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/tom5610/llm-wiki/claude-mdgit clone --depth 1 https://github.com/tom5610/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/tom5610/llm-wiki/claude-md)<a href="https://agentmods.dev/instructions/tom5610/llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/tom5610/llm-wiki/claude-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 | $0.04678 | $0.04678 |
| Opus 5 | $0.02339 | $0.02339 |
| Sonnet 5 | $0.00936 | $0.00936 |
| Haiku 4.5 | $0.00468 | $0.00468 |
Grade C, and why
llm-wiki CLAUDE.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**Always reset wiki state before running tests** — tests expect a clean slate. Run `rm -rf wiki/ .llm-wiki/ .wiki-snapshot/ extracts/` before every test run. After the test run completes, reset again. Show progress with How it starts
The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project overview
This is an LLM-maintained wiki — a personal knowledge base where the LLM incrementally builds and maintains a persistent, interlinked collection of markdown files from raw source documents. The default domain is writing craft — techniques, principles, frameworks, and practitioners related to the art and craft of writing. Additional domains can be added via lenses (see Lenses section). See @llm-wiki.md for the full pattern description.
Architecture
Three layers:
raw/— immutable source documents (articles, papers, notes, images, course transcripts). Never modify these.wiki/— LLM-generated markdown pages (summaries, entity pages, concept pages, technique pages, comparisons, synthesis). The LLM owns this layer entirely.CLAUDE.md— this file. The schema that governs wiki conventions and workflows.
Special files in wiki/ root:
wiki/index.md— content catalog. Every wiki page listed with link, one-line summary, and category. Organized hierarchically. Read this first when answering queries. Update on every ingest.wiki/log.md— chronological append-only record. Each entry:## [YYYY-MM-DD] operation | Title. Update on every ingest, query-that-creates-a-page, and lint pass.wiki/overview.md— high-level synthesis page (type:synthesis). The wiki's map: what topics it covers, how foundational concepts relate, emerging themes, open questions. Auto-updated on every ingest. Keep short (1-2 screens) — point to deeper pages, don't duplicate them.
Subdirectories in wiki/ (organized by page type):
wiki/concepts/—conceptpages (abstract ideas, principles, frameworks)wiki/techniques/—techniquepages (actionable methods with steps)wiki/entities/—entitypages (people, books, publications, organizations)wiki/synthesis/—synthesis,comparison, andquery-answerpages
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 · 383 lines · 4,678 tokens per session scan C 93a3e41c6750
llm-wiki CLAUDE.md is an instructions file published in the GitHub repository tom5610/llm-wiki (2 stars, last pushed 4mo ago), licensed MIT. It adds 4,678 tokens to every session, about $0.0234 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.