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 rfdiosuao/AgentSkill --skill heang-designgit clone --depth 1 https://github.com/rfdiosuao/AgentSkillWrote 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/rfdiosuao/agentskill/heang-design)<a href="https://agentmods.dev/skills/rfdiosuao/agentskill/heang-design"><img src="https://agentmods.dev/badge/skills/rfdiosuao/agentskill/heang-design/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/rfdiosuao/agentskill/heang-design"><img src="https://agentmods.dev/badge/skills/rfdiosuao/agentskill/heang-design.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 | $0.00142 | $0.02369 |
| Opus 5.5 | $0.00057 | $0.00948 |
| Sonnet 5.5 | $0.00028 | $0.00474 |
| Haiku 4.5 | $0.00014 | $0.00237 |
Grade A, and why
heang-design 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
宇航.design
Every project built "in 宇航's style" gets the same base: the 太空少年 (cadet) look, a logo loading splash when the page is heavy, and passive pointer interactions everywhere. World switching is an extra.
Project root: the heang-design/ folder that contains this .claude/. Source of truth for tokens and components
lives there; this skill tells you which pieces are required and how to wire them.
What every project gets
| Module | Status | Where |
|---|---|---|
| 太空少年 cadet style (tokens, type, sticker cards, dot grid) | required, default | src/tokens/tokens.css, src/index.css, spec in references/cadet.md |
| Water field: gravity + ripples in the dot grid | required, always on | src/motion/field.ts (GravityField wraps it) |
| Logo loading splash → flies to the header logo | required when the page has heavy resources | src/motion/splash.html + src/motion/splash.ts |
| 3D components (头像星系 OrbitScene, artifacts, gravity field) | use where it serves the page | src/components/lab/, assets/orbit-scene/ (portable), see references/3d.md |
| World switching (click-anywhere random UI worlds) | optional, off by default | the heang-world skill |
Don't ask whether to include the two required modules; include them. Ask only about optional ones.
1. Default style: 太空少年 (cadet)
Read references/cadet.md before designing. The short version:
- Sky ground
#CFE3FFwith a 22px navy dot grid; deep-space dark mode#0A1233. - Navy ink and edges
#0F2044; sun-yellow accent#FFD23F(highlights, primary actions); candy pink#FF93B4for the hero CTA; fog blue#9AB8E7. - Sticker objects: 2px navy border, 18px radius, hard offset shadow
4px 4px 0navy (.stk). Pill buttons. - Type: Unbounded (display, Latin), Noto Sans SC 900 (headings), Noto Sans SC (body), JetBrains Mono (labels, data).
- IP devices: the −18° orbit ellipse,
HA-xxcodes,T−daysto 2040, a sun-yellow<mark>on one word of the headline, the astronaut avatar, small planet dots. - In a project inside
heang-design/, importsrc/index.cssand use the components insrc/components/base/. Outside it, copysrc/tokens/tokens.cssand follow the spec; never invent a parallel palette.
What ships with it
9 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.
- assets/orbit-scene/avatar.jpg 36 KB
- assets/orbit-scene/bodies.ts 3.9 KB runs code
- assets/orbit-scene/heang-3d.ts 1.5 KB runs code
- assets/orbit-scene/orbit-scene.css 312 B
- assets/orbit-scene/OrbitLoader.tsx 1.0 KB
- assets/orbit-scene/OrbitScene.tsx 16 KB
- assets/orbit-scene/README.md 3.0 KB
- references/3d.md 3.1 KB
- references/cadet.md 4.3 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.
- 2d ago First seen · 128 lines · 142 tokens per session scan A 59c8310f00df
heang-design is a skill published in the GitHub repository rfdiosuao/AgentSkill (16 stars, last pushed 2d ago), licensed MIT. It adds 142 tokens to every session and 2,369 once invoked, about $0.0006 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 2026-10-26.
Other skills, from other repositories
superloopy-clone
Use when the user asks for Superloopy clone or asks to clone, rebuild, reverse-engineer, replicate, or copy a website or page into a Superloopy-governed implementation. Triggers on "loopy clone", target URLs plus requests such as "clone this site", "rebuild this page", "make a copy of this website", "pixel-perfect…
frontend-design
Design implementation-ready frontend solutions with UX intent, component structure, responsive behavior, accessibility, and handoff criteria.
core-components
Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.
build-webgl-liquid-glass
Build production-ready GPU liquid-glass surfaces with liquid-gl for React or DOM UIs. Default for refractive cards, notifications, panels, GPU bevels, and WebGL glass.
build-sdf-liquid-glass
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…