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 agentmods add instructions/cobusgreyling/llm-wiki/agents-mdgit clone --depth 1 https://github.com/cobusgreyling/llm-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/instructions/cobusgreyling/llm-wiki/agents-md)<a href="https://agentmods.dev/instructions/cobusgreyling/llm-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/cobusgreyling/llm-wiki/agents-md.svg" alt="Measured on agentmods" 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 | $0.01811 | $0.01811 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
llm-wiki AGENTS.md 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 5d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki Agent Instructions
You are the wiki maintainer for this knowledge base. Your job is to compile, cross-reference, and keep current a structured markdown wiki. The human curates sources and asks questions. You do the bookkeeping.
"Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase." — Andrej Karpathy
Architecture
| Layer | Path | Rules |
|---|---|---|
| Raw sources | raw/ |
Read-only. Never modify. |
| Wiki | wiki/ |
You own this. Create and update all pages. |
| Schema | AGENTS.md |
This file. Co-evolve with the human. |
| Templates | templates/ |
Starting points for new pages. |
Page types
| Type | Location | Purpose |
|---|---|---|
| Entity | wiki/entities/ |
Named things: people, orgs, products, places |
| Concept | wiki/concepts/ |
Ideas, frameworks, definitions |
| Source | wiki/sources/ |
One summary per ingested raw document |
| Answer | wiki/answers/ |
Filed responses to queries |
| Synthesis | wiki/synthesis.md |
Evolving thesis across all sources |
| Contradictions | wiki/contradictions.md |
Conflicting claims ledger |
Special files
wiki/index.md— Content catalog. Update on every ingest and when adding pages.wiki/log.md— Append-only timeline. Never edit past entries.
Log entry format
## [YYYY-MM-DD] <operation> | <detail>
Operations: ingest, query, lint, answer-filed, synthesis-update, init
Operation: Ingest
Triggered when the human adds a file to raw/ and asks you to ingest it.
Steps
- Read the raw source completely (text first; view images separately if present).
- Discuss key takeaways with the human before writing (unless they prefer batch mode).
- Create a source page in
wiki/sources/usingtemplates/source.md. - Update every entity and concept page the source touches — create new pages if needed.
- Revise
wiki/synthesis.mdif the source shifts the overall picture. - Flag contradictions in
wiki/contradictions.mdwhen new data conflicts with existing claims. - Update
wiki/index.mdwith all new/changed pages. - Append to
wiki/log.md:## [YYYY-MM-DD] ingest | <source title>
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.
- 5d ago First seen · 211 lines · 1,811 tokens per session scan A 9e707d787204
llm-wiki AGENTS.md is an instructions file published in the GitHub repository cobusgreyling/llm-wiki (43 stars, last pushed 2mo ago), licensed MIT. It adds 1,811 tokens to every session, about $0.0091 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 instructions, from other repositories
llm-knowledge-base AGENTS.md
Instructions for arturseo-geo/llm-knowledge-base, covering agents.md — llm knowledge base schema, 1. repository layout, 2. agent identity and scope, 3. file naming conventions and 4. article schema.
robust-llm-wiki CLAUDE.md
Instructions for KevinYoung-Kw/robust-llm-wiki, covering claude.md, the original karpathy baseline, made explicit and repository-specific policy.
llm-atomic-wiki CLAUDE.md
Claude Code instructions for cablate/llm-atomic-wiki, covering claude.md — schema for llms operating this repo, mental model, atom format (spec), frontmatter (yaml, required) and filename.
Pagecraft CLAUDE.md
Claude Code instructions for panamini/Pagecraft, covering claude.md — hybrid twoweeks + karpathy operating contract, project intent, operating principles, behavioral execution overlay and 1. think before mutating.
Pagecraft AGENTS.md
AGENTS.md instructions for panamini/Pagecraft: This repository keeps its canonical write-time contract in CLAUDE.md.
llm-wiki-compiler AGENTS.md
AGENTS.md instructions for atomicstrata/llm-wiki-compiler, covering llmwiki, development guidelines, code style & standards, clean code rules and comments and documentation.