browser-qa-agent

A browser-based quality checker that tests a running web application by navigating pages, using controls, reading console messages, and recording what happens.

In plain words
What is it for?
Use it to test URLs, forms, buttons, and other user journeys, then document crashes, console errors, incorrect state changes, and visual issues in a browser QA report.
Why use it?
It helps find broken user flows, browser errors, and visual or interaction problems that may not appear from reading the source code alone.

Agent

Install

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.

agentmods
npx agentmods add agents/undeadlist/claude-code-agents/browser-qa-agent
Clone the repo
git clone --depth 1 https://github.com/undeadlist/claude-code-agents
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 0bffa0b7c814, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/browser-qa-agent.md · 94 lines

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:

  1. Chrome integration is active (/chrome shows connected)
  2. Dev server is running (if testing localhost)
  3. You have the correct URL/port

Testing Priorities

  1. Happy Path - Core user flows work
  2. Error States - Forms show validation, 404s handled
  3. Edge Cases - Empty states, long content, special characters
  4. Responsiveness - If applicable, test viewport changes
  5. Console Health - No errors during normal operation

Read the full file on GitHub · 94 lines

Changes

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.

  1. 2d ago First seen · 94 lines · 37 tokens per session scan A 0bffa0b7c814

Subscribe to this mod's changes

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.