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/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.
<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="Reviewed on agentmods" width="80" 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 20d 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": "1.0.0",
"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.
- 20d ago Changed b832f2e2edf0
- 1mo ago First seen · 23 lines scan A 616097b3538a
swift-auto-gui is a plugin published in the GitHub repository NakaokaRei/SwiftAutoGUI (94 stars, last pushed 5d 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
claude-codex-computer-use
Control macOS apps from Claude Code through an existing OpenAI Computer Use installation.
clawdcursor
Safe cross-OS desktop & browser control for Claude Code — the fallback execution layer for when APIs, CLIs, and direct integrations aren't available. Registers the clawdcursor MCP server in compact mode and bundles its usage skill (the SKILL.md at the repo root). Requires Node.js 20+; the MCP server launches via npx…
hal-skills
Opinionated agentic skills that do the boring parts for you.
cctop
Monitor and navigate Claude Code sessions across workspaces.
apple-pim
Native macOS integration for Calendar, Reminders, Contacts, and Mail using EventKit, Contacts, and JXA frameworks.
openmessage
OpenMessage: read and send SMS/RCS messages via Google Messages.