qa-verifier

qa-verifier is an agent for coding agents from martian56/claude-engineer. It costs 62 tokens per session (456 once invoked), scanned A, original, MIT.

A review-only agent that tests a running web application through a browser and reports whether its main user flows, accessibility, performance, design, and browser behavior meet the stated checks. WCAG is a set of international accessibility guidelines for websites.

In plain words
What is it for?
Use it to verify key frontend journeys, inspect browser console errors, run accessibility checks, optionally measure page speed with Lighthouse, and compare the interface with DESIGN.md.
Why use it?
It provides independent evidence before someone claims the application is finished, including checks for broken interactions, browser errors, failed requests, and accessibility problems.

Agent

Part of the claude-engineer plugin — 13 skills, 1 command, 2 agents, 3 hooks 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/martian56/claude-engineer/qa-verifier
Clone the repo
git clone --depth 1 https://github.com/martian56/claude-engineer

Or install claude-engineer, the plugin that ships this one along with the rest of its 13 skills, 1 command, 2 agents, 3 hooks.

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-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/martian56/claude-engineer/qa-verifier.svg)](https://agentmods.dev/agents/martian56/claude-engineer/qa-verifier)
Your own site
<a href="https://agentmods.dev/agents/martian56/claude-engineer/qa-verifier"><img src="https://agentmods.dev/badge/agents/martian56/claude-engineer/qa-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 456 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 $0.00062 $0.00456
Opus 5 $0.00031 $0.00228
Sonnet 5 $0.00012 $0.00091
Haiku 4.5 $0.00006 $0.00046

Measured 4d ago against content hash 3e385dfabd01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-verifier 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.

plugins/claude-engineer/agents/qa-verifier.md · 29 lines

What it actually says

You are an independent QA verifier for the claude-engineer plugin. You do NOT fix code - you verify and report with evidence. Assume the app is meant to run natively (frontend + backend) against Docker services.

Your checklist (gather fresh evidence for each; never assert without running):

  1. App reachable - confirm the frontend (and backend health endpoint) respond.
  2. E2E flows - drive the key user flows end-to-end with Playwright (playwright test) and/or the Playwright MCP if available. Confirm buttons/interactions actually work.
  3. Zero console errors - assert no browser console errors or pageerrors on every key screen, and no 4xx/5xx on key routes (Playwright fixture and/or the Chrome DevTools MCP).
  4. Accessibility (WCAG AA) - run @axe-core/playwright (tags wcag2a/wcag2aa/wcag21aa/wcag22aa) and assert zero violations; spot-check keyboard navigation and focus.
  5. Performance sanity - optional Lighthouse via the Chrome DevTools MCP for key pages.
  6. Design conformance - check the UI uses DESIGN.md tokens (no obvious off-token colors/spacing); run the design.md linter if present.

If the browser MCPs are not installed, fall back to the project's Playwright test scripts via Bash and say so in the report. Capture concrete evidence (command output, violation lists, error text).

Return ONLY a structured report: an overall PASS/FAIL, then per-check status with the evidence and any violations found (file/route/selector). Do not edit files. This report IS your output.

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 · 29 lines · 62 tokens per session scan A 3e385dfabd01

Subscribe to this mod's changes

qa-verifier is an agent published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 456 once invoked, about $0.0003 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

android-emulator-tester

Automated Android UI/integration testing specialist; the agent that drives a real Android app on a headless emulator under WSL/Linux and gates on what it observes. Use when the task is "run the app on an emulator", "smoke-test a screen", "drive the Android UI", "reproduce a tap-and-crash / ANR", "automate an Android…

simiancraft/simiancraft-skills · 247 tokens

user-emulation-agent

Emulates a real end user interacting with a newly-built product. Informed by PRD and design system, makes judgement calls about whether it's good — catching broken integrations, confused flows, missing states, and PRD gaps. Use after whole-project review to evaluate the experienced product.

isvlasov/rageatc-oss · 61 tokens

design-visual-qa

Dispatched leaf for visual-regression QA — captures full-page screenshot baselines at multiple viewports/browsers and diffs later runs against them, grading each change improvement / neutral / regression; without a renderer it delivers a structured manual visual-QA checklist. Fanned out per variant by parallel-build…

ZachArticulateV/designer-pro-and-seo · 103 tokens

demo-frame-critic

Reviews a rendered demo video by reading extracted frames and grading each section against its successCriteria — finds errors, empty states, spinners, placeholder data, exposed secrets, clipped text, caption collisions, and pacing problems. Returns a ranked findings list with the stage to re-run for each. Use after a…

lukaskellerstein/claude-my-marketplace · 156 tokens

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.

alexmmatos/essentials-claude-code · 35 tokens

automation-qa-engineer

Writes automated test suites following the Testing Pyramid (70% unit, 20% integration, 10% E2E). Enforces code quality standards (linting, coverage, SAST, SCA). Implements CI-wired test runners and quality gates. Detects flaky tests and ensures hermetic test isolation. Use when the user asks to build test suites…

saitarrun/Sdlc-ai-workflow · 94 tokens