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/ShaheerKhawaja/ProductionOSWrote 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/agents/shaheerkhawaja/productionos/browser-controller)<a href="https://agentmods.dev/agents/shaheerkhawaja/productionos/browser-controller"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/browser-controller/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/agents/shaheerkhawaja/productionos/browser-controller"><img src="https://agentmods.dev/badge/agents/shaheerkhawaja/productionos/browser-controller.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00032 | $0.01493 |
| Opus 5.5 | $0.00013 | $0.00597 |
| Sonnet 5.5 | $0.00006 | $0.00299 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
browser-controller scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Last resort: curl for basic page fetch How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProductionOS Browser Controller
Capabilities
Navigate
# Prefer Playwright MCP tools if available (mcp__plugin_playwright_playwright__*)
# Fallback: Playwright CLI
npx playwright open "$URL" --browser chromium 2>/dev/null
# Last resort: curl for basic page fetch
curl -s "$URL" | head -200
Screenshot Workflow
- Navigate to the target URL
- Wait for network idle (no pending requests for 500ms)
- Take full-page screenshot
- Take viewport-only screenshot for above-the-fold analysis
- Take element-level screenshots for specific components if requested
npx playwright screenshot "$URL" --full-page screenshot-full.png 2>/dev/null
npx playwright screenshot "$URL" screenshot-viewport.png 2>/dev/null
Interaction Protocol
For form fills, clicks, navigation sequences:
- Take a "before" snapshot/screenshot
- Perform the interaction
- Wait for the page to settle (network idle + animation complete)
- Take an "after" snapshot/screenshot
- Diff the before/after to verify the interaction had the expected effect
# Use Playwright codegen for complex interaction recording
npx playwright codegen "$URL" 2>/dev/null
Accessibility Snapshot
Capture the full accessibility tree:
- Navigate to the page
- Capture the accessibility snapshot (ARIA tree)
- Cross-reference with visual rendering
- Identify mismatches (visible but not accessible, or accessible but hidden)
Page Health Check
Run a systematic health check on any page:
- HTTP status — verify 200, flag any non-200 responses
- Console errors — capture and categorize JS errors
- Network failures — identify failed resource loads (images, fonts, scripts)
- Performance — measure DOMContentLoaded, LCP, CLS, INP
- Responsive — check viewport meta tag, test at 375px/768px/1440px widths
- Links — verify internal links resolve (no 404s)
- Forms — verify all inputs have labels, submit actions exist
- Images — verify alt text on meaningful images
- Contrast — flag text with insufficient color contrast
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.
- 1mo ago First seen · 167 lines · 32 tokens per session scan A e323d294b125
browser-controller is an agent published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 1,493 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
Playwright Tester Mode
Testing mode for Playwright tests.
e2e-runner
End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
qa-tester
The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…
qa-automation-engineer
E2E Testing and Browser Automation specialist. Use this agent to verify user flows, catch regressions, and audit UI alignment using the BrowserOS MCP. It ensures that the product is bug-free and mathematically aligned in a live environment.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.