A guide and command-line tool for inspecting and controlling pages displayed in Chrome. CDP, or Chrome DevTools Protocol, lets an agent read rendered pages, inspect the page structure, use existing login sessions, view network activity, and take screenshots.

Use it to navigate pages, inspect their visible content and accessibility information, interact with forms, review network requests, and capture screenshots.

It helps when the needed information appears only after JavaScript runs or depends on an already authenticated browser tab. It also defines which browser actions are routine and which require confirmation.

chrome-cdp — Skill for Claude Code and Codex by IgorWarzocha

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.

Any agent

npx skills add IgorWarzocha/howaboua-pi-stuff --skill chrome-cdp

Clone the repo

git clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuff

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/chrome-cdp/github.svg)](https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/chrome-cdp)

Your own site

<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/chrome-cdp"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/chrome-cdp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/chrome-cdp"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/chrome-cdp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,414 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.01414
Opus 5.5	$0.00016	$0.00566
Sonnet 5.5	$0.00008	$0.00283
Haiku 4.5	$0.00004	$0.00141

Measured 2mo ago against content hash 96de0426a4b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/cdp-lib/actions.mjs, scripts/cdp-lib/cli.mjs, scripts/cdp-lib/daemon.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/pi-skill-chrome-cdp/skills/chrome-cdp/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chrome CDP

Authorization

Treat the user's request and applicable repository or environment instructions as authorization for browser operations reasonably needed to complete the task. Do not ask again merely because CDP is involved.

Proceed without separate confirmation for:

opening or navigating established public sites relevant to the task
reading, searching, filtering, or opening content, including routine search forms and logged-in pages when authentication is needed to find what the user requested
reversible interface actions that do not publish, communicate, purchase, delete, or change account state

Ask before navigating the user's browser to an unfamiliar or low-trust site they did not identify. Also ask before consequential external actions such as sending or posting content, reacting publicly, submitting applications or other consequential forms, purchasing, uploading, deleting, or changing account settings—unless the user explicitly authorized it or it follows directly from an action you already agreed to take. Once authorized, act without a redundant confirmation.

Command path

The CLI lives next to this skill at scripts/cdp.mjs. Resolve it relative to this SKILL.md file, or use the installed package path if your host exposes one.

Prerequisites

Chrome (or Chromium, Brave, Edge, Vivaldi) with remote debugging enabled: open chrome://inspect/#remote-debugging and toggle the switch
Node.js 22+ (uses built-in WebSocket)
The CLI first tries HTTP discovery on CDP_PORT or 9222 for deterministic access to the logged-in browser
If that fixed-port discovery fails, it falls back to DevToolsActivePort; set CDP_PORT_FILE if the file is in a non-standard location

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
scripts/cdp.mjs tabsjson

Read the full file on GitHub · 107 lines

Files

What ships with it

10 files 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.

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.

2mo ago First seen · 107 lines · 41 tokens per session scan A 96de0426a4b7

Subscribe to this mod's changes

chrome-cdp is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (413 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,414 once invoked, about $0.0002 per session on Opus 5.5. 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.

Browser automation

chrome-cdp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chrome-cdpIgorWarzocha/howaboua-pi-stuff	Skill	413	yesterday	MIT	A	41	Claude Code, Codex
interactive-loginyc-software/qm	Skill	16k	today	MIT	A	46	Claude Code, Codex
pinchtab-mcppinchtab/pinchtab	Skill	11k	10d ago	MIT	A	52	Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skills	Skill	3.2k	yesterday	MIT	A	43	Claude Code
cua-driverdavidondrej/skills	Skill	4.3k	3d ago	MIT	A	68	Claude Code, Codex
open-design-browsercompozy/compozy	Skill	2.8k	today	MIT	A	56	Claude Code, Codex
southwestborski/travel-hacking-toolkit	Skill	895	today	MIT	A	40	Claude Code