sitemcp CLAUDE.md

sitemcp CLAUDE.md is an instructions file for coding agents from ryoppippi/sitemcp. It costs 535 tokens per session, scanned A, original, from a forked repository, MIT.

Repository-specific instructions for sitemcp, an MCP server that crawls a website and makes its pages available to AI assistants. MCP is a standard way for AI tools to connect to external data and actions.

In plain words
What is it for?
Use them to install, build, lint, type-check, test, run the server for a URL, list crawled pages, and retrieve page content.
Why use it?
They explain the commands, architecture, caching, and testing conventions needed to work on the project.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/ryoppippi/sitemcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/ryoppippi/sitemcp

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 sitemcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ryoppippi/sitemcp/claude-md.svg)](https://agentmods.dev/instructions/ryoppippi/sitemcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ryoppippi/sitemcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ryoppippi/sitemcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 535 This file is loaded in full into every session.
When invoked 535 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.00535 $0.00535
Opus 5 $0.00267 $0.00267
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00053 $0.00053

Measured 6d ago against content hash 2743001a391c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

sitemcp 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 6d 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 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.

Commands

Development

  • bun install - Install dependencies
  • bun run build - Build the project using tsdown, outputs to dist/
  • bun run lint - Run Biome linter and formatter
  • bun run typecheck - Run TypeScript type checking using tsgo
  • bun test - Run unit tests
  • bun release - Full release process: lint, typecheck, test, build, and version bump

Running the MCP Server

  • bunx . [url] - Run the MCP server for a specific URL
  • Example: bunx . https://example.com --concurrency 5 --match "/**" --cache

Architecture

This is a Model Context Protocol (MCP) server that fetches websites and exposes them as tools for AI assistants.

Core Components

  1. MCP Server (server.ts): Creates dynamic tools based on the fetched site:

    • indexOf{SiteName} - Returns paginated list of all pages
    • getDocumentOf{SiteName} - Returns content of specific pages
    • Uses YAML format for responses
    • Implements file-based caching in ~/.cache/sitemcp
  2. Site Fetcher (fetch-site.ts): Queue-based concurrent web crawler:

    • Uses Cheerio for link extraction
    • Uses Happy DOM + Readability for content extraction
    • Respects match patterns and same-origin policy
    • Handles redirects and non-HTML content gracefully
  3. CLI (cli.ts): Command-line interface using gunshi framework

    • Validates inputs and configures the server
    • Supports options for concurrency, caching, content selectors, etc.

Key Technical Decisions

  • Content Extraction: Uses Mozilla's Readability library to extract article content intelligently
  • Concurrent Fetching: Queue-based system with configurable concurrency (default: 3)
  • Tool Naming: Dynamic tool names generated from site URL (domain/subdomain/pathname strategies)
  • Response Format: YAML for better readability in AI contexts
  • Logging: Custom logger outputs to stderr (stdout reserved for MCP protocol)

Read the full file on GitHub · 53 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. 6d ago First seen · 53 lines · 535 tokens per session scan A 2743001a391c

Subscribe to this mod's changes

sitemcp CLAUDE.md is an instructions file published in the GitHub repository ryoppippi/sitemcp (758 stars, last pushed 4mo ago), licensed MIT. It adds 535 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.