Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Grasseed/google-search-browser-usenpx agentmods add skills/grasseed/google-search-browser-use/gemini-research-browser-useWrote 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/grasseed/google-search-browser-use/gemini-research-browser-use)<a href="https://agentmods.dev/skills/grasseed/google-search-browser-use/gemini-research-browser-use"><img src="https://agentmods.dev/badge/skills/grasseed/google-search-browser-use/gemini-research-browser-use/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/grasseed/google-search-browser-use/gemini-research-browser-use"><img src="https://agentmods.dev/badge/skills/grasseed/google-search-browser-use/gemini-research-browser-use.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 | $0.00051 | $0.05158 |
| Opus 5 | $0.00026 | $0.02579 |
| Sonnet 5 | $0.00010 | $0.01032 |
| Haiku 4.5 | $0.00005 | $0.00516 |
Grade A, and why
gemini-research-browser-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 634 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Research Browser Use
Overview
Perform research or queries using Google Gemini via Chrome DevTools Protocol (CDP). This method reuses the user's existing Chrome login session to interact with the Gemini web interface (https://gemini.google.com/).
Prerequisites
-
Python + websockets Verify:
python3 --version python3 -m pip show websocketsInstall if missing:
python3 -m pip install websockets -
Google Chrome Verify:
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --version -
CDP Port Availability Verify Chrome is listening (after launch in Step 2):
curl -s http://localhost:9222/json | python3 -m json.tool -
Non-default user data directory (required by Chrome) Chrome CDP requires a non-default profile path. Use a cloned profile so you keep login state.
rm -rf /tmp/chrome-gemini-profile rsync -a "$HOME/Library/Application Support/Google/Chrome/" /tmp/chrome-gemini-profile/
Method Comparison
| Method | Pros | Cons | Recommended |
|---|---|---|---|
| Chrome Remote Debugging (CDP) | Uses existing login, full automation, reliable | Requires Chrome restart with debugging flag | ✅ Yes |
browser-use --browser real |
Simple CLI | Opens new session without login | ❌ No |
browser_subagent |
Visual feedback | Rate limited, may fail | ❌ No |
✅ Recommended Method: Chrome Remote Debugging (CDP)
This is the most reliable method that uses your system Chrome with existing Google login.
Prerequisites
- Python 3 with
websocketslibrary - Google Chrome installed at
/Applications/Google Chrome.app/ - User logged into Google in Chrome
Step 1: Install websockets (if needed)
pip3 install websockets
# Or in virtual environment:
python3 -m venv .venv && ./.venv/bin/pip install websockets
Step 2: Launch Chrome with Remote Debugging (Non-default profile)
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.
- 10d ago First seen · 634 lines · 51 tokens per session scan E f42c6163ca67
gemini-research-browser-use is a skill published in the GitHub repository Grasseed/google-search-browser-use (3 stars, last pushed 7mo ago), licensed MIT. It adds 51 tokens to every session and 5,158 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…