chrome-cdp is a skill that lets an AI coding agent connect to an already running Chrome session, including its open tabs, logged-in accounts, and current page state. It is for agents that need to inspect or interact with the browser a person is already using.
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.
npx agentmods add skills/pasky/chrome-cdp-skill/chrome-cdpnpx skills add pasky/chrome-cdp-skill --skill chrome-cdpgit clone --depth 1 https://github.com/pasky/chrome-cdp-skillWrote 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/skills/pasky/chrome-cdp-skill/chrome-cdp)<a href="https://agentmods.dev/skills/pasky/chrome-cdp-skill/chrome-cdp"><img src="https://agentmods.dev/badge/skills/pasky/chrome-cdp-skill/chrome-cdp.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00813 |
| Opus 5 | $0.00016 | $0.00407 |
| Sonnet 5 | $0.00007 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
chrome-cdp 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 6d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- chrome-cdp — 100% identical, 0 lines differ
- chrome-cdp — 100% identical, 0 lines differ
- chrome-cdp — 86% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome CDP
Lightweight Chrome DevTools Protocol CLI. Connects directly via WebSocket — no Puppeteer, works with 100+ tabs, instant connection.
Prerequisites
- Chrome (or Chromium, Brave, Edge, Vivaldi) with remote debugging enabled: open
chrome://inspect/#remote-debuggingand toggle the switch - Node.js 22+ (uses built-in WebSocket)
- If your browser's
DevToolsActivePortis in a non-standard location, setCDP_PORT_FILEto its full path
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: screenshot-<target>.png in runtime dir
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 multipleevalcalls when the DOM can change between them (e.g. after clicking Ignore, card indices shift). Collect all data in oneevalor 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 open [url] # open new tab (each triggers Allow prompt)
scripts/cdp.mjs stop [target] # stop daemon(s)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 78 lines · 33 tokens per session scan A a682214143bd
chrome-cdp is a skill published in the GitHub repository pasky/chrome-cdp-skill (3,251 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 813 once invoked, about $0.0002 per session on Opus 5. 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 skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…