What is llm-wiki CLAUDE.md?

Project instructions for LLM Wiki, a local-first knowledge base inspired by a wiki, where information is stored on the user’s computer. They define the required documentation-reading order, architecture, features, data model, AI integration, and build plan.

Building or modifying the wiki, document-ingestion pipeline, SQLite data model, chat threads, local files, LLM integration, user interface, and command-line distribution.

They give a coding agent the project specification and working rules before it changes code, reducing the risk of skipping requirements or using the wrong design.

How ddsyasas/llm-wiki configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to ddsyasas/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/ddsyasas/llm-wiki/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ddsyasas/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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ddsyasas/llm-wiki/claude-md/github.svg)](https://agentmods.dev/instructions/ddsyasas/llm-wiki/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ddsyasas/llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/ddsyasas/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ddsyasas/llm-wiki/claude-md"><img src="https://agentmods.dev/badge/instructions/ddsyasas/llm-wiki/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 744 This file is loaded in full into every session.

When invoked 744 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.

Model	Per session	Once invoked
Fable 5.1	$0.00744	$0.00744
Opus 5.5	$0.00298	$0.00298
Sonnet 5.5	$0.00149	$0.00149
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash 4c4244f6a19d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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.

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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Brief for Claude Code

You are building LLM Wiki, an open source local-first knowledge base inspired by Andrej Karpathy's LLM Wiki pattern (gist: https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f).

Read this first

Before writing any code, read every file in /docs/ in numerical order. Each file is short and focused. Together they form the complete spec.

docs/01-vision.md - What this is and who it's for
docs/02-architecture.md - Stack, repo layout, distribution
docs/03-data-model.md - On-disk structure and SQLite schema
docs/04-features-v1.md - Exact V1 feature scope
docs/05-llm-integration.md - OpenRouter, prompts, JSON contracts
docs/06-ingest-pipeline.md - How sources become wiki pages
docs/07-chat-threads.md - Chat feature spec
docs/08-ui-design.md - Design language and key screens
docs/09-cli-distribution.md - CLI behavior and npm packaging
docs/10-build-order.md - Sequenced build plan, follow this exactly
docs/11-attribution-license.md - Naming, credits, license

Core principles, do not violate

Everything is a file. The wiki, chats, schema, log all live as plain .md files in the user's chosen folder. SQLite is metadata only.
Local-first, BYOK. No telemetry, no remote storage, no auth. Users bring their own OpenRouter key.
One language: TypeScript everywhere. No Python sidecars in V1.
Cross-platform: Mac, Windows, Linux all supported from day one.
Karpathy's three operations are central: ingest, query, lint. Build them as separate, well-named modules.

Stack lock-in

Next.js (App Router) for the whole app
Tailwind + shadcn/ui for UI
better-sqlite3 for metadata
openai SDK pointed at OpenRouter
pnpm for package management
TypeScript strict mode

Do not introduce new frameworks without asking.

Working conventions

TypeScript strict mode, no any without comment explaining why
Functions over classes where possible
File names: kebab-case
React components: PascalCase
No default exports for shared modules, named exports only
Comments explain why, not what
Every LLM operation must validate its JSON response before using it

Read the full file on GitHub · 66 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.

2mo ago First seen · 66 lines · 744 tokens per session scan A 4c4244f6a19d

Subscribe to this mod's changes

llm-wiki CLAUDE.md is an instructions file published in the GitHub repository ddsyasas/llm-wiki (69 stars, last pushed 5mo ago), licensed MIT. It adds 744 tokens to every session, about $0.0030 per session on Opus 5.5. 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.

Memory and context agentic ai-agent byok karpathy knowledge-base knowledge-graph

llm-wiki CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
llm-wiki CLAUDE.mdddsyasas/llm-wiki	Instructions file	69	5mo ago	MIT	A	744	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

llm-wiki: Instructions file for Claude Code