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 liatrio-labs/ai-prompts --skill browser-qagit clone --depth 1 https://github.com/liatrio-labs/ai-promptsWrote 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/liatrio-labs/ai-prompts/browser-qa)<a href="https://agentmods.dev/skills/liatrio-labs/ai-prompts/browser-qa"><img src="https://agentmods.dev/badge/skills/liatrio-labs/ai-prompts/browser-qa/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/liatrio-labs/ai-prompts/browser-qa"><img src="https://agentmods.dev/badge/skills/liatrio-labs/ai-prompts/browser-qa.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 | $0.00051 | $0.02831 |
| Opus 5 | $0.00026 | $0.01416 |
| Sonnet 5 | $0.00010 | $0.00566 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
browser-qa 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from urllib.request import urlopen How it starts
The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser QA
Overview
Use this skill for a focused, evidence-producing browser QA pass against a public URL, local page, or running web app. Browser automation drives the page; this skill defines which checks to run, what counts as evidence, how to classify results, where to store report data, and how to launch the local report viewer.
Keep the pass demo-sized. This is for quick confidence, reviewer proof, and actionable defect reports, not for full accessibility certification, cross-browser coverage, or CI replacement.
When to Use
Use this skill when the user asks you to:
- verify a page, local HTML file, UI change, or critical browser path
- check console errors, failed requests, broken images, keyboard navigation, or obvious layout/readability issues
- capture evidence for a browser-visible defect
- produce structured findings JSON and a local HTML report link
Do not use this skill for:
- load testing or performance benchmarking
- broad cross-browser/device certification
- full WCAG compliance audits
- replacing unit, integration, or end-to-end tests in CI
Composition Boundary
Load and use the agent-browser skill for browser mechanics before starting the QA pass. Confirm the browser automation path is available enough to navigate, inspect console/network state, and capture screenshots or snapshots.
This skill owns the QA judgment:
- which checks to run
- how each check is interpreted
- status classification:
pass,warn,fail, orunknown - findings JSON contract
- temp-folder report layout
- local report viewer startup and final link
Agent Browser Observability and Cleanup
For demos or multi-agent work, start the agent-browser dashboard before the QA pass so the user can watch what browser sessions are doing in the background:
agent-browser dashboard start
The dashboard defaults to http://localhost:4848 and shows live browser viewports plus command activity for all active sessions. Use it when the user wants to observe agent browser behavior, during webinar demos, or when multiple agents may be using browser automation at the same time.
What ships with it
7 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.
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.
- 12d ago First seen · 286 lines · 51 tokens per session scan A f7ce2e39620b
browser-qa is a skill published in the GitHub repository liatrio-labs/ai-prompts (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 51 tokens to every session and 2,831 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webapp-tester
Activates WebAppTester for automated web application testing strategy, test case design, and quality assurance. Use when you need to design a test plan for a web app, write Playwright or Cypress end-to-end tests, create API integration test suites, design accessibility test checklists, or analyze test coverage gaps.
webapp-testing
Write and run comprehensive web app tests — unit, integration, E2E with Playwright/Cypress, and visual regression.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
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…
verify-bb
Verify BB user journeys in an isolated source dev app using dev-browser@next and the matching source CLI. Use after BB feature changes or when asked to verify or smoke-test BB. The feature map covers core UI and agent interfaces, every repository plugin, desktop, mobile, and hosted services; select the affected…
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".