.

ruvnet/RuView · 13 tokens

elegant-code-review

Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.

athola/claude-night-market · 27 tokens

git

The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.

azrtydxb/procoder · 20 tokens

prp-commit

Quick commit with natural language file targeting: describe what to commit in plain English.

Fmarzochi/EGC · 15 tokens

validate-pr-description

Use when validating a PR title and description for conventional commit format, issue linking keywords, and template compliance before submission.

rjmurillo/ai-agents · 22 tokens

fix-comments

Address PR review comments by implementing requested changes automatically.

rohitg00/awesome-claude-code-toolkit · 13 tokens