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.
npx agentmods add instructions/mosif16/doc-mcp/claude-mdgit clone --depth 1 https://github.com/mosif16/Doc-McpWrote 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.
[](https://agentmods.dev/instructions/mosif16/doc-mcp/claude-md)<a href="https://agentmods.dev/instructions/mosif16/doc-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mosif16/doc-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.08572 | $0.08572 |
| Opus 5 | $0.04286 | $0.04286 |
| Sonnet 5 | $0.01714 | $0.01714 |
| Haiku 4.5 | $0.00857 | $0.00857 |
Grade A, and why
Doc-Mcp CLAUDE.md scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- CLI examples with vertcoin-cli and JSON-RPC curl commands How it starts
The opening of the file, as written. The whole thing — 528 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
Apple Doc MCP is a Model Context Protocol (MCP) server written in Rust that provides access to developer documentation from multiple providers. It enables AI coding assistants to search, browse, and retrieve official documentation for:
- Apple: SwiftUI, UIKit, Foundation, CoreML, Vision, and 60+ frameworks (including ML/AI)
- Telegram: Bot API methods and types
- TON: Comprehensive blockchain documentation including:
- TON API (tonapi.io REST endpoints)
- Smart contract languages (Tact, FunC, Tolk, Fift)
- Security best practices and vulnerability patterns
- Token standards (Jettons, NFTs, SBTs)
- TVM (TON Virtual Machine) documentation
- Wallet contracts and TON Connect
- Cocoon: Confidential computing documentation
- Rust: Standard library (std, core, alloc) and any crate from docs.rs
- MDN: JavaScript, TypeScript, Web APIs, DOM documentation
- Web Frameworks: React, Next.js, Node.js, and Bun documentation
- Bun: Fast all-in-one JavaScript runtime with bundler, transpiler, test runner, and package manager
- MLX: Apple's machine learning framework for Apple Silicon (Swift and Python)
- Hugging Face: Transformers library and swift-transformers for LLM/AI development
- QuickNode: Solana blockchain RPC documentation (HTTP methods, WebSocket, Marketplace add-ons)
- Claude Agent SDK: TypeScript and Python SDKs for building AI agents with Claude Code capabilities
- Vertcoin: GPU-mineable cryptocurrency with Verthash algorithm, JSON-RPC API documentation
- CUDA: NVIDIA GPU programming (Runtime API, kernel development, cuBLAS, cuDNN) with RTX 3070/4090 specific documentation
Build Commands
# Build (requires Rust 1.76+)
cargo build --release
# Run tests
cargo test
# Run tests for a specific crate
cargo test -p docs-mcp-core
# Run the server (for local development)
cargo run -p docs-mcp-cli
# Lint
cargo clippy --all-targets
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.
- 5d ago First seen · 528 lines · 8,572 tokens per session scan A c7f029fbf677
Doc-Mcp CLAUDE.md is an instructions file published in the GitHub repository mosif16/Doc-Mcp (11 stars, last pushed 6mo ago), licensed MIT. It adds 8,572 tokens to every session, about $0.0429 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
turso AGENTS.md
AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.
cli AGENTS.md
AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.
azure-sdk-for-rust resourcemanager.instructions.md
Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
ton-rs AGENTS.md
AGENTS.md instructions for ston-fi/ton-rs, covering ton-rs agent guide, repository, boundaries, public api and ton invariants.
PDF-Writer CLAUDE.md
Instructions for galkahana/PDF-Writer, covering claude code context - pdf-writer development guide, project overview, coding standards discovered, project structure and key components.