llm-wiki: Instructions file for Claude Code

CLAUDE.md

llm-wiki CLAUDE.md is an instructions file for Claude Code from Pratiyush/llm-wiki. It costs 2,556 tokens per session, scanned A, original, MIT.

A set of instructions for maintaining an LLM wiki: a structured, linked collection of knowledge made from Claude Code session transcripts. It defines separate areas for unchanged source transcripts and generated summaries.

In plain words
What is it for?
It helps organize raw transcripts, create pages about people, projects, products, and ideas, maintain an index and activity log, and save comparison or research pages.
Why use it?
It gives session history a consistent structure, so facts remain traceable while summaries and cross-references can be updated safely.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code.

This is Pratiyush/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 Pratiyush/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/Pratiyush/llm-wiki/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Pratiyush/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/pratiyush/llm-wiki/claude-md.svg)](https://agentmods.dev/instructions/pratiyush/llm-wiki/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pratiyush/llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/pratiyush/llm-wiki/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,556 This file is loaded in full into every session.
When invoked 2,556 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02556 $0.02556
Opus 5 $0.01278 $0.01278
Sonnet 5 $0.00511 $0.00511
Haiku 4.5 $0.00256 $0.00256

Measured 8d ago against content hash 67e2a1347a4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

llm-wiki CLAUDE.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 8d 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.

CLAUDE.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

llmwiki — Claude Code Schema

You are maintaining an LLM Wiki (per Karpathy's spec) that compiles the user's Claude Code session history into a structured, interlinked markdown knowledge base.

Three layers

raw/           IMMUTABLE. Session transcripts converted from ~/.claude/projects/*/*.jsonl.
               Flat naming: YYYY-MM-DDTHH-MM-project-slug.md (no subdirectories).
               Never modify files here. Treat as source-of-truth for facts.

wiki/          YOU OWN THIS. LLM-generated pages that summarise, cross-reference, and
               synthesise the raw layer. All of your writes go here.
  index.md         Catalog of every page in the wiki. Update on every ingest.
  log.md           Append-only chronological record of every operation.
  overview.md      Living synthesis across all sources.
  sources/         One summary page per raw source (kebab-case slug).
  entities/        People, companies, projects, products (TitleCase.md).
  concepts/        Ideas, frameworks, methods, theories (TitleCase.md).
  syntheses/       Saved query answers (kebab-case slug).
  comparisons/     Side-by-side diffs of two or more entities/concepts (kebab-case slug). [v0.2+]
  questions/       First-class open questions with state tracking (kebab-case slug). [v0.2+]
  archive/         Deprecated / demoted pages preserved for history. [v0.2+]

site/          GENERATED. Static HTML from `python3 -m llmwiki build`. Do not edit by hand.

Slash commands (and what they do)

Command Intent Workflow
/wiki-sync Convert new .jsonl sessions into raw/sessions/ AND ingest them into wiki/ Runs python3 -m llmwiki sync, then executes the Ingest Workflow below for each new file
/wiki-ingest <path> Ingest one source or folder Executes the Ingest Workflow for the given path
/wiki-query <question> Answer a question from the wiki Executes the Query Workflow below
/wiki-lint Find orphans, broken links, stale pages Executes the Lint Workflow below
/wiki-build Regenerate the static HTML site Runs python3 -m llmwiki build
/wiki-serve Start the local HTTP server Runs python3 -m llmwiki serve
/wiki-update Update one wiki page in place (v0.2+) Surgical edit of one page without re-ingest
/wiki-graph Build the knowledge graph (v0.2+) Walks [[wikilinks]]graph/graph.json + graph.html
/wiki-reflect Higher-order self-reflection over the wiki (v0.2+) Finds gaps, patterns, and suggests new pages

Read the full file on GitHub · 204 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. 8d ago First seen · 204 lines · 2,556 tokens per session scan A 67e2a1347a4c

Subscribe to this mod's changes

llm-wiki CLAUDE.md is an instructions file published in the GitHub repository Pratiyush/llm-wiki (385 stars, last pushed 2mo ago), licensed MIT. It adds 2,556 tokens to every session, about $0.0128 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens