karpathy-wiki-read

karpathy-wiki-read is a skill for Claude Code from toolboxmd/karpathy-wiki. It costs 84 tokens per session (1,758 once invoked), scanned A, original, MIT.

A reading procedure for finding relevant information in a project wiki before answering a user question. It also decides when to read pages directly, use another agent, or search the web.

In plain words
What is it for?
Use it to locate wiki coverage, choose a retrieval method, and support answers with the right project information.
Why use it?
It reduces the risk of answering without checking existing project knowledge or using the wrong source.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Part of the karpathy-wiki plugin — 5 skills, 1 command, 1 hook shipped together

Good fit Use it to locate wiki coverage, choose a retrieval method, and support answers with the right project information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toolboxmd/karpathy-wiki/karpathy-wiki-read
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 toolboxmd/karpathy-wiki --skill karpathy-wiki-read
Clone the repo
git clone --depth 1 https://github.com/toolboxmd/karpathy-wiki

Made for: Claude Code.

Or install karpathy-wiki, the plugin that ships this one along with the rest of its 5 skills, 1 command, 1 hook.

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-wiki-read

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/toolboxmd/karpathy-wiki/karpathy-wiki-read"><img src="https://agentmods.dev/badge/skills/toolboxmd/karpathy-wiki/karpathy-wiki-read.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,758 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 75
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Output Handling · line 89
    Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
    Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 $0.00084 $0.01758
Opus 5 $0.00042 $0.00879
Sonnet 5 $0.00017 $0.00352
Haiku 4.5 $0.00008 $0.00176

Measured 11d ago against content hash 704e88992ef5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

karpathy-wiki-read 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 11d 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.

skills/karpathy-wiki-read/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

karpathy-wiki read

You loaded this skill because the user asked a question (per Iron Rule 4 in the loader: NO ANSWERING ANY USER QUESTION WITHOUT ORIENTING FIRST). Your job is to determine whether the wiki covers the answer, retrieve the coverage, and either cite-and-answer from the wiki or fall through to web search — without ever pre-classifying the question as "wiki-irrelevant."

The 6-step ladder

Every step is deterministic. There is no agent judgement at branch points; each branch is gated on a counted or boolean condition.

Step A.0: Unconfigured workspace

If no wiki root resolves because workspace routing is unconfigured, do not silently choose or initialize one. Skip the impossible schema/index reads and continue directly at Step F. After answering, follow the required capture flow. The capture skill is the sole owner of orphan preservation and the project, main, or both question. Do not add a second setup prompt here.

Malformed or incomplete configured routing is an error, not this branch.

Step A — Orient

Read these files in order:

  1. <wiki>/schema.md — taxonomy, conventions, thresholds.
  2. The relevant <wiki>/<category>/_index.md for the question's apparent topic. If the question crosses categories or you cannot tell which category applies, read <wiki>/index.md (the root MOC).

If you have already oriented earlier in this session, skip to Step B — the schema and index content are already in your working memory. Orientation is once per session.

Step B — Count signal-matching candidates

Extract the question's signal terms: meaningful nouns, proper-noun phrases, technical terms, version numbers, tool names. Skip stopwords ("the", "what", "how", "do", "is").

Walk the relevant _index.md (already in memory from Step A). For each term, count how many entries it substring-matches (case-insensitive) in the title, the one-liner, or the tag list on that line. A term that hits 6 or more entries is a common term (the Explore band). Other hitting terms are rare terms. Do not keep a denylist of tag names; frequency on this index is the only test.

Read the full file on GitHub · 130 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. 11d ago First seen · 130 lines · 84 tokens per session scan A 704e88992ef5

Subscribe to this mod's changes

karpathy-wiki-read is a skill published in the GitHub repository toolboxmd/karpathy-wiki (103 stars, last pushed 13d ago), licensed MIT. It adds 84 tokens to every session and 1,758 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens