cover-image

cover-image is a skill for Claude Code from widnyana/eyay-toolkits. It costs 107 tokens per session (3,902 once invoked), scanned B, original, MIT.

A workflow for creating blog cover images and Open Graph images, which are the preview pictures shown when a page is shared on social networks or messaging apps. It produces self-contained 1200-by-630 PNG files from HTML and CSS.

In plain words
What is it for?
Use it to create or redesign blog covers, featured images, thumbnails, social previews, and header images for posts.
Why use it?
It provides a consistent image for article pages, search results, and shared links without relying on external image files at capture time.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the visual-gen plugin — 3 skills shipped together

Good fit Use it to create or redesign blog covers, featured images, thumbnails, social previews, and header images for posts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/widnyana/eyay-toolkits/cover-image
Install

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.

Any agent
npx skills add widnyana/eyay-toolkits --skill cover-image
Clone the repo
git clone --depth 1 https://github.com/widnyana/eyay-toolkits

Made for: Claude Code.

Or install visual-gen, the plugin that ships this one along with the rest of its 3 skills.

Wrote 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.

agentmods badge for cover-image

README.md
[![agentmods](https://agentmods.dev/badge/skills/widnyana/eyay-toolkits/cover-image/github.svg)](https://agentmods.dev/skills/widnyana/eyay-toolkits/cover-image)
Your own site
<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.

agentmods 80×15 button for cover-image

Your own site · 80×15
<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>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,902 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 0b132167e1ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/screenshot.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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
plugins/visual-gen/skills/cover-image/SKILL.md · 430 lines

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.

Read the full file on GitHub · 430 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 430 lines · 107 tokens per session scan B 0b132167e1ca

Subscribe to this mod's changes

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.

Related

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.

nowork-studio/notfair-plugin · 72 tokens

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.

nowork-studio/notfair-plugin · 59 tokens

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.

nowork-studio/notfair-plugin · 52 tokens

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.

nowork-studio/notfair-plugin · 52 tokens

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.

nowork-studio/notfair-plugin · 59 tokens

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…

ShadowAqueduct/watermark-remover · 135 tokens