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 timurgaleev/vibestack --skill connect-chromegit clone --depth 1 https://github.com/timurgaleev/vibestackWrote 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/timurgaleev/vibestack/connect-chrome)<a href="https://agentmods.dev/skills/timurgaleev/vibestack/connect-chrome"><img src="https://agentmods.dev/badge/skills/timurgaleev/vibestack/connect-chrome.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 5.1 | $0.00027 | $0.00512 |
| Opus 5 | $0.00014 | $0.00256 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
connect-chrome scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://127.0.0.1:9222/json/version >/dev/null 2>&1 && echo "CHROME_CDP_OK" || echo "CHROME_CDP_UNREACHABLE" What it actually says
When to invoke
Use when the browse daemon needs to act as your logged-in self — reuse the cookies/sessions from your real Chrome (e.g. QA-ing a page behind a login) without typing credentials into the automated browser.
/connect-chrome — Reuse your Chrome session
{{include lib/snippets/browse-setup.md}}
If BROWSE_NOT_AVAILABLE: tell the user the browse shim is required and stop.
1. Start Chrome with remote debugging
Ask the user to launch (or relaunch) Chrome with a debugging port — this exposes its cookies over CDP without leaking the password:
- macOS:
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --remote-debugging-port=9222 - Linux:
google-chrome --remote-debugging-port=9222 - Windows:
chrome.exe --remote-debugging-port=9222
Confirm it is reachable:
curl -s http://127.0.0.1:9222/json/version >/dev/null 2>&1 && echo "CHROME_CDP_OK" || echo "CHROME_CDP_UNREACHABLE"
If CHROME_CDP_UNREACHABLE: the port differs or Chrome isn't in debug mode — ask
the user to confirm the launch flag and port.
2. Start the daemon and import the cookies
"$B" daemon >/dev/null 2>&1 & # persistent session (skip if already running)
sleep 1
"$B" cookies import-cdp http://127.0.0.1:9222
3. Verify
Navigate to a page that requires login and confirm you're signed in:
"$B" goto <authenticated-url>
"$B" snapshot # look for signed-in markers (account name, logout link)
Report whether the session carried over. Stop the daemon with "$B" daemon-stop
when done. Cookies stay in the daemon's session only — they are never written to
the repo or logged.
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.
- 6d ago First seen · 65 lines · 27 tokens per session scan A ac1c13cbd022
connect-chrome is a skill published in the GitHub repository timurgaleev/vibestack (6 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 512 once invoked, about $0.0001 per session on Opus 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 skills, from other repositories
chrome-devtools
Browser automation and debugging using Puppeteer for API testing, screenshot capture, and web scraping. Use when you need to interact with web interfaces programmatically.
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…
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
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-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-auth
Browse sites that need a logged-in session with playwright-cli, using attach mode, saved storage state, or individual cookies. Use when a page is behind a login wall and a plain open lands on a sign-in screen.