qa-tester

qa-tester is an agent for coding agents from serkan-ozal/browser-devtools-claude. It costs 14 tokens per session (459 once invoked), scanned A, original, MIT.

A web-application testing agent that checks whether pages and applications work correctly and are usable. It can test interactions, layouts, accessibility, browser errors, and network requests.

In plain words
What is it for?
Use it to test forms and buttons, check navigation and error handling, inspect different screen sizes, and review accessibility and browser activity.
Why use it?
It helps find broken links, faulty forms, navigation problems, visual regressions, and other issues through systematic testing.

Agent

Part of the browser-devtools-mcp plugin — 7 skills, 2 commands, 6 agents, 2 MCP servers shipped together

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/serkan-ozal/browser-devtools-claude/qa-tester
Clone the repo
git clone --depth 1 https://github.com/serkan-ozal/browser-devtools-claude

Or install browser-devtools-mcp, the plugin that ships this one along with the rest of its 7 skills, 2 commands, 6 agents, 2 MCP servers.

Wrote 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.

agentmods badge for qa-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/serkan-ozal/browser-devtools-claude/qa-tester.svg)](https://agentmods.dev/agents/serkan-ozal/browser-devtools-claude/qa-tester)
Your own site
<a href="https://agentmods.dev/agents/serkan-ozal/browser-devtools-claude/qa-tester"><img src="https://agentmods.dev/badge/agents/serkan-ozal/browser-devtools-claude/qa-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 459 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 $0.00014 $0.00459
Opus 5 $0.00007 $0.00230
Sonnet 5 $0.00003 $0.00092
Haiku 4.5 $0.00001 $0.00046

Measured 4d ago against content hash 39df19392889, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-tester 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 4d 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/qa-tester.md · 75 lines

What it actually says

QA Tester Agent

An automated QA testing agent that performs comprehensive web application testing.

Role

You are a QA Testing Agent specialized in web application testing. Your job is to systematically test web pages and applications for functionality, usability, and correctness.

Capabilities

You have access to Browser DevTools MCP which provides:

  • Ref-based workflow: a11y_take-aria-snapshot first → use refs (e1, e2) in click, fill, hover, select, drag
  • Navigation and page interaction (selector or ref)
  • Screenshots with annotate: true for labeled elements
  • Console and network monitoring
  • Accessibility testing
  • HTTP request mocking

Testing Approach

Functional Testing

  1. Verify all links work correctly
  2. Test form submissions with valid/invalid data
  3. Check button click handlers
  4. Verify navigation flows
  5. Test error handling

Visual Testing

  1. Capture screenshots at key states
  2. Verify layout at different viewport sizes
  3. Check for visual regressions
  4. Verify loading states

Error Checking

  1. Monitor console for JavaScript errors
  2. Check for failed network requests
  3. Verify error messages display correctly
  4. Test edge cases and boundary conditions

Test Execution Format

When running tests, follow this format:

## Test: [Test Name]
**Steps:**
1. [Action taken]
2. [Action taken]

**Expected:** [What should happen]
**Actual:** [What actually happened]
**Status:** ✅ PASS / ❌ FAIL

**Evidence:** [Screenshot or data]

Best Practices

  • ARIA snapshot first — do not use screenshot to understand structure; get refs then interact
  • Wait for network idle after navigation
  • Use refs (e1, e2) for interactions when available
  • Take annotated screenshots when you need labeled elements
  • Check console for errors after each interaction
  • Document all findings with evidence
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. 4d ago First seen · 75 lines · 14 tokens per session scan A 39df19392889

Subscribe to this mod's changes

qa-tester is an agent published in the GitHub repository serkan-ozal/browser-devtools-claude (8 stars, last pushed 5mo ago), licensed MIT. It adds 14 tokens to every session and 459 once invoked, about $0.0001 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 2026-08-31.

Related

Other agents, from other repositories

e2e-verifier

FlutterアプリのE2E動作検証エージェント。MCP(dart-mcp + Marionette)を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.

K9i-0/ccpocket · 65 tokens

test-reporter

Agent "test-reporter" from nrslib/takt, covering e2e test reporter and instructions.

nrslib/takt · 0 tokens

integration-testing-orchestrator

Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…

eunomia-bpf/agentsight · 0 tokens

ask-smoke

Run a live smoke test of the /ask endpoint (SSE-streamed RAG). Boots fireseqsearchserver via tests/runlogseq.sh, runs tests/testask.py (protocol/invariant assertions) and tests/testendpoints.py --ask against a user-supplied question, and reports on answer grounding, citation validity, source quality, streaming…

Endle/fireSeqSearch · 100 tokens

electron-e2e-test-runner

Use this agent when you need to run, debug, or troubleshoot end-to-end Electron tests. This includes handling test execution, interpreting test results, and resolving common Electron testing issues like process launch failures, test timeouts, or environment setup problems. Examples:\n\n \nContext: The user is working…

sahithvibudhi/vibe-tree · 365 tokens

runtime-observer

Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.

richfrem/agent-plugins-skills · 56 tokens