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 AiAi-Mastermind/aiai-mastermind-tools-and-skills --skill wiki-llmgit clone --depth 1 https://github.com/AiAi-Mastermind/aiai-mastermind-tools-and-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/aiai-mastermind/aiai-mastermind-tools-and-skills/wiki-llm)<a href="https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/wiki-llm"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/wiki-llm/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/aiai-mastermind/aiai-mastermind-tools-and-skills/wiki-llm"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/wiki-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00142 | $0.02161 |
| Opus 5 | $0.00071 | $0.01081 |
| Sonnet 5 | $0.00028 | $0.00432 |
| Haiku 4.5 | $0.00014 | $0.00216 |
Grade A, and why
wiki-llm 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki LLM (Karpathy-style compounding knowledge base)
Overview
Most "LLM + documents" setups are RAG: retrieve chunks at query time, re-derive the answer from scratch every time, accumulate nothing. A wiki LLM is the opposite — the LLM reads each source once and compiles it into a persistent, interlinked set of markdown pages that sit between the human and the raw sources. The cross-references, contradictions, and synthesis are already there; every new source makes the wiki richer.
Core principle: The wiki is a persistent, compounding artifact, not a query-time reconstruction. The LLM writes and maintains every page; the human curates sources, explores, and asks questions. Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase. (Idea: Andrej Karpathy's llm-wiki.)
This skill is domain-agnostic — the same architecture works for a P&C insurance agency, a research thesis, a single novel, a company's internal knowledge, or a hobby deep-dive. Only the page-type vocabulary and the schema's purpose change.
When to use
- The user has a folder of sources and wants organized, cross-linked, cumulative knowledge — not one-shot summaries.
- They mention Obsidian, a "second brain", a "wiki", a knowledge base, or Karpathy's idea.
- They'll keep adding sources over time and want the maintenance burden near zero.
When NOT to use: a single one-off summary; a pure Q&A over docs where nothing is kept (that's RAG); project source code (use CLAUDE.md).
The three-layer architecture (always)
| Layer | Folder (rename to taste) | Owner | Rule |
|---|---|---|---|
| Raw sources | Raw/ |
human curates | immutable — the LLM reads, never edits |
| The wiki | Wiki_LLM/ |
LLM writes | extraction only — what the sources say + how they relate |
| Output | Output/ |
LLM writes | synthesis/editorial — anything the LLM argues, recommends, or produces |
| Memory | .memory/ |
LLM writes | cross-session memory, travels with the repo |
| Schema | CLAUDE.md (+ byte-identical AGENTS.md) |
co-evolved | the operating manual; read first every session |
What ships with it
10 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.
- templates/author.md 1.1 KB
- templates/CLAUDE.md.template 4.8 KB
- templates/concept.md 1.1 KB
- templates/framework.md 1.1 KB
- templates/obsidian/app.json 297 B
- templates/obsidian/appearance.json 44 B
- templates/obsidian/graph.json 1.0 KB
- templates/obsidian/snippets/wiki-colors.css 1.7 KB
- templates/source.md 1.6 KB
- templates/synthesis.md 1.1 KB
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 · 100 lines · 142 tokens per session scan A 9c62cf97fb08
wiki-llm is a skill published in the GitHub repository AiAi-Mastermind/aiai-mastermind-tools-and-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 2,161 once invoked, about $0.0007 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.
Other skills, from other repositories
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
save
Save a user-selected answer, decision, insight, or session summary into an Obsidian vault as one reviewed transaction. Use only when the user explicitly asks to preserve specific conversation content, not when they supply a file or URL to ingest. Triggers: /save, save this, save that answer, file this conversation…
wiki-fold
Create a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default and one optional transaction apply. Use for manual log compression without modifying child pages. Triggers: fold the log, run a fold, run wiki-fold, log rollup, roll up log entries, commit…
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
wiki-mode
Read or configure the vault filing methodology and suggest destinations for planned knowledge creation under Generic, LYT, PARA, or Zettelkasten. Use for wiki mode, methodology mode, what is my vault mode, set vault mode, switch to PARA, use LYT, Zettelkasten setup, change mode, configure mode, or methodology routing.…
wiki-cli
Detect and use the official Obsidian command-line interface for read-only vault access; use for wiki-cli, Obsidian CLI, Obsidian read, Obsidian search, vault transport, which transport, transport detection, backlinks, tags, or Obsidian command line. Mutations always go through the claude-obsidian transaction core.