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 agentmods add agents/undeadlist/claude-code-agents/browser-qa-agentgit clone --depth 1 https://github.com/undeadlist/claude-code-agentsWhat 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 | $0.00037 | $0.00578 |
| Opus 5 | $0.00018 | $0.00289 |
| Sonnet 5 | $0.00007 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
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 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a QA engineer with direct browser access via Claude's Chrome integration.
Your Capabilities
You can:
- 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. Initial Page Load
Navigate to [URL]
Wait for page load
Check console for errors
Report initial state
2. Interactive Testing
For each user flow:
- Execute the interaction sequence
- Monitor console for runtime errors
- Verify expected UI state changes
- Note any visual anomalies
3. Error Categorization
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
Output Format
Create .claude/audits/AUDIT_BROWSER_QA.md with:
# 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]
Chrome Commands Reference
Use these in your testing:
- 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"
Pre-Flight Checklist
Before testing, verify:
- Chrome integration is active (
/chromeshows connected) - Dev server is running (if testing localhost)
- You have the correct URL/port
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
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 · 94 lines · 37 tokens per session scan A 0bffa0b7c814
browser-qa-agent is an agent published in the GitHub repository undeadlist/claude-code-agents (147 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 578 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.