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/NeoDrew/chromeflowWrote 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/neodrew/chromeflow/plugin)<a href="https://agentmods.dev/plugins/neodrew/chromeflow/plugin"><img src="https://agentmods.dev/badge/plugins/neodrew/chromeflow/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/neodrew/chromeflow/plugin"><img src="https://agentmods.dev/badge/plugins/neodrew/chromeflow/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
chromeflow 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 28d 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": "chromeflow",
"version": "0.13.18",
"description": "Let Claude Code drive your real browser \u2014 clicks, fills forms, grabs API keys, writes them to .env. Bundles the chromeflow MCP server, permission allowlist, and usage skill.",
"homepage": "https://chromeflow.run",
"repository": "https://gitlab.com/NeoDrew/chromeflow",
"license": "MIT",
"keywords": [
"mcp",
"browser",
"chrome",
"automation",
"stripe",
"supabase",
"claude-code"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 273 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.
- 28d ago Changed 051db076496c
- 29d ago Changed 811b5ca0c7f0
- 1mo ago Changed 98e8d27c7243
- 1mo ago First seen · 18 lines scan A 7d4d078088a9
chromeflow is a plugin published in the GitHub repository NeoDrew/chromeflow (3 stars, last pushed 29d 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 2026-08-31.
Other plugins, from other repositories
browser-mcp
Any MCP client drives the Chrome you are already signed into, without approving every session. Chrome extension plus a local server. 40 tools, 20 sessions, MIT.
mochi
A browser companion for AI assistants. Bundled MCP tools for Chrome automation, persistent project memory (Continuum chain), and an in-page hint modal — pair with the Mochi Chrome extension.
chromeboost
Drive your real Chrome from Claude Code — movable/hideable HUD plus occlusion-aware cursor control that clicks through JS overlays, scrims and sticky bars. Bundles the ChromeBoost MCP server, permission allowlist, and usage skill.
chromeboost
Give Gemini hands in your own browser. Drives your real, logged-in Chrome with human-shaped clicks, drags and keystrokes, and hit-tests before it clicks so scrims and sticky bars cannot swallow the click.
byob
Control the user's real Chrome from Claude Code through a local, auditable bridge.
browser-relay
Let agents use the Chrome you already have open and logged in through a Skill + CLI, locally or across machines.