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/2389-research/xtool/claude-mdgit clone --depth 1 https://github.com/2389-research/xtoolWrote 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/2389-research/xtool/claude-md)<a href="https://agentmods.dev/instructions/2389-research/xtool/claude-md"><img src="https://agentmods.dev/badge/instructions/2389-research/xtool/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 | $0.00525 | $0.00525 |
| Opus 5 | $0.00262 | $0.00262 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
xtool 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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xtool Plugin
Overview
This plugin provides guidance for Xcode-free iOS development using xtool. It helps build SwiftPM-based iOS apps on Linux, Windows, and macOS without requiring Xcode.
Skills Included
using-xtool (Main Skill)
Auto-detects when working with:
- xtool projects or configuration
- SwiftPM iOS apps
- iOS development on non-macOS platforms
- App extensions (widgets, share, keyboard, etc.)
Key Patterns
xtool is NOT XcodeGen
This is the most critical distinction. xtool:
- Uses
xtool.yml(notproject.ymlorProject.swift) - Uses standard SwiftPM
Package.swift - Uses
xtool devcommand (notxtool buildorxtool run) - Places extensions in
Sources/(standard SwiftPM, notExtensions/)
Project Structure
MyApp/
├── Package.swift # SwiftPM package definition
├── xtool.yml # xtool configuration
├── Sources/
│ ├── MyApp/ # Main app target
│ └── MyWidget/ # Extension targets
└── *-Info.plist # Optional custom plists
App Extensions Pattern
Extensions require:
.libraryproduct + target in Package.swift (not.executable)- Entry in
xtool.ymlunderextensions: - Info.plist with
NSExtensionPointIdentifier
Common Commands
xtool new MyApp # Create project
xtool dev # Build + run
xtool dev build --ipa # Build IPA
xtool dev run -s # Run on simulator
xtool devices # List devices
xtool auth login # Authenticate
Troubleshooting Reference
| Issue | Solution |
|---|---|
| "Untrusted Developer" | Settings > VPN & Device Management > Trust |
| Device not found | xtool devices, enable Developer Mode |
| Auth failed | xtool auth login |
| First build slow | Normal - SDK modules building |
Development Notes
When assisting with xtool projects:
- Always verify
xtool.ymlexists (notproject.yml) - Check Package.swift uses
.libraryproducts - Extensions go in
Sources/, notExtensions/ - Use
xtool devnotxtool build
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.
- 4d ago First seen · 73 lines · 525 tokens per session scan A 9bfae99dcde7
xtool CLAUDE.md is an instructions file published in the GitHub repository 2389-research/xtool (2 stars, last pushed 2mo ago), licensed MIT. It adds 525 tokens to every session, about $0.0026 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
apple-dev-skills AGENTS.md
Instructions for gaelic-ghost/apple-dev-skills, covering agents.md, scope, apple rules, install guidance and validation.
MarkdownView AGENTS.md
Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.
swift-architecture-skill AGENTS.md
Instructions for efremidze/swift-architecture-skill, covering agents guidelines for swift architecture skill, working with this repository, 1. understanding the skill, 2. modifying architecture playbooks and 3. testing and validation.
swift-kmp-skill AGENTS.md
Instructions for sorunokoe/swift-kmp-skill, covering agents.md — swift-kmp, what this repository is, repository structure, how to apply this skill and skill loading order.
uikit-expert-skill CLAUDE.md
Instructions for ivan-magda/uikit-expert-skill, a project described as: Agent skill for writing correct, modern UIKit code in Swift. Covers lifecycle, memory, concurrency, collection views, and iOS 13-26 APIs.