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/drewster99/drews-xcode-mcp/claude-mdgit clone --depth 1 https://github.com/drewster99/drews-xcode-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/drewster99/drews-xcode-mcp/claude-md)<a href="https://agentmods.dev/instructions/drewster99/drews-xcode-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/drewster99/drews-xcode-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 | $0.04983 | $0.04983 |
| Opus 5 | $0.02491 | $0.02491 |
| Sonnet 5 | $0.00997 | $0.00997 |
| Haiku 4.5 | $0.00498 | $0.00498 |
Grade A, and why
drews-xcode-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 today.
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 — 278 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 Drew's Xcode MCP Server (PyPI package drews-xcode-mcp, module drews_xcode_mcp) - a Model Context Protocol (MCP) server that enables AI assistants to interact with Xcode projects. It provides tools for building, running, and managing Xcode projects/workspaces programmatically through AppleScript.
The package was originally published as xcode-mcp-server. That PyPI name now hosts a compatibility shim (see shim/) that depends on drews-xcode-mcp with an exact version pin and forwards the old xcode-mcp-server command to it. deploy.sh and deploy-beta.sh publish both packages in lockstep; the shim's version and pin are rewritten automatically at deploy time. The settings directory is ~/.drews-xcode-mcp; on first run, a pre-rename ~/.xcode-mcp-server directory is adopted via rename (see ConfigManager._migrate_legacy_config_dir). The cache directory deliberately keeps the old name (~/Library/Caches/xcode-mcp-server) — it holds only transient logs/screenshots, and log paths already handed out in prior tool results should stay valid. When launched through the legacy name, the shim sets XCODE_MCP_LEGACY_PACKAGE_NAME, and the server adds migration guidance to its instructions, the version tool, and a migrate_to_drews_xcode_mcp MCP prompt.
Development Commands
Local Development
# Quick start with dev script (sets up venv and runs MCP Inspector)
./dev.sh
# Manual setup: Test the server locally with MCP Inspector
export XCODEMCP_ALLOWED_FOLDERS=/Users/username/Projects
mcp dev drews_xcode_mcp/__main__.py
# Run the server directly
python -m drews_xcode_mcp
Testing in-progress changes through the real MCP path
Two MCP servers are registered against this repo:
drews-xcode-mcp— the deployed build (unpinneduvx drews-xcode-mcp, registered at user scope). It runs the published PyPI release, NOT your working tree. Editing source here does nothing to it until you./deploy.shand the server respawns. Unpinned uvx re-resolves "latest" on spawn using uv's HTTP-cached view of the PyPI index (max-age 600s), so a respawn within ~10 minutes of a deploy can still launch the previous version.xcode-mcp-local-dev-server— runs your live local source viarun_local_for_claude.sh(cdinto the repo, thenpython -m drews_xcode_mcp). Use this to test uncommitted changes without deploying. (Note: the canonical repo path~/cursor/drews-xcode-mcpand~/Documents/ncc_source/cursor/drews-xcode-mcpare the same directory via symlink.)
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.
- today Changed · +5 lines · +1,037 tokens per session 1250695903ae
- 5d ago First seen · 273 lines · 3,946 tokens per session scan A 24f3ece09a3b
drews-xcode-mcp CLAUDE.md is an instructions file published in the GitHub repository drewster99/drews-xcode-mcp (5 stars, last pushed yesterday), licensed MIT. It adds 4,983 tokens to every session, about $0.0249 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.