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 widnyana/eyay-toolkits --skill cover-imagegit clone --depth 1 https://github.com/widnyana/eyay-toolkitsWrote 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/widnyana/eyay-toolkits/cover-image)<a href="https://agentmods.dev/skills/widnyana/eyay-toolkits/cover-image"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/cover-image/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/widnyana/eyay-toolkits/cover-image"><img src="https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/cover-image.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 | $0.00107 | $0.03902 |
| Opus 5 | $0.00053 | $0.01951 |
| Sonnet 5 | $0.00021 | $0.00780 |
| Haiku 4.5 | $0.00011 | $0.00390 |
Grade B, and why
cover-image scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**Fix:** Install Chrome or Chromium. The script searches for `google-chrome-stable`, `google-chrome`, `chromium-browser`, or `chromium` in that order. On Fedora: `sudo dnf install chromium`. On Ubuntu: `sudo apt install How it starts
The opening of the file, as written. The whole thing — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cover Image Generator
Generate blog cover images and Open Graph/social preview images as PNG files. Each cover is a self-contained HTML document with inline CSS, captured as a screenshot via Chrome headless at exactly 1200x630 pixels.
The output is a static PNG suitable for Hugo front matter (image:), HTML <meta property="og:image">, and Twitter card metadata. No external images, no JavaScript, no server-side rendering required at capture time.
Overview
Cover images serve as the primary visual identity for a blog post across social platforms, search results, and link previews. Each image is designed from scratch per post, reflecting the topic, tone, and key concepts of the content.
What this skill produces:
- A 1200x630px PNG file rendered from HTML+CSS
- Self-contained HTML with no external image dependencies
- Typography-driven design with CSS decorative elements
- Consistent branding placement
When to use this skill:
- Blog posts need an OG/social preview image
- Hugo front matter needs an
image:field - A series of posts need visually cohesive covers
- Existing covers need updating or redesigning
Detailed Workflow
Step 1: Read the source content
Read the blog post or article to extract the title, key concepts, and overall tone. The cover image must accurately represent the content. Identify:
- The exact title (or a shortened version if it exceeds 40 characters)
- The primary topic category (technical, tutorial, explanatory, announcement)
- Key visual metaphors or concepts from the content
- Whether the post is part of a series (affects series label placement)
- The desired output file path
If the user provides only a title without a file path, ask for the target output location before proceeding.
Step 2: Determine the visual direction
Select a design approach based on the post topic and tone:
- Technical posts (programming, infrastructure, security, blockchain): dark background with bold typography and accent gradients. Conveys depth and technical rigor.
- Tutorial/guide posts (how-to, step-by-step, beginner): light background with clean layout and structured visual hints. Conveys clarity and approachability.
- Conceptual/explanatory posts (architecture, design patterns, theory): gradient background with centered typography. Conveys breadth and sophistication.
- Announcement posts (new feature, series launch, milestone): bold accent colors with prominent typography. Conveys energy and importance.
What ships with it
2 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.
- 10d ago First seen · 430 lines · 107 tokens per session scan B 0b132167e1ca
cover-image is a skill published in the GitHub repository widnyana/eyay-toolkits (7 stars, last pushed 7d ago), licensed MIT. It adds 107 tokens to every session and 3,902 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
google-ads-assets
Plan, validate, and safely publish Google Ads assets, including sitelinks, callouts, structured snippets, image assets, and Performance Max asset briefs. Use when asked for Google Ads assets, ad extensions, sitelinks, callouts, snippets, image assets, Performance Max assets, PMax creative, or an asset audit.
meta-ads-creative
Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.
paid-ads-creative
Create grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs across advertising platforms. Use for ad copy, creative briefs, UGC concepts, headlines, creative fatigue, asset ideas, or a creative refresh.
paid-ads-tiktok
Plan and review TikTok Ads creative experiments with measurement, rights, and conversion guardrails. Use for TikTok advertising, Spark Ads, short-form video ads, creator briefs, TikTok campaign setup, or TikTok performance exports.
meta-ads-creative
Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC concepts, creative briefs, new ad concepts, or creative refreshes.
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…