Chrome Cdp Live Browser
Let your agent control your real Chrome tabs via CDP—screenshots, clicks, navigation, and reading logged-in page state.
Overview
Chrome CDP Live Browser is an agent skill most often used in Build (also Validate, Operate) that controls your live Chrome tabs via CDP with existing logins and page state.
Install
npx skills add https://github.com/aradotso/trending-skills --skill chrome-cdp-live-browserWhat is this skill?
- Connects to your running Chrome via CDP—not a headless disposable profile
- Persistent per-tab daemon; Allow debugging modal once per tab
- Requires only Node.js 22+; pi install git:github.com/pasky/chrome-cdp-skill@v1.0.1
- Supports 100+ open tabs and cross-origin iframe type commands
- Triggers include screenshots, clicks, navigate URL, read tab content
- 100+ tab support documented
- Node.js 22+ required; no npm install for core usage
Adoption & trust: 1.4k installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent cannot see or act on the Chrome tabs you already use, so automations miss logins and real page context.
Who is it for?
Indie builders who debug and automate against authenticated web apps in their daily Chrome profile.
Skip if: CI-only headless pipelines that must not touch a developer’s personal browser or unattended production machines.
When should I use this skill?
When triggers match controlling Chrome, interacting with open tabs, screenshots, clicks, navigation, reading tab content, or Chrome DevTools Protocol.
What do I get? / Deliverables
The agent reads and interacts with open tabs through CDP—navigate, screenshot, click, and type—including cross-origin iframes when needed.
- CDP-connected agent commands against live tabs
- Screenshots and DOM interactions from the user’s session
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary shelf is Build/agent-tooling because the skill installs browser control capability for agents, though it supports validation and shipping checks in a live session. Agent-tooling is the right facet for CDP WebSocket daemons and cross-origin typing, not generic frontend component work.
Where it fits
Install the pi skill so your agent can navigate and read content from tabs you already have open.
Click through a logged-in prototype flow without re-authenticating in a fresh headless profile.
Capture a screenshot of the failing dashboard tab to compare with user-reported UI state.
How it compares
Skill package for live CDP session control—not the same as spinning an isolated headless browser for every task.
Common Questions / FAQ
Who is chrome-cdp-live-browser for?
Solo builders and agent users who need DevTools Protocol access to real Chrome tabs with existing sessions.
When should I use chrome-cdp-live-browser?
During Build/agent-tooling to wire browser actions; in Validate/prototype to exercise flows in a logged-in tab; in Operate/errors when reproducing issues only visible in your live browser.
Is chrome-cdp-live-browser safe to install?
It grants agents control of your browser and local debugging ports—review source, trust the publisher, and check the Security Audits panel on this Prism page.
SKILL.md
READMESKILL.md - Chrome Cdp Live Browser
# chrome-cdp: Live Chrome Session for AI Agents > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. `chrome-cdp` connects your AI agent directly to your running Chrome browser via the Chrome DevTools Protocol (CDP). Unlike browser automation tools that spin up fresh isolated browsers, this connects to tabs you already have open — with your logins, cookies, and current page state intact. ## What It Does - **Live session access** — reads and interacts with tabs you're already logged into - **Persistent daemon** — one WebSocket daemon per tab; the "Allow debugging" modal appears once, not on every command - **No npm install** — only Node.js 22+ required - **100+ tab support** — handles large numbers of open tabs reliably - **Cross-origin iframe support** — `type` command works even inside cross-origin iframes ## Installation ### As a pi skill ```bash pi install git:github.com/pasky/chrome-cdp-skill@v1.0.1 ``` ### Manual (for Amp, Claude Code, Cursor, Codex, etc.) ```bash git clone https://github.com/pasky/chrome-cdp-skill # Copy the skills/chrome-cdp/ directory to wherever your agent loads context from ``` ### Enable Remote Debugging in Chrome 1. Open Chrome and navigate to: `chrome://inspect/#remote-debugging` 2. Toggle the **"Enable remote debugging"** switch That's all. No flags, no relaunching Chrome. The script auto-detects Chrome, Chromium, Brave, Edge, and Vivaldi on macOS, Linux, and Windows. For non-standard installs: ```bash export CDP_PORT_FILE=/path/to/DevToolsActivePort ``` ## Key Commands All commands use `scripts/cdp.mjs` as the entry point. `<target>` is a unique prefix of the targetId shown by `list`. ### List Open Tabs ```bash node scripts/cdp.mjs list # Output: # A1B2C3 https://github.com/pasky/chrome-cdp-skill chrome-cdp-skill # D4E5F6 https://mail.google.com/mail/u/0/ Gmail ``` ### Screenshot a Tab ```bash node scripts/cdp.mjs shot A1B2 # Saves screenshot to runtime dir, prints the file path ``` ### Accessibility Tree (Semantic Snapshot) ```bash node scripts/cdp.mjs snap A1B2 # Returns compact, semantic accessibility tree — best for understanding page structure ``` ### Full HTML or Scoped HTML ```bash node scripts/cdp.mjs html A1B2 # full page HTML node scripts/cdp.mjs html A1B2 ".main-content" # scoped to CSS selector node scripts/cdp.mjs html A1B2 "#article-body" # scoped to ID ``` ### Evaluate JavaScript ```bash node scripts/cdp.mjs eval A1B2 "document.title" node scripts/cdp.mjs eval A1B2 "window.location.href" node scripts/cdp.mjs eval A1B2 "document.querySelectorAll('a').length" ``` ### Navigate to URL ```bash node scripts/cdp.mjs nav A1B2 https://example.com # Navigates and waits for page load ``` ### Network Resource Timing ```bash node scripts/cdp.mjs net A1B2 # Shows network resource timing for the current page ``` ### Click an Element ```bash node scripts/cdp.mjs click A1B2 "button.submit" node scripts/cdp.mjs click A1B2 "#login-btn" node scripts/cdp.mjs click A1B2 "[data-testid='confirm']" ``` ### Click at Coordinates ```bash node scripts/cdp.mjs clickxy A1B2 320 480 # Clicks at CSS pixel coordinates (x=320, y=480) ``` ### Type Text ```bash node scripts/cdp.mjs type A1B2 "Hello, world!" # Types at the currently focused element — works in cross-origin iframes ``` ### Load More (Click Until Gone) ```bash node scripts/cdp.mjs loadall A1B2 "button.load-more" # Keeps clicking the selector until it disappears from the DOM ``` ### Open a New Tab