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/tmaasen/apple-dev-mcp/claude-mdgit clone --depth 1 https://github.com/tmaasen/apple-dev-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/tmaasen/apple-dev-mcp/claude-md)<a href="https://agentmods.dev/instructions/tmaasen/apple-dev-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tmaasen/apple-dev-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 5.1 | $0.02792 | $0.02792 |
| Opus 5 | $0.01396 | $0.01396 |
| Sonnet 5 | $0.00558 | $0.00558 |
| Haiku 4.5 | $0.00279 | $0.00279 |
Grade A, and why
apple-dev-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 308 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
This is an Apple Dev MCP (Model Context Protocol) server that provides complete Apple development guidance, combining Human Interface Guidelines (design principles) with Technical Documentation (API reference) for all Apple platforms. It serves comprehensive content through both traditional MCP integration and modern Desktop Extensions (.dxt) for AI assistants like Claude.
Development Commands
Build and Test
npm run build- Compile TypeScript to JavaScript indist/npm run clean:build- Clean and rebuild the projectnpm test- Run Jest test suitenpm run test:watch- Run tests in watch modenpm run lint- Run ESLint on TypeScript filesnpm run lint:fix- Fix linting issues automatically
Development
npm run dev- Start development server using tsxnpm start- Run compiled server fromdist/npm run test:automation- Automated MCP server testing
Testing with MCP Inspector
npx @modelcontextprotocol/inspector dist/server.js
Architecture Overview
The project uses a static content architecture with pre-built markdown files and optimized search indices. All content is pre-processed and cached for instant access without external dependencies:
Core Components
-
AppleHIGMCPServer (
src/server.ts) - Main MCP server entry point- Coordinates all components and handles MCP protocol communication
- Sets up request handlers for resources and tools
- Manages graceful startup/shutdown
- Initializes static content services
-
StaticContentSearchService (
src/services/static-content-search.service.ts) - Primary content search engine- Fast search across 113+ pre-processed Apple HIG sections
- Smart keyword matching with synonym expansion
- Platform-specific filtering and relevance scoring
- No external dependencies required
-
HIGCache (
src/cache.ts) - Smart caching layer- TTL-based caching with graceful degradation
- Backup cache entries for offline resilience
- Two-tier caching: fresh data + stale fallback data
- Methods:
getWithGracefulFallback(),setWithGracefulDegradation()
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.
- 6d ago First seen · 308 lines · 2,792 tokens per session scan A 0a52fcc1a8c4
apple-dev-mcp CLAUDE.md is an instructions file published in the GitHub repository tmaasen/apple-dev-mcp (21 stars, last pushed 1y ago), licensed MIT. It adds 2,792 tokens to every session, about $0.0140 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.
Other instructions, from other repositories
app-store-connect-mcp AGENTS.md
AGENTS.md instructions for erayendes/app-store-connect-mcp, covering agents.md, what this is, if a user asks you to install it, 1. agree on the profiles, then register them and 2. send the user to setup for the credentials.
Pepper CLAUDE.md
Instructions for skwallace36/Pepper, covering pepper, mcp tools, conventions, writing docs and work tracking.
instruments-mcp-server CLAUDE.md
Instructions for nemanjavlahovic/instruments-mcp-server, covering instrumentsmcp, what this is, architecture, key design decisions and adding new parsers.
xcforge CLAUDE.md
Claude Code instructions for justinthevoid/xcforge, covering claude.md, build & test commands, architecture, tool provider system and dependency injection.
xcodeinstrumentmcp AGENTS.md
Instructions for eksdev007/xcodeinstrumentmcp, covering agents.md, repository expectations, execution loop, priority order and guardrails.
Apple-Agent-Kit CLAUDE.md
Claude Code instructions for caglarbaranbora/Apple-Agent-Kit, covering claude.md, layer order (do not violate), the normative specs, file naming and structure and validating.