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/billy-enrizky/openbrowser-aiWrote 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/plugins/billy-enrizky/openbrowser-ai/plugin)<a href="https://agentmods.dev/plugins/billy-enrizky/openbrowser-ai/plugin"><img src="https://agentmods.dev/badge/plugins/billy-enrizky/openbrowser-ai/plugin/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/plugins/billy-enrizky/openbrowser-ai/plugin"><img src="https://agentmods.dev/badge/plugins/billy-enrizky/openbrowser-ai/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openbrowser 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 24d 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.
What it actually says
{
"name": "openbrowser",
"version": "0.1.54",
"description": "AI-powered browser automation -- lets Claude control real web browsers to navigate, click, type, extract content, automate workflows, and reuse saved login sessions",
"author": {
"name": "OpenBrowser Team",
"email": "[email protected]"
},
"homepage": "https://github.com/billy-enrizky/openbrowser-ai",
"repository": "https://github.com/billy-enrizky/openbrowser-ai",
"license": "MIT",
"keywords": [
"browser",
"automation",
"web-scraping",
"testing",
"mcp",
"openbrowser",
"web-automation",
"ai-agent",
"file-download",
"cli-daemon"
]
}
What it installs
The manifest is a name and a version. 7 skills travel with it, and installing the plugin installs all of them — 463 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 24d ago Changed 36c6e6307c30
- 25d ago Changed fc6050fab4bf
- 1mo ago First seen · 25 lines scan A de4654d5d34d
openbrowser is a plugin published in the GitHub repository billy-enrizky/openbrowser-ai (276 stars, last pushed 18d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
browser-harness
Direct browser control via CDP. Drives the user's real Chrome (or a Browser Use cloud browser) with coordinate clicks, screenshots, and Python helpers — no selector hunting. Requires the one-time browser-harness CLI install (see the skill's references/install.md).
assay
Opens a page you changed, drives every control it offers, and reports what it did and what happened. One line every time, clean or not.
browser-gateway
Cloud browsers through the hosted BrowserGateway MCP server. When WebFetch is blocked or gets an empty page, Claude retries with a real browser.
muggle
Run real-browser end-to-end (E2E) acceptance tests on your web app from any AI coding agent. Generate test scripts from plain English, replay them on localhost, capture screenshots, and validate user flows like signup, checkout, and dashboards. Works across Claude Code, Cursor, Codex, and Windsurf.
notte
Browser automation for AI agents — real cloud or local browsers, observe/click/fill/scrape primitives, structured Pydantic extraction from dynamic pages, captcha solving and stealth mode, authenticated sessions via Vault, and one-command deployment of any browser automation as a scheduled, API-callable Notte Function.
vibe-browser
Drive your real, logged-in Chrome from Claude Code. Navigate, click, type, screenshot and read pages in the browser you already use - including a browser on a different machine, with no inbound port open.