What is chrome-multi-instance-warn?

A Claude Code plugin that warns once per session when browser-driving work may start another Chrome instance or use parallel work based on the computer's processor count.

Use it with browser automation involving Playwright, Puppeteer, Chrome, or CDP when an existing browser session or task concurrency matters.

It draws attention to unnecessary browser processes and potentially excessive parallel tasks without blocking the agent.

chrome-multi-instance-warn — Plugin by didvc

Install

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.

agentmods

npx agentmods add plugins/didvc/claude-chrome-multi-instance-warn/chrome-multi-instance-warn

Claude Code

/plugin marketplace add didvc/claude-chrome-multi-instance-warn

Clone the repo

git clone --depth 1 https://github.com/didvc/claude-chrome-multi-instance-warn

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

chrome-multi-instance-warn 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.

plugins/chrome-multi-instance-warn/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "chrome-multi-instance-warn",
  "displayName": "Chrome Multi-Instance Warn",
  "version": "0.1.0",
  "description": "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.",
  "author": {
    "name": "didvc",
    "url": "https://github.com/didvc"
  },
  "repository": "https://github.com/didvc/claude-chrome-multi-instance-warn",
  "license": "MIT",
  "keywords": ["playwright", "puppeteer", "chrome", "cdp", "browser", "parallel", "hooks", "safety"]
}

Changes

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 · 14 lines scan A 396d242d640a

Subscribe to this mod's changes

chrome-multi-instance-warn is a plugin published in the GitHub repository didvc/claude-chrome-multi-instance-warn (1 stars, last pushed 19d 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.

Browser automation Planning Productivity agentic-ai ai-agents browser-automation chrome-devtools-protocol claude-code claude-code-hooks

chrome-multi-instance-warn

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

yutori

yutori-plugins

devharness

frane-vibesurfer

vibesurfer

kaboom-workflows