chrome-cdp

name	chrome-cdp
user-invocable	true
description	Interact with local Chrome browser session (only on explicit user approval after being asked to inspect, debug, or interact with a page open in Chrome)

Chrome CDP

Driving a LOGGED-IN session? Use the logged-in-browser skill (chrome-devtools MCP on :9222, full CDP, auto-launched by the chrome-debug-on.sh hook) — that's the one default for authenticated driving. This chrome-cdp CLI is the fast-scrape tool: read / screenshot / snapshot / loadall across many tabs. Same :9222 backend, different job.

Lightweight Chrome DevTools Protocol CLI. Connects directly via WebSocket — no Puppeteer, works with 100+ tabs, instant connection.

Prerequisites

• Chrome with remote debugging enabled: open chrome://inspect/#remote-debugging and toggle the switch
• Node.js 22+ (uses built-in WebSocket)

Keep Debugging Always On

The "Allow debugging" modal fires once per tab when a daemon first connects. To minimize popups:

1. Pre-warm daemons for tabs you use often (production sites, staging):

   bash ~/.claude/skills/chrome-cdp/scripts/ensure-cdp.sh https://your-app.pages.dev/
   

   This finds or opens the tab, warms the daemon (one popup), then all subsequent commands work instantly for 20 minutes.

2. Daemons auto-extend: Any command resets the 20-minute idle timer. Active debugging sessions stay warm indefinitely.

3. Other skills auto-warm: /carmack and /ship now auto-warm CDP daemons for production URLs before doing live checks.

Commands

All commands use scripts/cdp.mjs. The <target> is a unique targetId prefix from list; copy the full prefix shown in the list output (for example 6BE827FA). The CLI rejects ambiguous prefixes.

List open pages

scripts/cdp.mjs list

Take a screenshot

scripts/cdp.mjs shot <target> [file]    # default: /tmp/screenshot.png

Captures the viewport only. Scroll first with eval if you need content below the fold. Output includes the page's DPR and coordinate conversion hint (see Coordinates below).

Accessibility tree snapshot

scripts/cdp.mjs snap <target>

Evaluate JavaScript

scripts/cdp.mjs eval <target> <expr>

Watch out: avoid index-based selection (querySelectorAll(...)[i]) across multiple eval calls when the DOM can change between them (e.g. after clicking Ignore, card indices shift). Collect all data in one eval or use stable selectors.

Other commands

scripts/cdp.mjs html    <target> [selector]   # full page or element HTML
scripts/cdp.mjs nav     <target> <url>         # navigate and wait for load
scripts/cdp.mjs net     <target>               # resource timing entries
scripts/cdp.mjs click   <target> <selector>    # click element by CSS selector
scripts/cdp.mjs clickxy <target> <x> <y>       # click at CSS pixel coords
scripts/cdp.mjs type    <target> <text>         # Input.insertText at current focus; works in cross-origin iframes unlike eval
scripts/cdp.mjs loadall <target> <selector> [ms]  # click "load more" until gone (default 1500ms between clicks)
scripts/cdp.mjs evalraw <target> <method> [json]  # raw CDP command passthrough
scripts/cdp.mjs stop    [target]               # stop daemon(s)

Coordinates

shot saves an image at native resolution: image pixels = CSS pixels × DPR. CDP Input events (clickxy etc.) take CSS pixels.

CSS px = screenshot image px / DPR

shot prints the DPR for the current page. Typical Retina (DPR=2): divide screenshot coords by 2.

Tips

• Prefer snap --compact over html for page structure.
• Use type (not eval) to enter text in cross-origin iframes — click/clickxy to focus first, then type.
• Chrome shows an "Allow debugging" modal once per tab on first access. A background daemon keeps the session alive so subsequent commands need no further approval. Daemons auto-exit after 20 minutes of inactivity.