Skip to content
Back to search

chrome-cdp-skill

SkillWorks with Claude CodeGitHub

Give your AI agent access to your live Chrome session — works out of the box, connects to tabs you already have open

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pasky-chrome-cdp-skill/badge.svg)](/listings/pasky-chrome-cdp-skill)

HTML

<a href="/listings/pasky-chrome-cdp-skill"><img src="/api/listings/pasky-chrome-cdp-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

As a pi skill

pi install git:github.com/pasky/chrome-cdp-skill@v1.0.1

For other agents (Amp, Claude Code, Cursor, etc.)

Clone or copy the `skills/chrome-cdp/` directory wherever your agent loads skills or context from. The only runtime dependency is **Node.js 22+** — no npm install needed.

Enable remote debugging in Chrome

Navigate to `chrome://inspect/#remote-debugging` and toggle the switch. That's it.

The CLI auto-detects Chrome, Chromium, Brave, Edge, and Vivaldi on macOS, Linux, and Windows. If your browser stores `DevToolsActivePort` in a non-standard location, set the `CDP_PORT_FILE` environment variable to the full path.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 62 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # chrome-cdp
  2. Let your AI agent see and interact with your **live Chrome session** — the tabs you already have open, your logged-in accounts, your current page state. No browser automation framework, no separate browser instance, no re-login.
  3. Works out of the box with any Chrome installation. One toggle to enable, nothing else to install.
  4. ## Why this matters
  5. Most browser automation tools launch a fresh, isolated browser. This one connects to the Chrome you're already running, so your agent can:
  6. - Read pages you're logged into (Gmail, GitHub, internal tools, ...)
  7. - Interact with tabs you're actively working in
  8. - See the actual state of a page mid-workflow, not a clean reload
  9. ## Installation
  10. ### As a pi skill
  11. ```bash
  12. pi install git:github.com/pasky/chrome-cdp-skill@v1.0.1
  13. ```
  14. ### For other agents (Amp, Claude Code, Cursor, etc.)
  15. Clone or copy the `skills/chrome-cdp/` directory wherever your agent loads skills or context from. The only runtime dependency is **Node.js 22+** — no npm install needed.
  16. ### Enable remote debugging in Chrome
  17. Navigate to `chrome://inspect/#remote-debugging` and toggle the switch. That's it.
  18. The CLI auto-detects Chrome, Chromium, Brave, Edge, and Vivaldi on macOS, Linux, and Windows. If your browser stores `DevToolsActivePort` in a non-standard location, set the `CDP_PORT_FILE` environment variable to the full path.
  19. ## Usage
  20. ```bash
  21. scripts/cdp.mjs list # list open tabs
  22. scripts/cdp.mjs shot <target> # screenshot → runtime dir
  23. scripts/cdp.mjs snap <target> # accessibility tree (compact, semantic)
  24. scripts/cdp.mjs html <target> [".selector"] # full HTML or scoped to CSS selector
  25. scripts/cdp.mjs eval <target> "expression" # evaluate JS in page context
  26. scripts/cdp.mjs nav <target> https://... # navigate and wait for load
  27. scripts/cdp.mjs net <target> # network resource timing
  28. scripts/cdp.mjs click <target> "selector" # click element by CSS selector
  29. scripts/cdp.mjs clickxy <target> <x> <y> # click at CSS pixel coordinates
  30. scripts/cdp.mjs type <target> "text" # type at focused element (works in cross-origin iframes)
  31. scripts/cdp.mjs loadall <target> "selector" # click "load more" until gone
  32. scripts/cdp.mjs evalraw <target> <method> [json] # raw CDP command passthrough
  33. scripts/cdp.mjs open [url] # open new tab (triggers Allow prompt)
  34. scripts/cdp.mjs stop [target] # stop daemon(s)
  35. ```
  36. `<target>` is a unique prefix of the targetId shown by `list`.
  37. ## Why not chrome-devtools-mcp?
  38. [chrome-devtools-mcp](https://github.com/ChromeDevTools/chrome-devtools-mcp) reconnects on every command, so Chrome's "Allow debugging" modal can re-appear repeatedly and target enumeration times out with many tabs open. `chrome-cdp` holds one persistent daemon per tab — the modal fires once, and it handles 100+ tabs reliably.
  39. ## How it works
  40. Connects directly to Chrome's remote debugging WebSocket — no Puppeteer, no intermediary. On first access to a tab, a lightweight background daemon is spawned that holds the session open. Chrome's "Allow debugging" modal appears once per tab; subsequent commands reuse the daemon silently. Daemons auto-exit after 20 minutes of inactivity.
  41. This approach is also why it handles 100+ open tabs reliably, where tools built on Puppeteer often time out during target enumeration.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.