mcp-xcode-server: Instructions file for Claude Code

CLAUDE.md

mcp-xcode-server CLAUDE.md is an instructions file for Claude Code from Stefan-Nitu/mcp-xcode-server. It costs 384 tokens per session, scanned A, original, MIT.

A Claude Code instruction file requiring project documents to be read before work begins, including testing, architecture, and error-handling guidance.

In plain words
What is it for?
It is for enforcing initialization and verification steps in the mcp-xcode-server project, including its testing approach, layered architecture, and error conventions.
Why use it?
It makes the agent learn the project's required development patterns before changing or discussing the code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Stefan-Nitu/mcp-xcode-server's own configuration. It tells Claude Code how to work on mcp-xcode-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-xcode-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Stefan-Nitu/mcp-xcode-server. 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/Stefan-Nitu/mcp-xcode-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Stefan-Nitu/mcp-xcode-server

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.

agentmods badge for mcp-xcode-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/stefan-nitu/mcp-xcode-server/claude-md/github.svg)](https://agentmods.dev/instructions/stefan-nitu/mcp-xcode-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/stefan-nitu/mcp-xcode-server/claude-md"><img src="https://agentmods.dev/badge/instructions/stefan-nitu/mcp-xcode-server/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.

agentmods 80×15 button for mcp-xcode-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/stefan-nitu/mcp-xcode-server/claude-md"><img src="https://agentmods.dev/badge/instructions/stefan-nitu/mcp-xcode-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 384 This file is loaded in full into every session.
When invoked 384 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00384 $0.00384
Opus 5.5 $0.00154 $0.00154
Sonnet 5.5 $0.00077 $0.00077
Haiku 4.5 $0.00038 $0.00038

Measured 2mo ago against content hash aaa40398a3e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-xcode-server 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 · 31 lines

What it actually says

MANDATORY INITIALIZATION - DO THIS IMMEDIATELY

⚠️ STOP - READ THIS FIRST ⚠️

YOU MUST READ THESE DOCUMENTS IMMEDIATELY UPON STARTING ANY CONVERSATION ABOUT THIS PROJECT. DO NOT WAIT TO BE ASKED. DO NOT PROCEED WITHOUT READING THEM FIRST.

Required Documents (READ NOW):

  1. docs/TESTING-PHILOSOPHY.md - Critical testing patterns and approaches
  2. docs/ARCHITECTURE.md - Clean/Hexagonal Architecture structure
  3. docs/ERROR-HANDLING.md - Error handling patterns and presentation conventions

Verification Checklist:

  • I have read docs/TESTING-PHILOSOPHY.md completely
  • I have read docs/ARCHITECTURE.md completely
  • I have read docs/ERROR-HANDLING.md completely
  • I understand the testing philosophy (integration focus, proper mocking, behavior testing)
  • I understand the architecture layers (Domain, Application, Infrastructure, Presentation)
  • I understand error handling patterns (typed errors, emoji prefixes, separation of concerns)

If you haven't read these documents yet, STOP and read them now using the Read tool. Only after reading all three documents should you proceed to help the user.

Project Context

This is an MCP (Model Context Protocol) server for Xcode operations. The codebase follows:

  • Clean/Hexagonal Architecture principles
  • Integration-focused testing (60% integration, 25% unit, 10% E2E, 5% static)
  • Parse-don't-validate pattern with domain validation
  • Domain primitives over primitive types
  • Type-safe enum comparisons (always use SimulatorState.Booted, never 'Booted')
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. 2mo ago First seen · 31 lines · 384 tokens per session scan A aaa40398a3e7

Subscribe to this mod's changes

mcp-xcode-server CLAUDE.md is an instructions file published in the GitHub repository Stefan-Nitu/mcp-xcode-server (3 stars, last pushed 1y ago), licensed MIT. It adds 384 tokens to every session, about $0.0015 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 2026-08-31.

Related

mcp-xcode-server CLAUDE.md compared with instructions from other repositories

mcp-xcode-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-xcode-server CLAUDE.mdStefan-Nitu/mcp-xcode-serverInstructions file31y agoMITA384Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file282k3d agoMITA4,335Codex, OpenCode