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.
npx skills add indranilbanerjee/digital-marketing-pro --skill image-seo-auditgit clone --depth 1 https://github.com/indranilbanerjee/digital-marketing-proWrote 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/skills/indranilbanerjee/digital-marketing-pro/image-seo-audit)<a href="https://agentmods.dev/skills/indranilbanerjee/digital-marketing-pro/image-seo-audit"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/image-seo-audit/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/skills/indranilbanerjee/digital-marketing-pro/image-seo-audit"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/digital-marketing-pro/image-seo-audit.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 | $0.00139 | $0.01116 |
| Opus 5 | $0.00069 | $0.00558 |
| Sonnet 5 | $0.00028 | $0.00223 |
| Haiku 4.5 | $0.00014 | $0.00112 |
Grade A, and why
image-seo-audit 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 5d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digital-marketing-pro:image-seo-audit
Purpose
Perform a dedicated image optimization audit that evaluates all images on a page or site for SEO, performance, and accessibility. Produces a prioritized optimization list sorted by file size impact.
Input Required
- URL: Page or site to audit
- Scope: Single page or site-wide crawl (default: single page)
Process
- Load brand context: Read active brand profile for industry context.
- Discover images: Find all
<img>,<picture>, CSSbackground-image, and<source>elements. - Alt text audit: Check presence, quality, keyword inclusion, length (10-125 chars). Flag: missing, filename-only ("image.jpg"), keyword-stuffed, non-descriptive ("click here").
- File size audit: Apply tiered thresholds by image category — thumbnails (<50KB target, >200KB critical), content images (<100KB target, >500KB critical), hero/banner (<200KB target, >700KB critical).
- Format audit: Check for modern formats. Recommend WebP (97%+ support) or AVIF (92%+ support) over JPEG/PNG. Check for
<picture>element with format fallbacks. Note: JPEG XL restored in Chromium (Nov 2025) but not yet in Chrome stable — monitor, don't recommend yet. - Responsive images: Check for
srcsetandsizesattributes, appropriate resolution for device pixel ratios. - Lazy loading: Verify
loading="lazy"on below-fold images. Flagloading="lazy"on above-fold/hero images (directly harms LCP). - fetchpriority: Check for
fetchpriority="high"on LCP/hero images. Check fordecoding="async"on non-LCP images. - CLS prevention: Check for
widthandheightattributes oraspect-ratioCSS on all<img>elements. Flag images without dimensions. - File naming: Check for descriptive, hyphenated, lowercase file names vs generic names (IMG_1234.jpg).
- CDN usage: Check if images are served from a CDN (different domain, CDN headers, edge caching).
- Score and prioritize: Sort by file size savings impact (largest first).
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.
- 5d ago First seen · 91 lines · 139 tokens per session scan A 663656ef2152
image-seo-audit is a skill published in the GitHub repository indranilbanerjee/digital-marketing-pro (812 stars, last pushed 5d ago), licensed MIT. It adds 139 tokens to every session and 1,116 once invoked, about $0.0007 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 2026-09-07.
Other skills, from other repositories
image-post-processor
After batch completes, runs 4-step post-processing on each image: EXIF strip → WebP convert (q85) → srcset 3 sizes → SEO filename. Generates ImageObject schema fragment. Stage 27e.
kaicalls-design
Build KaiCalls-compliant UI components and pages using the KaiCalls design system. Use when creating new dashboard pages, components, forms, tables, cards, badges, or any UI within the KaiCalls admin panel. Ensures dark-first aesthetic, proper color tokens, typography classes, motion standards, and B2B SaaS best…
vertical-site-conventions
Compose pages and sites that read as their vertical: ecommerce-catalog storefronts that look like storefronts, hospitality-food sites that look like restaurants, b2b-manufacturer sites that look industrial. Use this skill whenever the user wants to build a site that looks like the vertical it serves, fix a build that…
interface-redesign
Upgrades an existing interface to a higher standard without rebuilding it — auditing what is there, identifying what reads as generic or unfinished, and sequencing changes by impact. Use this when a product works but looks dated or default, when a redesign is being considered, when deciding whether to restyle or…
design-context-extract
Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…
component-search
Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system…