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.
/plugin marketplace add NeoDrew/chromeflownpx agentmods add plugins/neodrew/chromeflow/plugingit clone --depth 1 https://github.com/NeoDrew/chromeflowGrade 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 yesterday.
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": "0.9.5",
"description": "Let Claude Code drive your real browser — 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://github.com/NeoDrew/chromeflow",
"license": "MIT",
"keywords": [
"mcp",
"browser",
"chrome",
"automation",
"stripe",
"supabase",
"claude-code"
]
}
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.
- yesterday First seen · 18 lines scan A 7d4d078088a9
chromeflow is a plugin published in the GitHub repository NeoDrew/chromeflow (2 stars, last pushed 3mo 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-relay
Let agents use the Chrome you already have open and logged in through a Skill + CLI, locally or across machines.
byob
Claude Code plugins from the byob project.
byob
Control the user's real Chrome from Claude Code through a local, auditable bridge.
chromeboost
ChromeBoost — drive your real Chrome from Claude Code with occlusion-aware cursor control and a movable HUD.
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.
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.