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 skills add mthines/agent-skills --skill aw-tester-chromegit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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/mthines/agent-skills/aw-tester-chrome)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00161 | $0.02663 |
| Opus 5 | $0.00081 | $0.01332 |
| Sonnet 5 | $0.00032 | $0.00533 |
| Haiku 4.5 | $0.00016 | $0.00266 |
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.
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.
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.
- 9d ago First seen · 226 lines · 161 tokens per session scan A 7713ccc48975
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.
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…
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…
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…
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.
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…
e2e-testing
Playwright and Cypress patterns, selectors, assertions, API mocking, visual testing, and CI/CD.