llm-wiki: Instructions file for Claude Code

CLAUDE.md

llm-wiki CLAUDE.md is an instructions file for Claude Code from tom5610/llm-wiki. It costs 4,678 tokens per session, scanned C, original, MIT.

Project instructions for an LLM-maintained wiki, a persistent set of linked markdown knowledge pages built from source documents. They describe the project structure, page conventions, architecture, and quality rules.

In plain words
What is it for?
Working on the wiki’s raw sources, generated pages, index, logs, domain lenses, and documentation workflows.
Why use it?
They give a coding agent the context and standards needed to add, update, and navigate wiki content consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is tom5610/llm-wiki's own configuration. It tells Claude Code how to work on llm-wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tom5610/llm-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tom5610/llm-wiki/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tom5610/llm-wiki

Made for: Claude Code.

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.

agentmods badge for llm-wiki CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tom5610/llm-wiki/claude-md/github.svg)](https://agentmods.dev/instructions/tom5610/llm-wiki/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tom5610/llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/tom5610/llm-wiki/claude-md/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.

agentmods 80×15 button for llm-wiki CLAUDE.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,678 This file is loaded in full into every session.
When invoked 4,678 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04678 $0.04678
Opus 5.5 $0.01871 $0.01871
Sonnet 5.5 $0.00936 $0.00936
Haiku 4.5 $0.00468 $0.00468

Measured 2mo ago against content hash 93a3e41c6750, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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
CLAUDE.md · 383 lines

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/ — concept pages (abstract ideas, principles, frameworks)
  • wiki/techniques/ — technique pages (actionable methods with steps)
  • wiki/entities/ — entity pages (people, books, publications, organizations)
  • wiki/synthesis/ — synthesis, comparison, and query-answer pages

Read the full file on GitHub · 383 lines

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.

  1. 2mo ago First seen · 383 lines · 4,678 tokens per session scan C 93a3e41c6750

Subscribe to this mod's changes

llm-wiki CLAUDE.md is an instructions file published in the GitHub repository tom5610/llm-wiki (3 stars, last pushed 6mo ago), licensed MIT. It adds 4,678 tokens to every session, about $0.0187 per session on Opus 5.5. 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.

Related

llm-wiki CLAUDE.md compared with instructions from other repositories

llm-wiki CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
llm-wiki CLAUDE.mdtom5610/llm-wikiInstructions file36mo agoMITC4,678Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot