What is karpathy-guidelines?

A set of behavioural guidelines for writing, reviewing, and refactoring code. It focuses on avoiding common mistakes, keeping changes small, stating assumptions, and defining checks for success.

Use it when creating, reviewing, or refactoring code to guide decisions, expose assumptions, avoid unnecessary complexity, and establish verification criteria.

It helps keep coding work understandable and limited to what is needed, while making the expected result easier to verify.

karpathy-guidelines — Skill for Claude Code by panamini

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 panamini/Pagecraft --skill karpathy-guidelines

Clone the repo

git clone --depth 1 https://github.com/panamini/Pagecraft

Made for: Claude Code.

Or install pagecraft, the plugin that ships this one along with the rest of its 3 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/panamini/pagecraft/karpathy-guidelines/github.svg)](https://agentmods.dev/skills/panamini/pagecraft/karpathy-guidelines)

Your own site

<a href="https://agentmods.dev/skills/panamini/pagecraft/karpathy-guidelines"><img src="https://agentmods.dev/badge/skills/panamini/pagecraft/karpathy-guidelines/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/panamini/pagecraft/karpathy-guidelines"><img src="https://agentmods.dev/badge/skills/panamini/pagecraft/karpathy-guidelines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 565 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 unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00565
Opus 5	$0.00023	$0.00282
Sonnet 5	$0.00009	$0.00113
Haiku 4.5	$0.00005	$0.00056

Measured 8d ago against content hash 6e22cc54cb02, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

karpathy-guidelines 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.

references/karpathy/skills/karpathy-guidelines/SKILL.md · 68 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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.

8d ago First seen · 68 lines · 46 tokens per session scan A 6e22cc54cb02

Subscribe to this mod's changes

karpathy-guidelines is a skill published in the GitHub repository panamini/Pagecraft (2 stars, last pushed 4mo ago), licensed GPL-3.0. It adds 46 tokens to every session and 565 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.

Code review LLM agents karpathy markdown obsidian pagecraft

cross-review

Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.

omnigent-ai/omnigent · 37 tokens

crit-cli

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…

tomasz-tomczyk/crit · 110 tokens

crit

Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.

tomasz-tomczyk/crit · 55 tokens

karpathy-guidelines