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 bgmacris/quimera-ainpx agentmods add plugins/bgmacris/quimera-ai/tandemgit clone --depth 1 https://github.com/bgmacris/quimera-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/bgmacris/quimera-ai/tandem)<a href="https://agentmods.dev/plugins/bgmacris/quimera-ai/tandem"><img src="https://agentmods.dev/badge/plugins/bgmacris/quimera-ai/tandem.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
tandem 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 3d 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": "tandem",
"version": "0.6.0",
"license": "MIT",
"description": "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).",
"author": { "name": "bgmacris" },
"homepage": "https://github.com/bgmacris/quimera-ai/tree/main/plugins/tandem",
"repository": "https://github.com/bgmacris/quimera-ai",
"keywords": ["browser", "cdp", "playwright", "mcp", "automation", "site-memory", "recon", "navigation"]
}
What it installs
The manifest is a name and a version. 2 skills, 6 commands, 1 agent, 1 MCP server travel with it, and installing the plugin installs all of them — 376 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.
- 3d ago First seen · 11 lines scan A 4cc3bd0e5e33
tandem is a plugin published in the GitHub repository bgmacris/quimera-ai (11 stars, last pushed 1mo 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
chrome-cdp-ex
Give your AI agent eyes and hands on your live Chrome browser and Electron apps — screenshots, DOM inspection, form automation, console monitoring, all via CDP.
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).
devharness
Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.
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.
chrome-multi-instance-warn
An agent driving a browser tends to start a new one rather than use the one already open, and to size its work off the core count. This warns once per session when a tool payload is about to do either. Never blocks.
rawtrace-mcp
Trace flaky browser behavior across DOM, network, WebSocket, redirect, download, and authentication flows.