What is llm-codes CLAUDE.md?

A development guide for llm.codes, a tool that turns JavaScript-heavy documentation websites into Markdown that AI systems can read. It covers the project's commands, architecture, scraping endpoint, caching, and content processing.

Use it to develop, build, test, type-check, and lint the application, or to change how it validates documentation URLs, fetches pages, caches results, and processes content.

Some documentation is rendered in the browser and is difficult for AI agents to read directly; this project converts it into simpler text.

How amantus-ai/llm-codes configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to amantus-ai/llm-codes. 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/amantus-ai/llm-codes/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/amantus-ai/llm-codes

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/amantus-ai/llm-codes/claude-md/github.svg)](https://agentmods.dev/instructions/amantus-ai/llm-codes/claude-md)

Your own site

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

Per session 572 This file is loaded in full into every session.

When invoked 572 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	$0.00572	$0.00572
Opus 5.5	$0.00229	$0.00229
Sonnet 5.5	$0.00114	$0.00114
Haiku 4.5	$0.00057	$0.00057

Measured 2mo ago against content hash 46091e9a70d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

llm-codes 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 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.

Development Commands

Building and Running

pnpm run dev - Start development server with Turbopack (fast HMR)
pnpm run build - Build production bundle
pnpm start - Start production server
pnpm run type-check - Run TypeScript type checking

Testing and Quality

pnpm test - Run all tests with Vitest
pnpm run test:ui - Run tests with interactive UI
pnpm run test:coverage - Generate test coverage report
pnpm run lint - Run lint and format checks

Architecture Overview

Core Concept

llm.codes converts JavaScript-heavy documentation sites into clean Markdown for AI consumption. It solves the problem of AI agents being unable to parse modern documentation that relies on client-side rendering.

Key Components

API Endpoint (/api/scrape/route.ts):
- Validates URLs against 69 whitelisted documentation domains
- Implements 30-day in-memory caching
- Uses Firecrawl API for JavaScript rendering
- Handles retries with exponential backoff
Content Processing Pipeline (/utils/):
- content-processing.ts: Multi-stage filtering (navigation, URLs, deduplication)
- documentation-filter.ts: Comprehensive content cleaning
- scraping.ts: Parallel URL processing (20 concurrent)
- url-utils.ts: Domain validation and URL extraction
Frontend (/app/page.tsx):
- React 19 with TypeScript strict mode
- Tailwind CSS v4 with semantic color system
- Real-time progress tracking
- Browser notifications support

Processing Flow

User enters documentation URL
Frontend validates against allowed domains
API checks cache, then fetches via Firecrawl
Content undergoes multi-stage filtering
Parallel processing for multi-page crawls (depth 0-5)
Returns clean Markdown optimized for AI context

Performance Optimizations

Parallel batch processing (20 URLs concurrently)
Set-based URL deduplication
Progressive UI updates
30-day cache reduces API calls by 70%+

Read the full file on GitHub · 78 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 · 78 lines · 572 tokens per session scan A 46091e9a70d0

Subscribe to this mod's changes

llm-codes CLAUDE.md is an instructions file published in the GitHub repository amantus-ai/llm-codes (351 stars, last pushed 4mo ago), licensed MIT. It adds 572 tokens to every session, about $0.0023 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.

llms llmstxt markdown

llm-codes CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
llm-codes CLAUDE.mdamantus-ai/llm-codes	Instructions file	351	4mo ago	MIT	A	572	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-codes: Instructions file for Claude Code