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 strikersam/autonomous-ai-agency --skill agent-browsergit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/agent-browser)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/agent-browser"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/agent-browser/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/strikersam/autonomous-ai-agency/agent-browser"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/agent-browser.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 | $0.00062 | $0.01110 |
| Opus 5 | $0.00031 | $0.00555 |
| Sonnet 5 | $0.00012 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade C, and why
agent-browser scanned grade C with 2 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 7d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s http://localhost:9222/json | python3 -m json.tool | head -20 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:9222/json | python3 -m json.tool | head -20 How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: agent-browser — Real Chrome Browser Automation
Why This Exists
agent-browser connects Claude to your real Chrome browser via Chrome DevTools Protocol (CDP) — no Playwright, no Puppeteer, no downloaded binaries. Your actual browser session, cookies, and authentication are preserved. Sites see a real human.
Benefits over Playwright MCP:
- 93% fewer tokens — ~200–400 tokens/page vs ~13,700
- 5× faster — direct WebSocket, no Node.js relay
- No bot detection — no
navigator.webdriverflag - Your real Chrome — persistent sessions, saved passwords, cookies
Installation (one-time)
npm install -g agent-browser # Install CLI globally
Start Chrome with remote debugging enabled (required once per session):
# macOS
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222
# Linux
google-chrome --remote-debugging-port=9222
# Windows
chrome.exe --remote-debugging-port=9222
Core Commands
agent-browser open <url> # Navigate to a URL
agent-browser snapshot # Get accessibility tree (use for reading page state)
agent-browser screenshot # Take a screenshot → /tmp/screenshot.png
agent-browser click "@e5" # Click element by ref (from snapshot)
agent-browser fill "@e3" "value" # Fill an input field
agent-browser type "text" # Type text at cursor
agent-browser press "Enter" # Press a key
agent-browser hover "@e7" # Hover over element
agent-browser eval "js code" # Execute JavaScript
agent-browser errors # Get JS console errors
agent-browser wait 2000 # Wait milliseconds
agent-browser back / forward # Browser navigation
agent-browser close # Close the connection
How to Use This Skill
Step 1 — Check Chrome is running with debugging
curl -s http://localhost:9222/json | python3 -m json.tool | head -20
If this fails, start Chrome with --remote-debugging-port=9222.
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.
- 7d ago First seen · 138 lines · 62 tokens per session scan C e0c316c792ae
agent-browser is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 1,110 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
create-scraper
Given a careers page URL, uses Playwright browser tools to explore the page, identify reliable scraping patterns (preferring hidden JSON APIs over DOM scraping), then writes a TypeScript Scraper subclass for that company.
verify
How to run and drive this app to verify UI/server changes at runtime.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…
browser-recording
Record a browser flow as a video/GIF for evidence — animations, transitions, and multi-step interactions that a still screenshot cannot prove. Drives the project's own Playwright through a bundled runner, then converts to mp4 + GIF via ffmpeg. Use when the user asks to record a demo, capture a GIF or video of the UI…
web-preview
Emit a hidden preview marker so Kiro Crew's right-panel "Browser" tab opens with a Load-preview card for the URL when you start a local web server for the user to preview. Use whenever you start a dev server or static server so the user can see a site/app you're working on (Vite, Next, npm run dev, python -m…