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 LearnPrompt/andrej-karpathy-skills --skill karpathy-llm-wikigit clone --depth 1 https://github.com/LearnPrompt/andrej-karpathy-skillsWrote 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/learnprompt/andrej-karpathy-skills/karpathy-llm-wiki)<a href="https://agentmods.dev/skills/learnprompt/andrej-karpathy-skills/karpathy-llm-wiki"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-llm-wiki/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/learnprompt/andrej-karpathy-skills/karpathy-llm-wiki"><img src="https://agentmods.dev/badge/skills/learnprompt/andrej-karpathy-skills/karpathy-llm-wiki.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 | $0.00101 | $0.01549 |
| Opus 5 | $0.00051 | $0.00775 |
| Sonnet 5 | $0.00020 | $0.00310 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
karpathy-llm-wiki 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill 2: LLM Wiki / Personal Knowledge Base（LLM知识库）
Source: https://x.com/karpathy/status/2039805659525644595 | https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f "59k likes — LLM Knowledge Bases" — top-2 most-liked post
Core Principle
You explore. The LLM maintains.
You read the world, capture raw signals. The LLM compiles, cross-links, deduplicates, lint-checks, and surfaces contradictions. Your Obsidian vault is the output, not the input.
Architecture
RAW INPUTS LLM LAYER OUTPUT
────────── ───────── ──────
Papers (PDF/arXiv) ──→ ingest.py ──→ entities/*.md
Articles (URL) ──→ compile_wiki.py ──→ index.md
Chat logs ──→ lint_wiki.py ──→ contradiction_log.md
Notes (voice/text) ──→ query_wiki.py ──→ slides/
update_entity.py ──→ weekly_digest.md
The 5 Core Prompts
1. Ingest Prompt
You are a knowledge compiler. Given this raw source:
[PASTE RAW CONTENT]
Source URL/title: [SOURCE]
Date: [DATE]
Extract and output:
1. Key entities (people, concepts, tools, papers) — one per line with a 2-sentence description
2. Key claims with confidence level (high/medium/speculative)
3. Connections to existing topics: [LIST YOUR KNOWN TOPICS]
4. Contradictions with anything you know: [WHAT YOU ALREADY BELIEVE]
5. Suggested entity page updates (format: ENTITY_NAME | UPDATE_TEXT)
2. Compile Wiki Entry Prompt
You are maintaining a personal knowledge wiki. Update the entity page for [ENTITY_NAME].
Existing page content:
[CURRENT_PAGE_CONTENT]
New information to integrate:
[NEW_INFO]
Rules:
- Preserve all existing information; only add or correct
- Flag contradictions with: ⚠️ CONFLICT: [old claim] vs [new claim]
- Keep the page under 500 words
- End with: "Last updated: [DATE] | Sources: [LINKS]"
3. Weekly Ingest Prompt (run every week)
Process this week's reading list:
[PASTE 5-10 ITEMS: title + URL + 1-sentence summary]
For each item:
1. Extract top 3 entities to update
2. List 2-3 key claims worth adding to wiki
3. Note any contradictions with existing knowledge
4. Suggest connections to other entities in my wiki
Output as structured markdown, one section per item.
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.
- 13d ago First seen · 181 lines · 101 tokens per session scan A 9883b5376c98
karpathy-llm-wiki is a skill published in the GitHub repository LearnPrompt/andrej-karpathy-skills (97 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,549 once invoked, about $0.0005 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.