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.
git clone --depth 1 https://github.com/NakaokaRei/SwiftAutoGUIWrote 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/plugins/nakaokarei/swiftautogui/swift-auto-gui)<a href="https://agentmods.dev/plugins/nakaokarei/swiftautogui/swift-auto-gui"><img src="https://agentmods.dev/badge/plugins/nakaokarei/swiftautogui/swift-auto-gui.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
swift-auto-gui 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 8d 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.
What it actually says
{
"name": "swift-auto-gui",
"description": "Control macOS GUI applications and Chromium pages using the sagui CLI.",
"version": "0.30.0",
"author": {
"name": "NakaokaRei"
},
"homepage": "https://github.com/NakaokaRei/SwiftAutoGUI",
"repository": "https://github.com/NakaokaRei/SwiftAutoGUI",
"license": "MIT",
"keywords": [
"macos",
"automation",
"gui",
"mouse",
"keyboard",
"screenshot",
"browser",
"chromium",
"cdp"
]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 130 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 8d ago First seen · 23 lines scan A 616097b3538a
swift-auto-gui is a plugin published in the GitHub repository NakaokaRei/SwiftAutoGUI (92 stars, last pushed 16d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
che-ical-mcp
A macOS server that lets a coding agent work with Apple Calendar and Reminders through EventKit, Apple's calendar and reminder framework.
dear-hiring-manager
Assisted job-application filler. Extracts the JD, scores fit, fills every form field from your profile and answer memory, and stops before Submit for your review. Runs interactively in Claude Code.
che-apple-mail-mcp
Apple Mail MCP server plugin — archive-mail SOP commands, compose and confirmation rules, and the wrapper that downloads the signed, notarized binary pinned by binaryversion. Release narrative and version history live in CHANGELOG.md.
claude-codex-computer-use
Control macOS apps from Claude Code through an existing OpenAI Computer Use installation.
macwright-skills
Project-specific skills for the MacWright MCP server — Safari automation, screen coordinate system, tool development patterns, and workflows discovered during iterative testing.
shortcuts-mcp
MCP server that lets Claude run, view, and annotate macOS Shortcuts via a hybrid AppleScript + CLI approach. Covers interactive shortcuts (file pickers, dialogs), permission handling, and per-shortcut purpose tracking.