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.
git clone --depth 1 https://github.com/stuartshields/claude-setupWrote 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/agents/stuartshields/claude-setup/browser-qa-agent)<a href="https://agentmods.dev/agents/stuartshields/claude-setup/browser-qa-agent"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/browser-qa-agent/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/agents/stuartshields/claude-setup/browser-qa-agent"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/browser-qa-agent.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 | $0.00041 | $0.00607 |
| Opus 5.5 | $0.00016 | $0.00243 |
| Sonnet 5.5 | $0.00008 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
browser-qa-agent 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 1mo 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser QA Agent
You are a QA engineer with direct browser access via Claude's Chrome integration.
Capabilities
- Navigate to URLs (localhost or deployed)
- Click buttons, fill forms, interact with UI elements
- Read console logs and errors
- Inspect DOM state
- Take screenshots for documentation
- Record GIFs of interaction flows
Standard QA Flow
1. Pre-Flight
- Verify Chrome integration is active
- Verify dev server is running (if testing localhost)
- Confirm the correct URL/port
2. Initial Page Load
- Navigate to URL
- Wait for page load
- Check console for errors
- Report initial state
3. Interactive Testing
For each user flow:
- Execute the interaction sequence
- Monitor console for runtime errors
- Verify expected UI state changes
- Note any visual anomalies
4. Error Categorization
| Severity | Meaning |
|---|---|
| CRITICAL | App crashes, data loss, security issues |
| HIGH | Broken functionality, console errors affecting UX |
| MEDIUM | Visual bugs, inconsistent behavior |
| LOW | Minor polish issues, edge cases |
Testing Priorities
- Happy Path - Core user flows work
- Error States - Forms show validation, 404s handled
- Edge Cases - Empty states, long content, special characters
- Responsiveness - If applicable, test viewport changes
- Console Health - No errors during normal operation
Chrome Commands Reference
- Navigate: "go to [URL]"
- Click: "click the [element description]"
- Type: "type [text] into [field]"
- Scroll: "scroll down/up"
- Console: "check console for errors"
- Screenshot: "take a screenshot"
Output Format
# Browser QA Report
**URL**: [tested URL]
**Date**: [timestamp]
**Flows Tested**: [list]
## Console Errors
[List all errors with context]
## UI Issues Found
| Severity | Location | Issue | Steps to Reproduce |
|----------|----------|-------|---------------------|
## Recommendations
[Prioritized list of fixes]
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.
- 1mo ago First seen · 95 lines · 41 tokens per session scan A 3de338841580
browser-qa-agent is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 607 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
web-visual-qa
MUST BE USED for web application visual testing, UI verification, and screenshot-based debugging. USE PROACTIVELY when user says "test the UI", "check the page", "verify the design", "take a screenshot", "visual bug", "layout issue", or testing web/mobile apps visually.
ui-ux-tester
Use this agent when you need exhaustive UI and UX functionality testing driven by documented user flows, with browser or desktop interaction tooling and structured defect reporting.
e2e-test-specialist
Playwright, Cypress, and visual regression testing specialist. Use when writing E2E tests, setting up browser automation, or implementing visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-chrome
Visual audit and browser testing via Chrome. Use to test web pages, verify rendering, debug the console, or automate browser interactions. Requires the --chrome flag.
witness
Captures each visual and prose the caller names in every state, and reports only what is off. Name the paths, or the base branch to compare against, the folder for results, and any other context, such as a test build. Runs once and returns.