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 vibeeval/vibecosystem --skill browser-automationgit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/vibeeval/vibecosystem/browser-automation)<a href="https://agentmods.dev/skills/vibeeval/vibecosystem/browser-automation"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/browser-automation/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/vibeeval/vibecosystem/browser-automation"><img src="https://agentmods.dev/badge/skills/vibeeval/vibecosystem/browser-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.00620 |
| Opus 5 | $0.00010 | $0.00310 |
| Sonnet 5 | $0.00004 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Automation
AI-powered browser automation via browser-use MCP server. Navigate web pages, fill forms, extract content, take screenshots, and verify deployments.
Setup
Add to ~/.mcp.json:
{
"mcpServers": {
"browser-use": {
"command": "uvx",
"args": ["browser-use", "--mcp"]
}
}
}
Restart Claude Code after adding.
Usage
Navigate & Extract
/browser-automation navigate https://docs.example.com
/browser-automation extract https://docs.example.com --format markdown
Form Interaction
/browser-automation fill https://app.example.com/login
email: [email protected]
password: [from env TEST_PASSWORD]
submit: button[type=submit]
Deploy Verification
/browser-automation verify https://myapp.com
- Check: homepage loads (< 3s)
- Check: /api/health returns 200
- Check: login page renders
- Screenshot: homepage, login, dashboard
Screenshot
/browser-automation screenshot https://myapp.com --full-page
/browser-automation screenshot https://myapp.com --element "#hero-section"
Integration Points
| Trigger | How It Helps |
|---|---|
shipper deploys |
Auto-verify live URL, take screenshots |
e2e-runner needs browser |
Natural language browser tests |
oracle needs deep docs |
Navigate multi-page documentation |
designer needs references |
Capture UI patterns from live sites |
qa-engineer tests forms |
Fill and submit forms, verify results |
growth analyzes competitors |
Extract features, pricing, UX patterns |
MCP Tools Available
| Tool | Description |
|---|---|
browser_navigate |
Go to a URL |
browser_click |
Click element by selector or text |
browser_type |
Type into input field |
browser_screenshot |
Capture page/element screenshot |
browser_extract |
Extract page content as text/markdown |
browser_wait |
Wait for element or condition |
browser_evaluate |
Execute JavaScript in page context |
browser_scroll |
Scroll page or element |
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 · 97 lines · 19 tokens per session scan A e5145e2ab327
browser-automation is a skill published in the GitHub repository vibeeval/vibecosystem (529 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 620 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
browser-automation
Web automation with 4-layer escalation (Fetch, Genesis Browser, On-Demand MCP, Computer Use), anti-detection, and persistent profiles.
stealth-browser
Anti-detection behavioral rules for stealth browser automation.
playwright-expert
Expert in Playwright E2E testing framework, auto-waiting mechanisms, test generation, trace viewer, and CI/CD integration. Use when the user mentions testing, end-to-end tests, QA, automation, end-to-end testing, or test automation, or when the task involves Playwright Framework, Test Organization, Advanced Features…
selenium-expert
Expert in Selenium WebDriver, Selenium Grid, page object model, waits, cross-browser testing, and test automation frameworks. Use when the user mentions testing, end-to-end tests, QA, automation, WebDriver, or Selenium grid, or when the task involves Selenium Components, Browser Support, Advanced Features, or Basic…
agent-browser
Advanced browser automation for AI agents with snapshot-ref interaction pattern - navigate, snapshot interactive elements with refs, click/fill/select by refs, manage sessions, and extract structured data.
webapp-testing
Test local web applications using browser automation - verify frontend functionality, debug UI behavior, capture screenshots, view console logs, run E2E scenarios, and check accessibility.