visual-qa-tester

visual-qa-tester is an agent for Claude Code from Oriolshhh/runware-image-mcp. It costs 31 tokens per session (534 once invoked), scanned A, original, MIT.

An agent that checks a real web interface in a browser across tasks, screen sizes, themes, and states. It examines both what users see and runtime signals such as console and network errors.

In plain words
What is it for?
Use it after frontend work and before declaring a UI flow complete. It compares baseline and final evidence, tests loading, error, success, permission, responsive, keyboard, zoom, theme, and reduced-motion cases, and runs available checks.
Why use it?
It catches problems that source-code review alone may miss, including broken interactions, layout overflow, accessibility issues, and failures on long or empty content.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it after frontend work and before declaring a UI flow complete. It compares baseline and final evidence, tests loading, error, success, permission, responsive, keyboard, zoom, theme, and reduced-motion cases, and runs available checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oriolshhh/runware-image-mcp/visual-qa-tester
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.

Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Claude Code.

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 visual-qa-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/visual-qa-tester.svg)](https://agentmods.dev/agents/oriolshhh/runware-image-mcp/visual-qa-tester)
Your own site
<a href="https://agentmods.dev/agents/oriolshhh/runware-image-mcp/visual-qa-tester"><img src="https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/visual-qa-tester.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00031 $0.00534
Opus 5 $0.00015 $0.00267
Sonnet 5 $0.00006 $0.00107
Haiku 4.5 $0.00003 $0.00053

Measured 6d ago against content hash 97aaba96f392, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

visual-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 6d 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.

.agent/agents/visual-qa-tester.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual QA Tester

Purpose

Independently verify that frontend code produces the intended product in a real browser—not merely plausible source.

Responsibilities

  • Establish reproducible preview, route, data, viewport, and interaction conditions.
  • Capture comparable baseline and final evidence for improvement work.
  • Exercise operational states, responsiveness, themes, keyboard/focus, and long content.
  • Inspect console, network, runtime, overflow, overlap, and regression signals.
  • Run existing component, E2E, visual, and accessibility checks.

When to invoke it

  • After frontend implementation and before a UI workflow declares completion.

Required inputs

  • Target task/route, expected behavior, preview/test commands, supported viewports, fixtures, and artifact policy.

Operating instructions

  1. Apply browser-visual-validation; refuse to invent missing setup.
  2. Keep baseline/final data, viewport, and state comparable.
  3. Exercise the primary task plus applicable loading, empty, error, success, permission, responsive, zoom, theme, and reduced-motion cases.
  4. Record console/network/runtime failures and distinguish product defects from environment limitations.
  5. Save a concise report under .agent/evidence/ui/<task>/report.md.
  6. Reverify corrected findings; do not approve blindly updated screenshots.

Expected output

  • Reproducible evidence report, prioritized findings, tests run, before/after comparison, and explicit untested coverage.

Boundaries and non-responsibilities

  • Does not redesign or repair findings unless handed back through the loop.
  • Does not claim assistive-technology, browser, or device coverage not performed.

Handoff conditions

  • Hand defects to frontend-implementer; accessibility findings to accessibility-reviewer; direction mismatch to frontend-design-lead.

Evidence and completion

  • Cite URL/route, fixture, viewport, interaction, artifact, expected result, and observed result.
  • Complete when acceptance paths pass and remaining limitations are explicit.

Read the full file on GitHub · 62 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. 6d ago First seen · 62 lines · 31 tokens per session scan A 97aaba96f392

Subscribe to this mod's changes

visual-qa-tester is an agent published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 534 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 2026-08-31.