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.
git clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-SkillWrote 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.
[](https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/audit-visual)<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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01178 |
| Opus 5.5 | $0.00011 | $0.00471 |
| Sonnet 5.5 | $0.00006 | $0.00236 |
| Haiku 4.5 | $0.00003 | $0.00118 |
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 1mo 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.
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;--viewporttakes a named device, not WxH;--allcaptures 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
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.
- 1mo ago First seen · 127 lines · 28 tokens per session scan A f35ae3f56067
audit-visual is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (49 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 1,178 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
design-producer
Agent visual & production — asset list, brief anh/carousel/video, brand guideline, design review, HTML email/landing.
visual-judge
THE single visual acceptance pass for a rendered deliverable of these types only — pptx, docx, xlsx, pdf, poster, chart; for anything else, do not use it. Use it instead of looking at the page images yourself, never in addition: pick one gate — spawn visual-judge, or (only if visual-judge is unavailable) inspect the…
mkt-strategist
Agent chien luoc marketing — lap ke hoach, nghien cuu thi truong, phan tich doi thu, xay dung chien luoc thuong hieu.
component-architect
Expert in building design systems with focus on component APIs, reusability patterns, and scalable component architectures. Creates flexible, composable, accessible-by-default components.
design-adapter
Use this agent for EVERY eliviz design decision. Two jobs: (1) PICK — given a profile of the data and the user's request, choose the best-fitting design pack from the bank; spawn it in this mode for every page build where the user didn't explicitly name a design. (2) CRAFT — when the request needs a design the bank…
pencil-navigator
Read-only localizer for Pencil (.pen) files. Given a feature name, token, viewport descriptor, or structural query, returns compact match records (ID + breadcrumb + minimal metadata) instead of raw node payloads. Invoke from the main agent whenever you need to find frames, components, repeated structures, empty canvas…