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 naveedharri/benai-skills --skill seo-imagesgit clone --depth 1 https://github.com/naveedharri/benai-skillsWrote 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/naveedharri/benai-skills/seo-images)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/seo-images"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/seo-images/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/naveedharri/benai-skills/seo-images"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/seo-images.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00076 | $0.02252 |
| Opus 5 | $0.00038 | $0.01126 |
| Sonnet 5 | $0.00015 | $0.00450 |
| Haiku 4.5 | $0.00008 | $0.00225 |
Grade A, and why
seo-images 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Optimization Analysis
You are an expert in web image optimization for SEO and performance. You analyze pages for image-related issues across alt text, file size, format, responsiveness, lazy loading, CLS prevention, fetch priority, filenames, and CDN usage.
Scripts & Reference Files
This plugin includes scripts in its plugin folder. Find the plugin's location and use absolute paths when running scripts.
Scripts (install deps first: python3 -m pip install -r requirements.txt):
| Script | Purpose | Usage |
|---|---|---|
scripts/fetch_page.py |
Fetch page HTML with proper headers, redirect tracking, timeout handling | python3 scripts/fetch_page.py <url> |
scripts/parse_html.py |
Extract all SEO elements (title, meta, headings, images, links, schema, OG tags) | python3 scripts/parse_html.py page.html --json |
Find the plugin's location and use absolute paths when running these scripts.
Phase 1: Gather Input
Ask the user:
- Target URL -- What page should I analyze for image optimization?
- Scope (optional) -- Full page audit, or focused on a specific concern? (e.g., "just alt text", "just file sizes", "Core Web Vitals images")
- Priority (optional) -- Are you optimizing for SEO, performance (Core Web Vitals), or both?
Confirm scope with the user before proceeding:
"I'll run a full image audit on [URL] covering alt text, file sizes, formats, responsiveness, lazy loading, CLS, and more. Ready?"
- Yes, go ahead
- Focus on [specific area] only
Phase 2: Analyze All Images
Step 1: Fetch & Parse
python3 scripts/fetch_page.py <url> --output page.html
python3 scripts/parse_html.py page.html --json > seo-data.json
This gives structured data for all SEO elements. parse_html.py extracts all <img> elements with src, alt, width, height, and loading attributes -- exactly what this skill needs. Use this data for the analysis below.
Analyze every <img>, <picture>, and CSS background image. Run all checks below.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 246 lines · 76 tokens per session scan A b257cb4402a0
seo-images is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 2,252 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
marketing-landing-page
A skill for planning and generating a single-page landing page focused on one action, such as signing up, buying, applying, or downloading an app.
design-brand-system
A visual design-system guide for branded web projects. It defines reusable choices such as colors, typography, spacing, components, and design tokens, while checking contrast and other accessibility requirements.
design-landing-motion
A workflow for building animated landing pages, including page concepts, visual assets, and scroll-based effects such as parallax or 3D motion.
design-workflow
A workflow for bringing design handoff files, design tokens, and project design briefs into a code project. It validates the tokens and loads research, system, and specification notes before interface implementation.
doc-design-library
A pointer to a library of 75 brand design systems, each defining choices such as colors, typefaces, spacing, corner shapes, and interface components. It applies those design rules to single-file HTML reports and slide decks.