SwiftAutoGUI: Skill for Claude Code

.agents/skills/agent-smoke-test/SKILL.md

agent-smoke-test is a skill for Claude Code, Codex from NakaokaRei/SwiftAutoGUI. It costs 43 tokens per session (659 once invoked), scanned A, original, MIT.

A manual test guide for checking SwiftAutoGUI AI-agent actions through the local sagui command-line tool on macOS. SwiftAutoGUI controls apps through native macOS interfaces such as Accessibility.

In plain words
What is it for?
Use it to build sagui, run example agent commands, and check actions in Safari, Calculator, and TextEdit. It is for testing native macOS automation during development.
Why use it?
It gives developers repeatable checks for whether generated app-control actions work as expected. It also helps catch mistakes in actions such as opening an app, pressing a button, or filling a text field.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is NakaokaRei/SwiftAutoGUI's own configuration. It tells Claude Code and Codex 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 →

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/.agents/skills/agent-smoke-test/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NakaokaRei/SwiftAutoGUI

Made for: Claude Code, Codex.

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 agent-smoke-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/agent-smoke-test/github.svg)](https://agentmods.dev/skills/nakaokarei/swiftautogui/agent-smoke-test)
Your own site
<a href="https://agentmods.dev/skills/nakaokarei/swiftautogui/agent-smoke-test"><img src="https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/agent-smoke-test/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 agent-smoke-test

Your own site · 80×15
<a href="https://agentmods.dev/skills/nakaokarei/swiftautogui/agent-smoke-test"><img src="https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/agent-smoke-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00043 $0.00659
Opus 5 $0.00022 $0.00329
Sonnet 5 $0.00009 $0.00132
Haiku 4.5 $0.00004 $0.00066

Measured 11d ago against content hash 552b9a93c22e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

agent-smoke-test 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 11d 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.

.agents/skills/agent-smoke-test/SKILL.md · 91 lines

What it actually says

SwiftAutoGUI Agent Smoke Test

Run examples from the repository root. Always source ~/.zshrc so the latest OPENAI_API_KEY is available.

Build once:

swift build --product sagui

Search for Swift in Safari:

source ~/.zshrc && .build/debug/sagui agent \
  "Search for Swift in Safari." \
  --max-iterations 10 --delay 1

Get the frontmost application:

source ~/.zshrc && .build/debug/sagui agent \
  "Use exactly one getFrontmostApp action, then mark the goal done." \
  --max-iterations 1 --delay 0

Activate Calculator:

source ~/.zshrc && .build/debug/sagui agent \
  "Use exactly one activateApp action with app name Calculator, then mark the goal done." \
  --max-iterations 1 --delay 0

Press Calculator button 7 with Accessibility:

source ~/.zshrc && .build/debug/sagui agent \
  "Calculator is open. Use exactly one pressButton action with label 7 and bundleID com.apple.calculator. Do not use mouse or keyboard actions." \
  --max-iterations 1 --delay 0

Set the first TextEdit text field:

source ~/.zshrc && .build/debug/sagui agent \
  "TextEdit has a Save sheet open. Use exactly one setTextField action with an empty label, value SWIFTAUTOGUI_AGENT_TEST, and bundleID com.apple.TextEdit." \
  --max-iterations 1 --delay 0

Select a TextEdit menu item:

source ~/.zshrc && .build/debug/sagui agent \
  "TextEdit has a rich-text document open. Use exactly one selectMenuItem action with path [Format, Make Plain Text] and bundleID com.apple.TextEdit." \
  --max-iterations 1 --delay 0

Raise a Calculator window:

source ~/.zshrc && .build/debug/sagui agent \
  "Use exactly one raiseWindow action with title Calculator and bundleID com.apple.calculator." \
  --max-iterations 1 --delay 0

Open a URL:

source ~/.zshrc && .build/debug/sagui agent \
  "Use exactly one openURL action with URL https://example.com." \
  --max-iterations 1 --delay 0

Quit Calculator:

source ~/.zshrc && .build/debug/sagui agent \
  "Use exactly one quitApp action with app name Calculator." \
  --max-iterations 1 --delay 0

Check the Actions: line in each command output to confirm which BasicAction the Agent generated.

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. 11d ago First seen · 91 lines · 43 tokens per session scan A 552b9a93c22e

Subscribe to this mod's changes

agent-smoke-test is a skill published in the GitHub repository NakaokaRei/SwiftAutoGUI (93 stars, last pushed 20d ago), licensed MIT. It adds 43 tokens to every session and 659 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

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.

wimi321/macos-computer-use-skill · 37 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

KUP-IP/the-bridge · 35 tokens

playwright-cli

Automate browser interactions, test web pages and work with Playwright tests.

microsoft/playwright · 19 tokens

playwright-component-testing

Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.

microsoft/playwright · 69 tokens

playwright-trace

Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.

microsoft/playwright · 29 tokens

peekaboo

Use Peekaboo for macOS desktop automation, screenshots, visual UI maps, native accessibility inspection, app/window/menu/dialog control, native app and browser chrome control, browser-page MCP tooling, MCP diagnostics, and Peekaboo repo validation. Use when Codex needs current macOS UI state, direct desktop control…

openclaw/Peekaboo · 82 tokens