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 wan-huiyan/cutify-this --skill sparkle-that-pagegit clone --depth 1 https://github.com/wan-huiyan/cutify-thisWrote 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/wan-huiyan/cutify-this/sparkle-that-page)<a href="https://agentmods.dev/skills/wan-huiyan/cutify-this/sparkle-that-page"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/sparkle-that-page/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/wan-huiyan/cutify-this/sparkle-that-page"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/sparkle-that-page.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 | $0.00185 | $0.04210 |
| Opus 5.5 | $0.00074 | $0.01684 |
| Sonnet 5.5 | $0.00037 | $0.00842 |
| Haiku 4.5 | $0.00018 | $0.00421 |
Grade A, and why
sparkle-that-page 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 6d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sparkle That Page ✨
Make the whole browser page delightful — not just the favicon (that's the
sibling skill cutify-that-tab). Seven self-contained, zero-dependency
effects you paste in: a fairy-wand cursor, a sparkle trail, an animated scroll
indicator, tab-title peekaboo, click confetti, ambient floaters, and
cute-chrome touches. Each is one short vanilla file — copy, drop in, tweak a
data-* attribute. No npm, no build, no framework.
Problem
A web app feels flat. The user wants personality — magic on the cursor, sparkle on a click, a little mascot that climbs as you scroll — without pulling in a particle framework, a build step, or a pile of dependencies. They want to point at an effect and have it just work, and to be able to hand-edit it afterward.
Context / Trigger conditions
Use when any of:
- User asks for a "cute cursor / fairy cursor / magic wand cursor / sparkle cursor", "sparkles when I move/click the mouse", "cursor trail".
- "scroll progress bar / scroll indicator / reading progress / a thing that fills as you scroll".
- "confetti / heart burst on click", "celebrate when they click".
- "floating petals / snow / bubbles / leaves / fairy dust in the background".
- "make the tab say something when you leave", "come back message".
- "cute selection color / bouncy buttons / kawaii spinner".
- General: "make this page cuter / more playful / more alive / add some magic."
Skip if: the user wants a serious/corporate UI, a full design system, or a
heavyweight, highly-configurable particle engine (point them at the libraries
in Prior art instead). Also skip motion-heavy effects for users who've
asked for a calm/minimal experience — though every effect here already
self-disables under prefers-reduced-motion.
Solution — pick the effect(s), copy the file, wire it in
Every effect ships as one file in examples/. Wire JS with a <script> and
CSS with a <link>, then set options via data-* attributes on <html>:
<!-- one line per effect you want -->
<script src="/static/fairy_cursor.js"></script>
<script src="/static/sparkle_trail.js"></script>
<link rel="stylesheet" href="/static/cute_chrome.css">
<!-- options live on the html tag -->
<html data-wand="sailormoon" data-trail="fairydust" data-palette="candy">
What ships with it
8 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.
- examples/ambient_floaters.js 4.0 KB runs code
- examples/click_confetti.js 4.6 KB runs code
- examples/cute_chrome.css 3.0 KB
- examples/demo.html 9.0 KB
- examples/fairy_cursor.js 2.9 KB runs code
- examples/scroll_indicator.js 3.9 KB runs code
- examples/sparkle_trail.js 4.3 KB runs code
- examples/tab_title_peekaboo.js 1.7 KB runs code
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.
- 6d ago Changed · +50 lines 2a4b17aadab1
- 2mo ago First seen · 227 lines · 185 tokens per session scan A 423c42ddbbe7
sparkle-that-page is a skill published in the GitHub repository wan-huiyan/cutify-this (1 stars, last pushed 5d ago), licensed MIT. It adds 185 tokens to every session and 4,210 once invoked, about $0.0007 per session on Opus 5.5. 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 skills, from other repositories
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
design-tokens
This skill should be used when a user wants to scaffold or refactor a design token system — e.g. "set up design tokens", "create a design system foundation", "extract these hardcoded colors into tokens", "add a type scale", "theming setup", or "dark mode tokens". It produces a single source of truth for color, type…
window-alert-confirm
Guidelines for using window.alert() and window.confirm() in web applications. Use when implementing error notifications or destructive action confirmations.
interaction-feedback
This skill should be used when the user wants clear visual feedback for async actions and state changes — triggers like "add loading and error states", "show a success message", "add a toast/notification", "inline form validation", "optimistic UI", "empty state for this list", "this button gives no feedback", or "add…
tools-unity-ugui
Unity UI patterns including Canvas optimization, list virtualization, and mobile-friendly UI.
motion
UIForge's motion layer — art-directs motion for React/Next.js + Tailwind interfaces built with Motion-Primitives (the shadcn-style copy-in registry, powered by Motion / ex Framer Motion). Use whenever you build or polish a landing page, hero, dashboard, pricing table, feature section, empty state, or any screen where…