agentmods.dev

SwiftAutoGUI: Instructions file for Claude Code

CLAUDE.md

SwiftAutoGUI CLAUDE.md is an instructions file for Claude Code from NakaokaRei/SwiftAutoGUI. It costs 873 tokens per session, scanned A, original, MIT.

Project instructions for SwiftAutoGUI, a Swift library that controls macOS mouse and keyboard input and can generate actions from natural-language requests. They describe the project, build commands, tests, and Metal shader rebuilding.

In plain words
What is it for?
Use them when developing, testing, or updating documentation for the SwiftAutoGUI project.
Why use it?
They provide the repository-specific commands and safety details needed to build and test the library, including tests that generate real input.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is NakaokaRei/SwiftAutoGUI's own configuration. It tells Claude Code how to work on SwiftAutoGUI 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 SwiftAutoGUI configures →

not rated 92repo 18d ago A scan 873 tokens original MIT
View source ↗ NakaokaRei/SwiftAutoGUI nakaokarei.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to NakaokaRei/SwiftAutoGUI. 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/NakaokaRei/SwiftAutoGUI/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/NakaokaRei/SwiftAutoGUI

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 SwiftAutoGUI CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nakaokarei/swiftautogui/claude-md/github.svg)](https://agentmods.dev/instructions/nakaokarei/swiftautogui/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nakaokarei/swiftautogui/claude-md"><img src="https://agentmods.dev/badge/instructions/nakaokarei/swiftautogui/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 SwiftAutoGUI CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nakaokarei/swiftautogui/claude-md"><img src="https://agentmods.dev/badge/instructions/nakaokarei/swiftautogui/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 873 This file is loaded in full into every session.
When invoked 873 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 $0.00873 $0.00873
Opus 5 $0.00436 $0.00436
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00087 $0.00087

Measured 10d ago against content hash d4bd0ebf4a13, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

SwiftAutoGUI 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 10d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 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

SwiftAutoGUI is a Swift library for programmatically controlling the mouse and keyboard on macOS. It's inspired by pyautogui and provides low-level access to system input events through CoreGraphics. It also includes AI-powered action generation from natural language.

Development Commands

Build and Test

swift build                    # Build the package
swift build -c release         # Build in release mode
swift test                     # Run safe tests (does not generate mouse/keyboard input)
swift test --parallel          # Run safe tests in parallel (used in CI)
SWIFTAUTOGUI_RUN_INPUT_TESTS=1 swift test  # Explicitly run tests that generate real input
swift test --filter KeyboardTests  # Run safe tests in a single test suite
swift package --allow-writing-to-package-directory build-metal-library
                               # Rebuild the bundled Metal shader library

Rebuilding the Metal library requires Xcode's optional Metal Toolchain component. Package consumers use the committed .metallib and do not need the component installed.

Documentation

swift package generate-documentation
swift package --disable-sandbox preview-documentation --target SwiftAutoGUI

sagui CLI Tool

swift run sagui key shortcut command c    # Keyboard shortcut
swift run sagui mouse move --x 100 --y 200  # Mouse movement
swift run sagui screen screenshot --output capture.png  # Screenshot

Sample App

Located at Sample/Sample.xcodeproj. Open in Xcode and run (⌘+R).

Architecture

Two SPM Targets

  • SwiftAutoGUI (library) — the core automation library
  • sagui (executable) — CLI tool wrapping the library via swift-argument-parser

Core Library (Sources/SwiftAutoGUI/)

  • Core/ — Main SwiftAutoGUI namespace and low-level mouse/keyboard operations.
  • Input/ — Key codes, keyboard layouts, and tweening functions.
  • Accessibility/ — Accessibility element lookup, attributes, actions, and matching types.
  • Actions/ — Declarative actions and agent orchestration.
  • AI/ — Action-generation protocols, model backends, and screen context.
  • Screen/ — Screen capture and image-recognition integration.
  • System/ — AppleScript and system-dialog helpers.
  • Documentation.docc/ — DocC catalog for the library.

Read the full file on GitHub · 87 lines

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. 10d ago First seen · 87 lines · 873 tokens per session scan A d4bd0ebf4a13

Subscribe to this mod's changes

SwiftAutoGUI CLAUDE.md is an instructions file published in the GitHub repository NakaokaRei/SwiftAutoGUI (92 stars, last pushed 18d ago), licensed MIT. It adds 873 tokens to every session, about $0.0044 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.

ai-agentsautomationcomputer-use-agentdesktop-automationmacosswift
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens