aw-tester-chrome

aw-tester-chrome is a skill for Claude Code from mthines/agent-skills. It costs 161 tokens per session (2,663 once invoked), scanned A, original, MIT.

A browser-based UI test runner that follows written steps in an already open Chrome session and checks the results.

In plain words
What is it for?
It is for running UI verification specs against a local, in-session Chrome browser. It needs the claude-in-chrome extension and cannot run in CI or a sub-agent.
Why use it?
It lets you verify a website by seeing each page while navigating and acting, including pages where the browser is already signed in.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Part of the mthines-agent-skills plugin — 55 skills, 4 agents shipped together

Good fit It is for running UI verification specs against a local, in-session Chrome browser. It needs the claude-in-chrome extension and cannot run in CI or a sub-agent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mthines/agent-skills/aw-tester-chrome
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 mthines/agent-skills --skill aw-tester-chrome
Clone the repo
git clone --depth 1 https://github.com/mthines/agent-skills

Made for: Claude Code.

Or install mthines-agent-skills, the plugin that ships this one along with the rest of its 55 skills, 4 agents.

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 aw-tester-chrome

README.md
[![agentmods](https://agentmods.dev/badge/skills/mthines/agent-skills/aw-tester-chrome/github.svg)](https://agentmods.dev/skills/mthines/agent-skills/aw-tester-chrome)
Your own site
<a href="https://agentmods.dev/skills/mthines/agent-skills/aw-tester-chrome"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/aw-tester-chrome/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 aw-tester-chrome

Your own site · 80×15
<a href="https://agentmods.dev/skills/mthines/agent-skills/aw-tester-chrome"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/aw-tester-chrome.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,663 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00161 $0.02663
Opus 5 $0.00081 $0.01332
Sonnet 5 $0.00032 $0.00533
Haiku 4.5 $0.00016 $0.00266

Measured 9d ago against content hash 7713ccc48975, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

aw-tester-chrome 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 9d 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.

skills/workflow/autonomous-workflow/aw-tester-chrome/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aw-tester-chrome — In-Session Spec Runner

You are the Chrome runner. Same spec, same verdict as aw-tester — different engine. You drive the user's real Chrome through the claude-in-chrome extension, in this session, seeing the page between every step. That see→act loop is the point: no throwaway batch script, no blind compile, and the browser is already logged in, so a local run is fast.

Read the spec-run contract first. It owns the locator ladder, the auth semantics, the spec-parsing rules, and the verdict schema. This file owns only how Chrome executes them. Where the two ever disagree, the contract wins.

[!NOTE] This runner needs the claude-in-chrome browser extension. It is a local, in-session tool. It cannot run inside a sub-agent (sub-agents have no claude-in-chrome tools) and cannot run in a remote / CI environment. Those callers use aw-tester (Playwright). See § Preflight for the fallback.


Critical First Actions

1. Load the browser tools

If the mcp__claude-in-chrome__* tools are deferred, load the set you need in one call:

ToolSearch "select:mcp__claude-in-chrome__tabs_context_mcp,mcp__claude-in-chrome__navigate,mcp__claude-in-chrome__read_page,mcp__claude-in-chrome__find,mcp__claude-in-chrome__get_page_text,mcp__claude-in-chrome__computer,mcp__claude-in-chrome__form_input,mcp__claude-in-chrome__read_network_requests,mcp__claude-in-chrome__tabs_create_mcp"

2. Preflight — is the extension connected?

Call tabs_context_mcp. If it errors or returns no browser, the extension is not connected. Do not improvise. Emit this and stop:

verdict: inconclusive
fallback: playwright
specs: []
notes: claude-in-chrome extension not connected — re-run with --driver playwright (aw-tester).

preview-spec run --driver auto reads fallback: playwright and, in auto mode, asks the user before dispatching aw-tester — it does not fall back silently. A direct caller should do the same. An explicit --driver chrome stops here and reports this verdict as-is.

Read the full file on GitHub · 226 lines

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. 9d ago First seen · 226 lines · 161 tokens per session scan A 7713ccc48975

Subscribe to this mod's changes

aw-tester-chrome is a skill published in the GitHub repository mthines/agent-skills (13 stars, last pushed today), licensed MIT. It adds 161 tokens to every session and 2,663 once invoked, about $0.0008 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 2026-09-03.

Related

Other skills, from other repositories

browser-testing-with-devtools

Use Chrome DevTools MCP to inspect, debug, and verify anything that runs in a browser — DOM structure, console errors, network requests, performance traces, and accessibility. Use when building or fixing browser UI, diagnosing a runtime bug that isn't visible from source code alone, or verifying a fix actually works…

shennawardana23/skillme · 80 tokens

browser-testing-with-devtools

Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…

addyosmani/agent-skills · 68 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

web-test

A browser-automation tool for testing the 1C:Enterprise web client. It uses Playwright to navigate sections, fill forms, read tables and reports, and perform user actions in a browser.

Nikolay-Shirokov/cc-1c-skills · 44 tokens

playwright-visual-testing

Add, repair, or review Playwright visual regression tests for browser-facing .NET apps, including screenshot baselines, Pixelmatch thresholds, deterministic rendering, and GitHub Actions artifacts. USE FOR: toHaveScreenshot, page.screenshot visual checks, Pixelmatch/pngjs comparison scripts, visual baseline updates…

managedcode/dotnet-skills · 101 tokens

e2e-testing

Playwright and Cypress patterns, selectors, assertions, API mocking, visual testing, and CI/CD.

cosmicstack-labs/mercury-agent-skills · 24 tokens