Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/monoes/monomindnpx agentmods add skills/monoes/monomind/agent-browser-testingWrote 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/monoes/monomind/agent-browser-testing)<a href="https://agentmods.dev/skills/monoes/monomind/agent-browser-testing"><img src="https://agentmods.dev/badge/skills/monoes/monomind/agent-browser-testing/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/monoes/monomind/agent-browser-testing"><img src="https://agentmods.dev/badge/skills/monoes/monomind/agent-browser-testing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00036 | $0.09347 |
| Opus 5.5 | $0.00014 | $0.03739 |
| Sonnet 5.5 | $0.00007 | $0.01869 |
| Haiku 4.5 | $0.00004 | $0.00935 |
Grade A, and why
agent-browser-testing 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 2d 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 — 965 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Browser Testing — Full QA Suite
Engine: npx monomind browse — native TypeScript CDP client. No Playwright, no Puppeteer, no external binary. Every command below goes through this single infrastructure.
CRITICAL RULE: Never use mcp__claude-in-chrome__*, mcp__plugin_playwright__*, or any other browser tool. Always use npx monomind browse.
Commands at a Glance
All 55 subcommands — grouped by what they do.
| Group | Commands |
|---|---|
| Open / Navigate | open, navigate back|forward|reload, pushstate, connect, close |
| Inspect | snapshot, get url|title|text|html|value|attr|count|box|styles, errors, console |
| Find | find role|text|label|placeholder|testid|alttext|title|selector |
| Assert | is visible|enabled|checked, isvisible, isenabled, ischecked |
| Click / Tap | click, dblclick, tap, hover, focus |
| Type / Fill | fill, type, keyboard type|inserttext, keydown, keyup, press |
| Form | select, check, uncheck, upload |
| Scroll / Drag | scroll, scrollintoview, drag, swipe up|down|left|right |
| Mouse (raw) | mouse move|down|up|wheel |
| Wait | wait --text|--not-text|--url|--selector|--load|--ms|--fn|--download |
| Download | download <ref> <path>, wait --download <path> |
| Screenshot / PDF | screenshot, pdf, highlight, diff url |
| Clipboard | clipboard read|write|copy|paste |
| Dialogs | dialog accept|dismiss|status |
| Tabs | tab list|new|close|<targetId> |
| Windows | window new [url] (isolated context / incognito) |
| Frames | frame <ref>|main |
| Storage | storage local|session, cookies list|set|clear |
| Network | network route|unroute|headers|capture|requests|request |
| Emulation | set device|media|geo|offline|useragent|viewport|credentials, resize |
| Session | state save|load|list|show|clear|rename|clean, open --session|--state |
| JS / Init | eval, eval --stdin, addinitscript, removeinitscript |
| Record | record start|stop|restart|status |
| Performance | vitals, trace start|stop|status, profiler start|stop|heap, har start|stop|status |
| Batch | batch "cmd1" "cmd2" ... |
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.
- 2d ago First seen · 965 lines · 36 tokens per session scan A 44e8ae280afc
agent-browser-testing is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 9,347 once invoked, about $0.0001 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 2026-10-26.
Other skills, from other repositories
web-app-qa
Test a web app the way a real user would: click through the main flows, try odd inputs, watch for errors, and keep screenshots as proof. You get a bug report ranked by how serious each problem is.
agent-browser
Automates browser and Electron app interactions for user-flow validation.
browser-qa
Use when validating or debugging a workflow in the embedded browser and you need a reproducible, evidence-first loop.
user-testing-validator
Real-surface validation coordinator for engineering validation assignments. Exercises assigned assertions through browser, API, CLI, background, generated-artifact, migration/data, public-library, or parity surfaces and returns per-target verdicts with fresh evidence.
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.