agentmods.dev

verify-chrome-cdp-ex

verify-chrome-cdp-ex is a skill for Claude Code, Cursor from EndeavorYen/chrome-cdp-ex. It costs 42 tokens per session (1,345 once invoked), scanned A, original, from a forked repository, MIT.

A verification workflow that drives a real, isolated Chrome browser through its developer control interface. It checks a user path on a pull request, which is a proposed code change for review, and records whether the fix works.

In plain words
What is it for?
It is for testing web interactions in headless Chrome, checking fixes on a pull request, collecting evidence, and testing that a button action fails when deliberately removed.
Why use it?
Unit tests can miss problems that appear only when a person uses the web page. This workflow provides a repeatable browser check without attaching to a normal daily browser.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: shipped in a Claude Code plugin, but also installed under .cursor/. Also seen: mentions AGENTS.md.

Part of the chrome-cdp-ex plugin — 2 skills shipped together

not rated 22repo yesterday A scan 42 tokens fork MIT

Good fit It is for testing web interactions in headless Chrome, checking fixes on a pull request, collecting evidence, and testing that a button action fails when deliberately removed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/endeavoryen/chrome-cdp-ex/verify-chrome-cdp-ex
View source ↗ EndeavorYen/chrome-cdp-ex endeavoryen.github.io
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 EndeavorYen/chrome-cdp-ex --skill verify-chrome-cdp-ex
Clone the repo
git clone --depth 1 https://github.com/EndeavorYen/chrome-cdp-ex

Made for: Claude Code, Cursor.

Or install chrome-cdp-ex, the plugin that ships this one along with the rest of its 2 skills.

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.

agentmods badge for verify-chrome-cdp-ex

README.md
[![agentmods](https://agentmods.dev/badge/skills/endeavoryen/chrome-cdp-ex/verify-chrome-cdp-ex/github.svg)](https://agentmods.dev/skills/endeavoryen/chrome-cdp-ex/verify-chrome-cdp-ex)
Your own site
<a href="https://agentmods.dev/skills/endeavoryen/chrome-cdp-ex/verify-chrome-cdp-ex"><img src="https://agentmods.dev/badge/skills/endeavoryen/chrome-cdp-ex/verify-chrome-cdp-ex/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.

agentmods 80×15 button for verify-chrome-cdp-ex

Your own site · 80×15
<a href="https://agentmods.dev/skills/endeavoryen/chrome-cdp-ex/verify-chrome-cdp-ex"><img src="https://agentmods.dev/badge/skills/endeavoryen/chrome-cdp-ex/verify-chrome-cdp-ex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.01345
Opus 5.5 $0.00017 $0.00538
Sonnet 5.5 $0.00008 $0.00269
Haiku 4.5 $0.00004 $0.00135

Measured 4d ago against content hash 9f424603ef20, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-chrome-cdp-ex scanned grade A with 1 finding 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (helpers/drive-once.sh), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Ready when `curl -s http://127.0.0.1:9444/json/version` responds. Use the port you set.
.cursor/skills/verify-chrome-cdp-ex/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verify-chrome-cdp-ex

Node.js 22+. Chrome is ${CHROME_BIN:-google-chrome}.

Helper: .cursor/skills/verify-chrome-cdp-ex/helpers/drive-once.sh.

Setup

  • Save local work on a branch before git fetch origin and git reset --hard onto the commit under test.
  • Run npm ci only when node_modules is missing or the lockfile changed.

Launch / Teardown

  • Unit tests do not need a browser.
  • .cursor/skills/verify-chrome-cdp-ex/helpers/drive-once.sh [repo] [evidence-dir] starts an isolated headless Chrome (CDP_VERIFY_PORT, default 9444, temporary profile) and a local http server (CDP_VERIFY_HTTP_PORT, default 41744), then tears both down. repo defaults to git rev-parse --show-toplevel. CDP_VERIFY_NO_ONCLICK=1 writes the page button without the onclick attribute (reverse check: the click fails with click-no-change and CDP_VERIFY_NO_ONCLICK=1 drive-once.sh exits non-zero).
  • Ready when curl -s http://127.0.0.1:9444/json/version responds. Use the port you set.
  • The script sets CDP_ISOLATED_ONLY=1. Do not attach to a daily browser. If the port is taken, change CDP_VERIFY_PORT.

Doctor

Read-only. Run this first when something looks wrong.

CDP_PORT=9444 ./bin/chrome-cdp doctor exits 0 and prints CDP: 127.0.0.1:9444 → Chrome/<version>. Pass the same port as CDP_VERIFY_PORT.

Test steps

Step Command Pass condition
Unit tests npm test exit 0
Lint npm run lint exit 0
Docs contract npm run check:docs exit 0 and prints Docs contract OK
Changelog fragments npm run check:changelog exit 0
Live smoke npm run smoke:live exit 0 and no FAIL line
User path .cursor/skills/verify-chrome-cdp-ex/helpers/drive-once.sh drive-once.sh exits 0

AGENTS.md "Verify before pushing" is the gate: npm test, npm run lint, npm run check:docs. npm run check:docs already checks changelog fragments. On a small machine, npm test -- --maxWorkers=2. A single area can start with npx vitest run tests/<area>-*.test.mjs. CI also runs Windows and smoke:live. Run npm run smoke:live locally only when attach, perceive, or act code changed and a browser is installed.

Read the full file on GitHub · 87 lines

Files

What ships with it

5 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.

  1. 4d ago First seen · 87 lines · 42 tokens per session scan A 9f424603ef20

Subscribe to this mod's changes

verify-chrome-cdp-ex is a skill published in the GitHub repository EndeavorYen/chrome-cdp-ex (22 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,345 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). It comes from a forked repository.

Browser automationClaude CodeE2E testingTestingai-agentbrowser-automationcdpchrome-devtools-protocolclaude-code-plugin
Related

Other skills, from other repositories

BrowserBash Browser Automation

BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream NDJSON results with CI exit codes — using free local Ollama…

PramodDutta/qaskills · 79 tokens

browser

Use this skill when the user says browser, /browser, test in Chrome, inspect a webpage, verify a localhost app, capture screenshots, check console/network errors, run browser QA, or automate browser flows with the Mochi browser MCP.

DevZonayed/Mochi · 50 tokens

test-site

Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.

microsoft/power-platform-skills · 46 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

browser-viz-verify

Verifies that a NetClaw-generated visualization HTML file (three.js, canvas, drawio, UML, markmap) actually renders correctly — screenshot, console-error check, and an optional Lighthouse audit. Use immediately after generating any browser-based visualization output, to close the QA gap that otherwise requires a human…

automateyournetwork/netclaw · 84 tokens

actionbook-web-test

Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…

actionbook/actionbook · 71 tokens