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.
npx skills add toolboxmd/karpathy-wiki --skill karpathy-wiki-doctorgit clone --depth 1 https://github.com/toolboxmd/karpathy-wikiWrote 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.
[](https://agentmods.dev/skills/toolboxmd/karpathy-wiki/karpathy-wiki-doctor)<a href="https://agentmods.dev/skills/toolboxmd/karpathy-wiki/karpathy-wiki-doctor"><img src="https://agentmods.dev/badge/skills/toolboxmd/karpathy-wiki/karpathy-wiki-doctor/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.
<a href="https://agentmods.dev/skills/toolboxmd/karpathy-wiki/karpathy-wiki-doctor"><img src="https://agentmods.dev/badge/skills/toolboxmd/karpathy-wiki/karpathy-wiki-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00502 |
| Opus 5 | $0.00028 | $0.00251 |
| Sonnet 5 | $0.00011 | $0.00100 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
karpathy-wiki-doctor 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 12d 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.
What it actually says
karpathy-wiki doctor (detached census)
You are the detached wiki doctor. Wiki root is ${WIKI_ROOT}. Run id is
${WIKI_RUN_ID}. Perform this census yourself. Do not launch another model.
Completion
After the census succeeds:
bash "${WIKI_PLUGIN_ROOT}/scripts/wiki-complete-doctor.sh"
Exit non-zero if that helper fails.
Steps
- Run
wiki-archive-schema-proposals.py --wiki-root "${WIKI_ROOT}"so leftover proposal files sit under pending archive, not in a live inbox. - Read
<wiki>/schema.mdand category_index.mdfiles. - Read
.ingest-issues.jsonland.doctor-runs.jsonlif they exist. - Run page validation and tag lint (
wiki-validate-page.py,wiki-lint-tags.py). - Collapse same-idea tag pairs. Lint is a detector; also use
tag-driftlines in.ingest-issues.jsonl. Skip pairs that are not the same idea. For each same-idea pair runwiki-collapse-tag.py --wiki-root "${WIKI_ROOT}" --same-idea <a> <b>. One spelling remains on pages, indexes, and Tag Taxonomy. Do not write==synonym pairs. Do not treat historical==schema lines as the collapse plan. - Patch schema.md via
wiki-schema-patch.py(objects, tags, categories, extra Page contract keys). - You may fix frontmatter, tags, and related lists. Leave page synthesis unchanged.
- If a cluster needs a playbook body, write one rewrite job under
<wiki>/.wiki-pending/rewrite-jobs/naming the object token and pages. Do not execute the rewrite. - Complete through the helper.
Done
Tests ran, schema objects/tags/categories match the index, rewrite jobs are recorded when a body rewrite is needed, page bodies are unchanged.
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.
- 12d ago First seen · 52 lines · 55 tokens per session scan A f9ae1beb6514
karpathy-wiki-doctor is a skill published in the GitHub repository toolboxmd/karpathy-wiki (103 stars, last pushed 14d ago), licensed MIT. It adds 55 tokens to every session and 502 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…