A skill for building a persistent, linked knowledge base about large language models in Obsidian, a note-taking application. It turns source material into connected pages that can be searched, checked, and corrected with human feedback.

Ingesting sources, compiling wiki pages, answering grounded questions, researching topics, finding insights and contradictions, linting the knowledge graph, and auditing feedback.

It keeps compiled knowledge and links between ideas instead of making the agent reread raw documents for every question. Its checks can surface gaps and contradictions.

llm-wiki — Skill for Claude Code and Codex by JeanBaissari

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 JeanBaissari/llm-wiki-monorepo --skill skill

Clone the repo

git clone --depth 1 https://github.com/JeanBaissari/llm-wiki-monorepo

Made for: Claude Code, Codex.

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/jeanbaissari/llm-wiki-monorepo/skill/github.svg)](https://agentmods.dev/skills/jeanbaissari/llm-wiki-monorepo/skill)

Your own site

<a href="https://agentmods.dev/skills/jeanbaissari/llm-wiki-monorepo/skill"><img src="https://agentmods.dev/badge/skills/jeanbaissari/llm-wiki-monorepo/skill/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/jeanbaissari/llm-wiki-monorepo/skill"><img src="https://agentmods.dev/badge/skills/jeanbaissari/llm-wiki-monorepo/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,981 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.

Model	Per session	Once invoked
Fable 5.1	$0.00185	$0.06981
Opus 5.5	$0.00074	$0.02792
Sonnet 5.5	$0.00037	$0.01396
Haiku 4.5	$0.00018	$0.00698

Measured 1mo ago against content hash 7679b7a37c8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo ago.

The scan reads SKILL.md. This mod also ships 27 executable files (scripts/ask.py, scripts/atomic_write.py, scripts/audit_review.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skill/SKILL.md · 541 lines

How it starts

The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Wiki — Karpathy Knowledge Base Pattern

Experimental skill — iterating. Authored by Lewis Liu ([email protected]) · Inspired by Karpathy's llm-wiki Gist

Core idea

Instead of RAG (re-retrieving raw docs on every query), the LLM compiles raw sources into a persistent, cross-linked wiki. Every ingest, query, lint, and audit pass makes the wiki richer. Knowledge compounds — and the human stays in the loop via a structured feedback channel instead of ad-hoc corrections that get lost.

You own: sourcing raw material, asking good questions, steering direction, filing feedback on anything the AI got wrong.
LLM owns: all writing, cross-referencing, filing, bookkeeping, and acting on your feedback.

The wiki is a living artifact with ten operations — compile, ingest (single-pass), ingest-2step (two-step chain-of-thought), query, lint, audit, research (deep research), insights (graph insights), ask (grounded QA, v0.6.0), contradictions (epistemic, v0.6.0). Every session starts by reading CLAUDE.md, PURPOSE.md, and wiki/index.md.

Directory layout

<wiki-root>/
├── PURPOSE.md          ← Project purpose — why this wiki exists, scope, success criteria
├── CLAUDE.md          ← Schema: scope, conventions, current articles, gaps
├── log/               ← Per-day operation log (one file per day)
│   ├── 20260409.md
│   └── 20260410.md
├── audit/             ← Human feedback inbox (one file per comment)
│   ├── 20260409-143022-claude-code-size.md
│   └── resolved/      ← Processed feedback, archived with resolution notes
├── raw/               ← Immutable source documents (LLM reads, never writes)
│   ├── articles/
│   ├── papers/
│   ├── notes/
│   └── refs/          ← Pointer files for large binaries kept outside raw/
├── wiki/              ← LLM-generated knowledge (LLM writes, you read)
│   ├── index.md       ← Master catalog — every page, structured by category
│   ├── concepts/      ← Concept/topic pages (split into subfolders when >1200 words)
│   ├── entities/      ← People, tools, papers, organizations
│   ├── summaries/     ← Per-source summary pages
│   ├── comparisons/   ← Side-by-side comparisons of entities, tools, or concepts
│   ├── graphs/        ← Domain-specific graph/report pages (optional)
│   └── synthesis/     ← Deep-research synthesis pages
├── outputs/
│   └── queries/       ← Query answers (promote durable ones to wiki/)
└── graph-data.json    ← Generated knowledge graph (graph-engine build; gitignored)

Read the full file on GitHub · 541 lines

Files

What ships with it

39 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · -25 lines 7679b7a37c8f
2mo ago First seen · 566 lines · 185 tokens per session scan A e30fbfb27069

Subscribe to this mod's changes

llm-wiki is a skill published in the GitHub repository JeanBaissari/llm-wiki-monorepo (3 stars, last pushed 1mo ago), licensed MIT. It adds 185 tokens to every session and 6,981 once invoked, about $0.0007 per session on Opus 5.5. 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.

Data and AI Research ai-agents community-detection concurrency fts5 hermes-agent knowledge-base

llm-wiki next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
llm-wikiJeanBaissari/llm-wiki-monorepo	Skill	3	1mo ago	MIT	A	185	Claude Code, Codex
llm-wikiAr9av/obsidian-wiki	Skill	3.7k	yesterday	MIT	A	41	Claude Code
wiki-exportAr9av/obsidian-wiki	Skill	3.7k	yesterday	MIT	A	53	Claude Code
openai-whisper-apithe-open-agent/openagent	Skill	5.7k	5d ago	Apache-2.0	A	20	Claude Code, Codex
llmwikiatomicstrata/llm-wiki-compiler	Skill	2.2k	7d ago	MIT	A	66	Claude Code, Codex
wegent-knowledgewecode-ai/Wegent	Skill	882	yesterday	Apache-2.0	A	60	Claude Code, Codex
llm-wikizosmaai/pi-llm-wiki	Skill	623	3d ago	MIT	A	52	Claude Code