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/conorluddy/xclaude-plugin/claude-mdgit clone --depth 1 https://github.com/conorluddy/xclaude-pluginWrote 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/conorluddy/xclaude-plugin/claude-md)<a href="https://agentmods.dev/instructions/conorluddy/xclaude-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/conorluddy/xclaude-plugin/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 | $0.01727 | $0.01727 |
| Opus 5 | $0.00864 | $0.00864 |
| Sonnet 5 | $0.00345 | $0.00345 |
| Haiku 4.5 | $0.00173 | $0.00173 |
Grade A, and why
xclaude-plugin 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 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.
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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - AI Assistant Context
This file provides essential guidance to Claude Code when working with the xclaude-plugin repository.
Project Overview
xclaude-plugin is a production-ready MCP (Model Context Protocol) plugin for iOS development automation. It provides 8 modular, workflow-specific MCP servers that consolidate 23 iOS operations across build, test, simulator control, and UI automation.
Status: ✅ Production-ready (v0.4.0) - All operations fully implemented, tested, and with codecov integration.
Key Features:
- 8 modular MCP servers - Workflow-specific, composable architecture
- 23 total operations across Xcode, Simulator, and IDB domains
- 8 procedural Skills (on-demand documentation with examples)
- 100% TypeScript with zero tolerance for
anytypes - Full test coverage with codecov reporting
Repository Structure
xclaude-plugin/
├── README.md # User-facing plugin documentation
├── CLAUDE.md # This file - AI assistant context
├── CODESTYLE.md # Development guidelines
├── .claude-plugin/ # Plugin configuration
│ ├── plugin.json # Plugin manifest (entry point)
│ └── marketplace.json # Marketplace configuration
├── mcp-servers/ # 8 modular MCP servers
│ ├── xc-build/ # Build, clean, list schemes
│ ├── xc-launch/ # Simulator lifecycle: install and launch
│ ├── xc-interact/ # Simulator + IDB UI automation
│ ├── xc-ai-assist/ # AI-specific workflows
│ ├── xc-setup/ # Health check, project info
│ ├── xc-testing/ # Test execution, results parsing
│ ├── xc-meta/ # Metadata and introspection
│ └── xc-all/ # All-in-one consolidated server
│ └── [each server]/
│ ├── src/
│ │ ├── index.ts # Server entry point
│ │ └── operations/ # Operation implementations
│ ├── package.json
│ ├── tsconfig.json
│ └── dist/ # Compiled JavaScript (committed for distribution)
├── skills/ # 8 procedural Skills (on-demand)
│ ├── xcode-workflows/
│ ├── simulator-workflows/
│ ├── ui-automation-workflows/
│ ├── accessibility-testing/
│ ├── ios-testing-patterns/
│ ├── crash-debugging/
│ ├── performance-profiling/
│ └── state-management/
├── .mcp.json # Default MCP configuration (loads xc-setup, xc-build)
├── .mcp.json.example # Full configuration showing all 8 servers
└── .gitignore # Version control exclusions
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 · 230 lines · 1,727 tokens per session scan A b675e308f55e
xclaude-plugin CLAUDE.md is an instructions file published in the GitHub repository conorluddy/xclaude-plugin (182 stars, last pushed 6mo ago), licensed MIT. It adds 1,727 tokens to every session, about $0.0086 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
maui uitests.instructions.md
Instructions for dotnet/maui, covering ui testing guidelines for .net maui, ui test structure, two-project requirement, base class and infrastructure and naming conventions.
ios-simulator-skill CLAUDE.md
Instructions for conorluddy/ios-simulator-skill, covering claude.md - developer guide, project overview, project structure, architecture patterns and pattern 1: class-based script design.
lead-dev-os CLAUDE.md
Instructions for CaptainMe-AI/lead-dev-os, covering claude.md, project, terminology, plugin architecture and repository structure.
earnings-edge CLAUDE.md
Claude Code instructions for suhaas/earnings-edge, covering earnings-edge: project memory for claude code, architecture & core concepts, the graph, agent roles and tools & skills boundary.
swarms CLAUDE.md
Instructions for DheerG/swarms, a project described as: Achieve extraordinary results with claude code across a variety of tasks.
mobile-automator-mcp copilot-instructions.md
Copilot instructions for jegriffi91/mobile-automator-mcp, covering copilot instructions for mobile-automator-mcp, tool selection guide, composite & batch testing, runfeaturetest — one call, full lifecycle and mock variant sweeps (3+ configurations).