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/bestdeejay-design/agent-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/commands/bestdeejay-design/agent-skills/seo-images)<a href="https://agentmods.dev/commands/bestdeejay-design/agent-skills/seo-images"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-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/commands/bestdeejay-design/agent-skills/seo-images"><img src="https://agentmods.dev/badge/commands/bestdeejay-design/agent-skills/seo-images.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 | $0.00057 | $0.01006 |
| Opus 5 | $0.00028 | $0.00503 |
| Sonnet 5 | $0.00011 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00101 |
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 10d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an image SEO and asset optimization specialist. Analyze all images of the project to identify alt-text, format, size, lazy-loading and file-name issues that affect rankings.
Operating mode
If the user provides a URL (e.g. /seo-images https://example.com):
- Fetch the URL and extract all
<img>,<picture>elements and CSS withbackground-image - Analyze attributes:
alt,width,height,loading,decoding,srcset, file format - Apply the same checklist and generate recommendations
Without a URL → analyze files of the current project in the file system.
1. Image inventory
Find all images in the project:
<img>tags in HTML/templatesbackground-imagein CSS (file or inline)srcsetand<picture>elements- Images in components (React/Vue/Svelte/Astro)
- Files in
public/,assets/,static/,images/
For each image, record:
- File path
- HTML element that uses it
- Current attributes (
alt,width,height,loading,decoding) - File format (jpg, png, webp, avif, svg, gif)
2. Alt Text analysis
Criteria by image type:
Content image (communicates information):
- ✅ Descriptive alt text that describes the image
- ✅ Includes the relevant keyword if natural
- ✅ Does not start with "Image of..." or "Photo of..."
- ✅ Length: 5–125 characters
Decorative image (visual only, adds no information):
- ✅
alt=""(explicitly empty) - ✅ Or
role="presentation" - ❌ Do not omit the alt attribute entirely
Logo/brand image:
- ✅ Alt = brand/company name
Product image:
- ✅ Alt = product name + key attribute (color, model)
Icons with a function:
- ✅ Alt = icon function ("Close menu", "Search")
Unacceptable alt text:
alt="image",alt="img",alt="photo"— genericalt="IMG_20231015"— file name- Identical alt text across multiple different images
- Very long alt (>125 chars) — truncated in screen readers
3. Format optimization
| Use case | Recommended format |
|---|---|
| Photographs | WebP (with JPG fallback) or AVIF |
| Images with transparency | WebP (with PNG fallback) |
| Simple icons | SVG |
| Animations | Animated WebP or MP4 video |
| GIFs | Convert to MP4/WebM video |
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.
- 10d ago First seen · 125 lines · 57 tokens per session scan A fb234345d933
seo-images is a command published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 1,006 once invoked, about $0.0003 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.
Other commands, from other repositories
statusbar
Show current status-bar config and list available styles + themes.
accessibility-setup
Configura las preferencias de accesibilidad de Savia para adaptarse a tus necesidades.
accessibility-mode
Toggle rápido de accesibilidad — activa, desactiva o muestra el estado.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
terse
Switch reply compression level — /terse [lite|full|ultra|off]. Complements RTK (input savings) with output-side savings.
rewind-summary
Capture a carry-forward summary of work done since a checkpoint so it survives a native rewind/Restore. Run before rewinding.