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/bpc-oss/chrome-faithfulWrote 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/bpc-oss/chrome-faithful/chrome-faithful)<a href="https://agentmods.dev/plugins/bpc-oss/chrome-faithful/chrome-faithful"><img src="https://agentmods.dev/badge/plugins/bpc-oss/chrome-faithful/chrome-faithful/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/bpc-oss/chrome-faithful/chrome-faithful"><img src="https://agentmods.dev/badge/plugins/bpc-oss/chrome-faithful/chrome-faithful.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentos-chrome-cdp 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 8d 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": "agentos-chrome-cdp",
"version": "0.4.0",
"description": "Control exact logged-in Chrome profiles with a Codex-compatible browser API.",
"author": {
"name": "bpc-oss"
}
}
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 — 95 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.
- 8d ago First seen · 9 lines scan A 6de00b73b6cd
agentos-chrome-cdp is a plugin published in the GitHub repository bpc-oss/chrome-faithful (5 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 2026-08-31.
Other plugins, from other repositories
claude-in-chrome
Drive your real, logged-in Chrome from Claude Code, and list tabs across readable Chrome and Chromium profiles. Exposes the extension's browser tools through the Claude in Chrome bridge and adds a read-only listopentabs tool backed by local session data. Driving requires the connected extension and a running Chrome.
claude-bridge marketplace
Marketplace for Claude Bridge: autonomous browser handoff for Claude Code.
claude-bridge
Closes the gap between Claude Code and the browser. When a task needs the web, Claude Code drives the browser itself: your real logged-in Chrome (via the Claude extension) for account work, a headless browser for public lookups. It reports back in the terminal, with no copy-paste handoff.
fast-browser
Fast Playwright browser automation for Claude Code and Codex.
familiar
Control your real macOS Google Chrome via AppleScript — tab-scoped browser automation without the DevTools Protocol or Playwright.
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).