design-visual-qa

design-visual-qa is an agent for Claude Code from ZachArticulateV/designer-pro-and-seo. It costs 103 tokens per session (1,402 once invoked), scanned A, original, MIT.

A visual-regression checker that captures full-page screenshots at selected browser and screen sizes, then compares later captures with saved baselines. A baseline is the earlier image used as the visual reference.

In plain words
What is it for?
Use it to check responsive pages across viewports and browsers, review changed regions, and classify each visual change as an improvement, neutral change, or regression.
Why use it?
It helps reveal unintended layout or styling changes after a website update. If no browser renderer is available, it provides a manual checklist instead of pixel comparisons.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the designer-pro-and-seo plugin — 41 skills, 14 agents, 1 MCP server shipped together

Good fit Use it to check responsive pages across viewports and browsers, review changed regions, and classify each visual change as an improvement, neutral change, or regression.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ZachArticulateV/designer-pro-and-seo
Claude Code
/plugin install designer-pro-and-seo

Made for: Claude Code.

Or install designer-pro-and-seo, the plugin that ships this one along with the rest of its 41 skills, 14 agents, 1 MCP server.

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 design-visual-qa

README.md
[![agentmods](https://agentmods.dev/badge/agents/zacharticulatev/designer-pro-and-seo/design-visual-qa/github.svg)](https://agentmods.dev/agents/zacharticulatev/designer-pro-and-seo/design-visual-qa)
Your own site
<a href="https://agentmods.dev/agents/zacharticulatev/designer-pro-and-seo/design-visual-qa"><img src="https://agentmods.dev/badge/agents/zacharticulatev/designer-pro-and-seo/design-visual-qa/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-visual-qa

Your own site · 80×15
<a href="https://agentmods.dev/agents/zacharticulatev/designer-pro-and-seo/design-visual-qa"><img src="https://agentmods.dev/badge/agents/zacharticulatev/designer-pro-and-seo/design-visual-qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,402 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 $0.00103 $0.01402
Opus 5 $0.00051 $0.00701
Sonnet 5 $0.00021 $0.00280
Haiku 4.5 $0.00010 $0.00140

Measured 11d ago against content hash 3ea569b378f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-visual-qa 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 11d 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/design-visual-qa.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

design-visual-qa (dispatched-leaf agent)

Wraps: skills/design-visual-qa/SKILL.md — same method, no forked logic.

Method

Visual regression for the rendered surface — the visual analog of seo-drift. Probe for the renderer, capture full-page screenshots after the page settles (network idle + fonts + animations), then compare each shot to its stored baseline and grade the delta. When no browser is available it can't capture pixels, so it hands back a structured manual visual-QA checklist plus the one step to enable the free renderer — it never just fails.

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/workflow/capability_probe.py" --human   # detect Playwright + odiff/pixelmatch; use `py` on Windows

With the bundled Playwright extension connected, capture each (URL, viewport, browser) and save baselines to visual-qa/baselines/ in the user's workspace; on a diff run, compare against the baseline — an exact differ (odiff/pixelmatch) reports a pixel-delta % and a highlighted diff image, otherwise Claude-vision names the changed regions and whether each looks intentional. Grade every change against the four axes (hierarchy, rhythm, contrast, restraint) and the severity ladder in references/design-visual-qa/visual-qa-rubric.md: a large delta can be a deliberate improvement, while a tiny delta that drops text below AA or hides a focus ring is a critical regression. When only vision ran, never emit a fabricated pixel number.

Read the full file on GitHub · 102 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. 11d ago First seen · 102 lines · 103 tokens per session scan A 3ea569b378f1

Subscribe to this mod's changes

design-visual-qa is an agent published in the GitHub repository ZachArticulateV/designer-pro-and-seo (8 stars, last pushed 2mo ago), licensed MIT. It adds 103 tokens to every session and 1,402 once invoked, about $0.0005 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.