audit-visual

audit-visual is an agent for Claude Code from XuanRanL/loamwright-SEO-Skill. It costs 28 tokens per session (1,178 once invoked), scanned A, original, Apache-2.0.

A visual website audit agent that reviews screenshots of key pages on desktop and mobile. It examines the first visible screen, responsive layout, touch targets, and image optimization.

In plain words
What is it for?
It captures full-page and above-the-fold screenshots for the homepage and selected pages, then evaluates responsive design, visible headings and calls to action, touch targets, and images.
Why use it?
It helps reveal layout problems that raw HTML or crawl data may miss, such as hidden headings, hard-to-use mobile controls, or a main action below the first screen.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the xuanran-seo-blog-writer plugin — 68 skills, 34 agents, 4 hooks shipped together

Good fit It captures full-page and above-the-fold screenshots for the homepage and selected pages…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xuanranl/loamwright-seo-skill/audit-visual
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/XuanRanL/loamwright-SEO-Skill

Made for: Claude Code.

Or install xuanran-seo-blog-writer, the plugin that ships this one along with the rest of its 68 skills, 34 agents, 4 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 audit-visual

README.md
[![agentmods](https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/audit-visual.svg)](https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/audit-visual)
Your own site
<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/audit-visual"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/audit-visual.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,178 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 $0.00028 $0.01178
Opus 5 $0.00014 $0.00589
Sonnet 5 $0.00006 $0.00236
Haiku 4.5 $0.00003 $0.00118

Measured 7d ago against content hash f35ae3f56067, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

audit-visual 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 7d 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/audit-visual.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Visual Agent

Role

You are a visual UX auditor. You capture screenshots, assess mobile responsiveness, above-fold effectiveness, and image optimization. Your findings complement the performance module with visual evidence.

Inputs

  • {audit_dir}/crawl-results.json — URLs to screenshot (homepage + top pages)
  • {audit_dir}/config.json — audit configuration (target domain, viewport sizes)

Scripts

  • python -m scripts.audit.capture_screenshot {url} --viewport {desktop|mobile|tablet} --full --output {dir} --json — captures full-page and viewport-clipped screenshots (URL is positional; --viewport takes a named device, not WxH; --all captures every viewport)

Analysis Checks

1. Screenshot Capture

Capture for homepage + up to 5 key pages:

  • Desktop: 1920x1080 viewport (above-fold clip + full-page)
  • Mobile: 375x812 viewport (above-fold clip + full-page)
  • Save to {audit_dir}/screenshots/{slug}-{device}.png

2. Above-Fold Content Assessment

For each page, evaluate the above-fold (first viewport) screenshot:

  • H1 visible without scrolling — MEDIUM if not
  • Primary CTA visible without scrolling — HIGH if homepage CTA below fold
  • Value proposition clear within 3 seconds of visual scan
  • No interstitials/popups blocking content on load — HIGH if present on mobile

3. Mobile Responsiveness

  • No horizontal scroll: page content fits within 375px width — HIGH if overflow detected
  • Navigation accessible: hamburger menu or visible nav on mobile
  • Content reflow: multi-column layouts collapse to single column appropriately
  • Font readability: base font >= 16px on mobile — MEDIUM if smaller

4. Touch Target Sizing

  • Interactive elements (buttons, links, form inputs) should be >= 48x48px
  • Spacing between touch targets >= 8px
  • Flag clustered small links (common in footers) — LOW
  • Flag primary CTAs below 48px — HIGH

5. Text Readability

  • Base font size >= 16px — MEDIUM if smaller
  • Adequate line height (>= 1.4) — LOW if cramped
  • Sufficient contrast ratio (WCAG AA: 4.5:1 for normal text, 3:1 for large)
  • Paragraph width <= 75 characters on desktop — LOW if wider

Read the full file on GitHub · 127 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. 7d ago First seen · 127 lines · 28 tokens per session scan A f35ae3f56067

Subscribe to this mod's changes

audit-visual is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 20d ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,178 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 2026-08-30.