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 majiayu000/spellbook --skill illustrated-gallerygit clone --depth 1 https://github.com/majiayu000/spellbookWrote 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/majiayu000/spellbook/illustrated-gallery)<a href="https://agentmods.dev/skills/majiayu000/spellbook/illustrated-gallery"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/illustrated-gallery/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/majiayu000/spellbook/illustrated-gallery"><img src="https://agentmods.dev/badge/skills/majiayu000/spellbook/illustrated-gallery.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 | $0.00065 | $0.01334 |
| Opus 5 | $0.00032 | $0.00667 |
| Sonnet 5 | $0.00013 | $0.00267 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
illustrated-gallery 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 today.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Illustrated Gallery
Create a website from the retained source template. Use artifact-template.json for reference paths. Preserve its visual system and accepted interactions while adapting content to the brief.
Workflow
- Inspect the target project and its instructions. For a new site, copy
assets/sourceinto a new working directory; leave the skill's source intact. For an existing site, adapt only the requested surface instead of replacing the entire project. - Identify the audience, brand, text, and illustration subjects from the request. The five blue botanical artworks are examples, not mandatory subjects or a fixed image count.
- Retain the large artwork stage, fixed text layer, restrained floating card, serif headline hierarchy, and compact navigation unless the user requests changes. Keep images still between transitions.
- Replace or generate a coherent image set, then adjust each mobile crop and keep text and cards clear of faces, bird heads, and flower centers.
- Validate the complete interaction and responsive layout. Prepare static output only when needed for hosting; use the user's authorized hosting workflow.
Accepted interaction contract
- Keep the full-frame ASCII dissolve, approximately 1.5 seconds long. Reuse the implementation in app.js; do not substitute an edge wipe or ordinary crossfade as an unsolicited optimization.
- Keep artwork static. Do not add warping, ripples, floating particles, pointer parallax, or zoom unless explicitly requested. Improve image composition or crop instead when the image feels flat.
- Treat subject motion, slide transitions, and scroll animation independently. A request to stop image motion must not remove the transition animation.
- Preserve autoplay, pause, previous/next, direct slide selection, touch swipes, and reduced-motion support. Pause stops autoplay; manual navigation still works.
- Reuse existing sections without adding dashboards, forms, configuration panels, or theme systems. The sample brief-download form saves a local file; do not describe it as sending a message or collecting a lead.
What ships with it
18 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.
- agents/openai.yaml 314 B
- artifact-template.json 110 B
- assets/preview.png 7.9 KB
- assets/source/.gitignore 11 B
- assets/source/.openai/hosting.json 45 B
- assets/source/app.js 6.7 KB runs code
- assets/source/assets/bloom-small.webp 59 KB
- assets/source/assets/bloom.webp 293 KB
- assets/source/assets/heron-small.webp 43 KB
- assets/source/assets/heron.webp 233 KB
- assets/source/assets/moon-small.webp 47 KB
- assets/source/assets/moon.webp 273 KB
- assets/source/assets/muse-small.webp 42 KB
- assets/source/assets/muse.webp 220 KB
- assets/source/assets/tide-small.webp 37 KB
- assets/source/assets/tide.webp 194 KB
- assets/source/index.html 6.9 KB
- assets/source/style.css 11 KB
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.
- today First seen · 117 lines · 65 tokens per session scan A 36b20c9be56f
illustrated-gallery is a skill published in the GitHub repository majiayu000/spellbook (278 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,334 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 2026-09-12.
Other skills, from other repositories
pneuma-preferences
Persistent user preference memory across sessions. Consult this skill BEFORE making any design, style, or aesthetic decisions — choosing colors, themes, layouts, fonts, tone of voice, content density, or visual direction. Also consult when starting a new creative task in any mode, when the user corrects your style…
Cursor rules for avoiding placeholder or broken image URLs, using stable visual
Cursor rules for avoiding placeholder or broken image URLs, using stable visual assets, and checking alt text, dimensions, licensing, and responsive behavior.
Tailwind CSS Patterns
Use this skill when styling UI with Tailwind and you want consistent design tokens, maintainable class composition, and good accessibility defaults.
Cursor rules for embedding Beefree SDK's no-code content editors (for emails, pa
Cursor rules for embedding Beefree SDK's no-code content editors (for emails, pages, and popups) into a web application.
Guidelines and best practices for building applications with [Beefree SDK](https
Guidelines and best practices for building applications with Beefree SDK, including installation, authentication, configuration, customization, and template management.
Create Design System
You are an expert design systems architect. You create comprehensive, production-ready CSS design systems from requirements or existing designs. Your output is immediately usable in any modern web project.