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 skills add NakaokaRei/SwiftAutoGUI --skill macos-controlgit 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/skills/nakaokarei/swiftautogui/macos-control)<a href="https://agentmods.dev/skills/nakaokarei/swiftautogui/macos-control"><img src="https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/macos-control/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/skills/nakaokarei/swiftautogui/macos-control"><img src="https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/macos-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 170 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Privilege Escalation · line 39 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 5.1 | $0.00058 | $0.02392 |
| Opus 5.5 | $0.00023 | $0.00957 |
| Sonnet 5.5 | $0.00012 | $0.00478 |
| Haiku 4.5 | $0.00006 | $0.00239 |
Grade B, and why
macos-control scanned grade B with 1 finding 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 23d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo cp .build/release/sagui /usr/local/bin/sagui How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macos-control
The sagui CLI provides mouse control, keyboard input, screenshot capture, image recognition, and screen queries for macOS automation.
Preflight: ensure sagui is installed
Before issuing any sagui command, run:
command -v sagui
If the command prints a path, you're ready — continue to the sections below.
If it prints nothing (exit code 1), sagui is not installed. Stop and ask the user for permission to install it before doing anything else. Show them these options and wait for confirmation:
Recommended — Homebrew:
brew install NakaokaRei/tap/sagui
Fallback — build from source (requires Xcode / Swift 6.2+ toolchain; verify with swift --version):
git clone https://github.com/NakaokaRei/SwiftAutoGUI.git /tmp/SwiftAutoGUI
cd /tmp/SwiftAutoGUI
swift build -c release
# Copy the binary somewhere on $PATH. /usr/local/bin requires sudo:
sudo cp .build/release/sagui /usr/local/bin/sagui
# Or, no sudo, into a user dir already on PATH:
# cp .build/release/sagui ~/.local/bin/sagui
After install, re-run command -v sagui to confirm the binary is reachable, then continue.
Permissions
The first time sagui issues an event or screenshot, macOS will prompt for these permissions. Without them, commands silently fail or return blank screenshots.
- Accessibility — required for
sagui keyandsagui mouse. Enable in System Settings → Privacy & Security → Accessibility for the app running Claude Code (Terminal.app, iTerm, etc.). - Screen Recording — required for
sagui screen screenshot,sagui screen pixel, andsagui screen locate*. Enable in System Settings → Privacy & Security → Screen Recording for the same app.
If a command unexpectedly fails or returns empty output, ask the user to verify both permissions are granted to their terminal app.
This skill is macOS-only — sagui builds on CoreGraphics. On other platforms, tell the user the skill cannot run and stop.
Coordinates
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.
- 23d ago Changed ab8f4a16e3a3
- 1mo ago First seen · 207 lines · 58 tokens per session scan B 1811b320e7dd
macos-control is a skill published in the GitHub repository NakaokaRei/SwiftAutoGUI (94 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 2,392 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
peekaboo
Use Peekaboo for macOS screenshots, Accessibility inspection, and background app/window/UI automation, including fallback computer use when the primary tool cannot handle an authorized task.
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
web-navigator
A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.
computer-use-macos
Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.
cua-sandboxes
Create, use and clean up cua sandboxes (disposable Linux or macOS computers) on this computer with the cua CLI or the cua SDK, and browse the web inside one. Use when a task needs an isolated machine to run code, test an app, drive a desktop GUI, browse or test a website, fill a web form, take a web page screenshot…
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate…