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 agentmods add skills/spillwavesolutions/automating-mac-apps-plugin/web-browser-automationnpx skills add SpillwaveSolutions/automating-mac-apps-plugin --skill web-browser-automationgit clone --depth 1 https://github.com/SpillwaveSolutions/automating-mac-apps-pluginWrote 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/spillwavesolutions/automating-mac-apps-plugin/web-browser-automation)<a href="https://agentmods.dev/skills/spillwavesolutions/automating-mac-apps-plugin/web-browser-automation"><img src="https://agentmods.dev/badge/skills/spillwavesolutions/automating-mac-apps-plugin/web-browser-automation.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00077 | $0.01864 |
| Opus 5 | $0.00039 | $0.00932 |
| Sonnet 5 | $0.00015 | $0.00373 |
| Haiku 4.5 | $0.00008 | $0.00186 |
Grade A, and why
web-browser-automation 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS Web Browser Automation Guide
Table of Contents
- Overview
- Browser Compatibility Matrix
- PyXA Integration
- Playwright Automation
- Selenium WebDriver
- Puppeteer Node.js
- Comprehensive Automation Workflows
- Brief Automation Patterns
- Advanced Techniques
- Troubleshooting and Validation
- Security Considerations
- Performance Optimization
- Integration Examples
Overview
This guide covers comprehensive web browser automation on macOS desktop, focusing on automation (not testing). We cover four major automation frameworks with practical examples for real-world scenarios.
PyXA Installation: To use PyXA examples in this skill, see the installation instructions in automating-mac-apps skill (PyXA Installation section).
Primary Automation Tools
- PyXA: macOS-native Python wrapper with direct browser integration
- Playwright: Cross-platform framework with Python bindings for modern web automation
- Selenium: Industry-standard automation with ChromeDriver integration
- Puppeteer: Node.js framework for Chrome/Chromium automation
Tool Selection Guide
| Tool | Primary Use | Key Advantages |
|---|---|---|
| PyXA | macOS-native control | Direct OS integration, Arc spaces |
| Playwright | Cross-browser testing | Auto-waiting, mobile emulation |
| Selenium | Legacy enterprise | Mature ecosystem, wide language support |
| Puppeteer | Headless Chrome | Fast execution, PDF generation |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 209 lines · 77 tokens per session scan A 2c84178fa47e
web-browser-automation is a skill published in the GitHub repository SpillwaveSolutions/automating-mac-apps-plugin (40 stars, last pushed 14d ago), licensed MIT. It adds 77 tokens to every session and 1,864 once invoked, about $0.0004 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.
Other skills, from other repositories
document-hunter
Searches and retrieves documents from free public sources using automated browser navigation. Use when research needs primary source documents like court filings, government reports, or public records.
playwright-openwebui
Use when inspecting UI bugs in OpenWebUI plugins, taking screenshots of plugin output, capturing console errors, testing Action/Filter/Pipe plugins in the chat interface, or verifying plugin installation in the Admin panel. Triggered by: plugin UI bug, Action HTML output, screenshot, console error, plugin not working…
browser-testing
Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.
mission-creation
Use this skill to create and drive a UAV mission end-to-end through the web UI with the Playwright MCP browser tools on LOCALDEV (https:// ) — rebuild/redeploy, Keycloak login, the multi-step BYROUTE/REALTIME mission wizard, pre-flight, the Start-Mission FSM, AND the full per-drone flight-command lifecycle (arm →…
browser-verification
Verify UI behavior in a live browser via Playwright MCP (navigate, snapshot, screenshots, console/network) against localdev or staging. NOT for full domain E2E flows and never against production.
reviewing-flows
Use when the pending flow queue needs triage before approval, such as deciding which recorded flows are worth keeping, clearing out ones that can never replay, or reading a flow's real steps before consenting to it.