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/VibeTechnologies/vibe-mcpWrote 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/vibetechnologies/vibe-mcp/vibe-browser)<a href="https://agentmods.dev/plugins/vibetechnologies/vibe-mcp/vibe-browser"><img src="https://agentmods.dev/badge/plugins/vibetechnologies/vibe-mcp/vibe-browser.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
vibe-browser 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 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.
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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "vibe-browser",
"displayName": "Vibe Browser",
"version": "0.3.6",
"description": "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.",
"author": {
"name": "Vibe Technologies",
"url": "https://vibebrowser.app"
},
"homepage": "https://vibebrowser.app",
"repository": "https://github.com/VibeTechnologies/vibe-mcp",
"license": "Apache-2.0",
"keywords": [
"browser",
"chrome",
"browser-automation",
"web-automation",
"mcp",
"playwright-alternative",
"puppeteer-alternative"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 63 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.
- 7d ago First seen · 24 lines scan A 9b6777d4c8f2
vibe-browser is a plugin published in the GitHub repository VibeTechnologies/vibe-mcp (3 stars, last pushed 15d ago), licensed Apache-2.0. 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 2026-08-31.
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).
browser-skills
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
playwright-rs
Procedural reference for writing Rust browser automation with playwright-rs: adding the crate and installing its browsers, object model, the locator!() macro, builder options, auto-wait semantics, and trace capture.
ghostlight
Governed, semantic tools for driving the user's real browser: navigate, inspect, find, click, fill, type, screenshot, record. Local by construction, with optional policy and audit.
tandem
A shared Chrome browser (human + Claude, CDP + Playwright MCP) that learns how each site is navigated: the human drives with the mouse and clears captchas/logins, Claude operates over CDP, and tandem:map persists per-site navigation memory (durable locators, drift, auto-injection).
vibelens
Gives Claude eyes on localhost. Captures a screenshot, console/network errors and a token-optimized DOM snapshot of your dev server so UI bugs get fixed from evidence instead of guesswork.