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 hatch-that-worldgit 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/hatch-that-world)<a href="https://agentmods.dev/skills/wan-huiyan/cutify-this/hatch-that-world"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/hatch-that-world/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/hatch-that-world"><img src="https://agentmods.dev/badge/skills/wan-huiyan/cutify-this/hatch-that-world.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 | $0.00215 | $0.02877 |
| Opus 5.5 | $0.00086 | $0.01151 |
| Sonnet 5.5 | $0.00043 | $0.00575 |
| Haiku 4.5 | $0.00021 | $0.00288 |
Grade A, and why
hatch-that-world 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hatch that world 🐛→🦋
How the morning brief in morning-fairy
(builder: plugins/morning-fairy/skills/morning-fairy/digest/build_digest.py) was built, written down so the next cute app starts from the method and not from scratch. Sister skills:
cutify-that-tab, sparkle-that-page, pop-that-readme.
The idea in one line: the content stays plain data; one builder turns it into a drawn little world, and every look is a swappable world. The reader decides from the picture; the details sit one click away.
The shape of the app
Read references/world-anatomy.md before writing code. The short version:
- One builder, one self-contained HTML file. A Python (or Node) builder reads a content JSON and writes a single page with all CSS, JS and SVG inline. The content never sets colours, layout or motion; all design lives in the builder. That is what lets a new world change nothing about the content or the copy.
- A world = colour tokens + one scene function + one sound voice. Tokens on
:root[data-world="x"](light and dark), aSCENE.x()that draws the ground, sky, sun/moon, signposts and mascot spot as SVG, and an oscillator voice in the sound table. Adding a world touches only those three places plus the world picker and the whitelist that reads the saved choice. If you find yourself editing content or copy to add a world, stop. - The scene is the data. Meetings lift the ground into hills by weight; the sun rides the clock and can be dragged; "now" is where the mascot stands. Make the drawing carry a real quantity, never decoration only.
- A mascot with moods derived from the data (sweat when something is overdue, starry when nothing waits, sleepy after 6 PM). Moods come from rules in the builder, not from the content.
- The drawing is clickable, but the drawing stays
aria-hidden. Put an invisible layer of real<a href="#row">links over it, placed from the drawing's geometry on every redraw. Each link opens the section holding its row, unfolds any<details>, scrolls and flashes the row. Keyboard order = time order, visible focus ring. - Calm when asked. Every animation has a reduced-motion guard; with reduced motion nothing flies, bobs, wiggles or sparkles, and a finale becomes a still picture.
What ships with it
5 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.
- today First seen · 146 lines · 0 tokens per session scan A 9bc9526a52c9
hatch-that-world is a skill published in the GitHub repository wan-huiyan/cutify-this (1 stars, last pushed yesterday), licensed MIT. It adds 215 tokens to every session and 2,877 once invoked, about $0.0009 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 2026-11-07.
hatch-that-world compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hatch-that-worldwan-huiyan/cutify-this | Skill | 1 | yesterday | MIT | A | 215 | Claude Code |
| aceternity-uisecondsky/claude-skills | Skill | 247 | 7d ago | MIT | A | 48 | Claude Code |
| design-tokensTimboGP/timbogp-marketplace | Skill | 3 | 24d ago | MIT | A | 98 | Claude Code |
| window-alert-confirmncaq/konoka | Skill | 3 | 2d ago | Apache-2.0 | A | 29 | Claude Code |
| interaction-feedbackTimboGP/timbogp-marketplace | Skill | 3 | 24d ago | MIT | A | 103 | Claude Code |
| tools-unity-uguiIdoCohen560/claude-unity-game-studio | Skill | 27 | 4mo ago | MIT | A | 22 | Claude Code |
| motionTaewoooPark/UIForge | Skill | 10 | 3mo ago | MIT | A | 164 | Claude Code |