Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Mineru98/imaginenpx agentmods add skills/mineru98/imagine/imagine-uiWrote 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/mineru98/imagine/imagine-ui)<a href="https://agentmods.dev/skills/mineru98/imagine/imagine-ui"><img src="https://agentmods.dev/badge/skills/mineru98/imagine/imagine-ui/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/mineru98/imagine/imagine-ui"><img src="https://agentmods.dev/badge/skills/mineru98/imagine/imagine-ui.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 | $0.00173 | $0.02518 |
| Opus 5 | $0.00086 | $0.01259 |
| Sonnet 5 | $0.00035 | $0.00504 |
| Haiku 4.5 | $0.00017 | $0.00252 |
Grade A, and why
imagine-ui 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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imagine-ui
중요: 이 출력은 설계 자료가 아닙니다. 구현할 수 있는 UI 스펙이 아니라 스타일 보드입니다. 실제 픽셀 퍼펙트 화면은 Figma/Sketch에서 만드세요.
트리거
imagine-ui <screen>/imagine-ui --screen login --system kr-minimal- "UI 목업 만들어줘"
- "앱 화면 레퍼런스"
- "스크린 레퍼런스"
- "모바일 UI 스타일 보드"
- "imagine-ui"
이 스킬이 하지 않는 것 — "이 UI 그대로 개발해주세요" 요청 처리
이 스킬의 출력은 스타일 레퍼런스입니다. 실제 UI 스펙·와이어프레임·구현 가능한 레이아웃이 아닙니다.
- 글자는 디코레이티브 글리프 placeholder이며 실제 카피가 아닙니다.
- 탭 타겟 크기·여백·접근성·컴포넌트 계층은 보증되지 않습니다.
- 브랜드 로고/문구처럼 보이는 것은 우연한 형태일 뿐입니다.
"이 UI 그대로 개발해주세요" 류 요청은 거절합니다. 진짜 디자인은 Figma에서 프레임·컴포넌트·토큰으로 만들어야 구현 가능합니다. 이 이미지는 Figma 시작 단계의 인상 수집용으로만 사용하세요.
스킬 entrypoint는 실제 호출 결과 출력에 위 경고 블록을 항상 포함해야 한다.
파이프라인
- 프리셋 매핑:
--system/--screen/--mood/--density를config.json의 매핑 테이블로 영문 비주얼 구문 변환. - Style Guardian 조회:
--keep플래그 또는 "같은 스타일로"·"이어서" 트리거 시scripts/lib/style-guardian.js로 이전 manifest에서system/palette_hex/corner_radius_estimate/mood/density를 불러와 prefix 주입. 트리거 없으면 패스스루. - 프롬프트 구성: 시스템 + 스크린 + mood + density 구문을 영문으로 조립. 사용자가 "login 화면에 실제 한국어 텍스트 넣어줘"라고 해도 넣지 않는다 — 글자 렌더링 기대를 버리는 것이 이 스킬의 원칙.
- Negative 강제:
real readable text, photo of phone, hand holding phone, device frame, bezel, notch, cluttered elements, real brand logo, korean letters, chinese letters, japanese letters. 디바이스 프레임 금지 — 프레임 합성은imagine-product(12-product-mockup) 담당. - 이미지 생성:
size: 1024x1536(9:19.5 근사, 2:3) PNG로 Codex 이미지 모델 호출. 기본n: 1, 최대 4 (Style Guardian 이어쓰기가 아닌 첫 탐색일 때만 n을 2~4로). - Style Guardian 저장: 결과에서 추정되는
palette_hex(dominant 3~5색, 후속 PR에서sharp+colorthief 결정적 추출) /corner_radius_estimate/system/mood/density를 manifest에 저장해 다음 호출에서--keep으로 재사용.
시스템 프리셋
| key | 설명 |
|---|---|
ios |
iOS 19 스타일, 12px 라운드, SF Pro-like sans, 하어라인 디바이더. |
android |
Material 3, 16dp 라운드, Roboto-like, accent surface. |
web-mobile |
모바일 뷰포트용 반응형 웹 UI, 8px 라운드, 뉴트럴 sans. |
kr-minimal |
한국 fintech 감성, Pretendard-like sans, 베이지/뉴트럴 배경, 부드러운 카드 + 서브틀 섀도. |
What ships with it
1 file 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.
- 9d ago First seen · 112 lines · 173 tokens per session scan A 319f07971704
imagine-ui is a skill published in the GitHub repository Mineru98/imagine (5 stars, last pushed 11d ago), licensed MIT. It adds 173 tokens to every session and 2,518 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. This skill covers foundational Glimmer design principles, workflows for implementing Jetpack Compose Glimmer, and interaction models for the glasses form factor. Use this skill to build an…
expo-design-system
Framework (OSS). Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when…
flutter-build-responsive-layout
Use LayoutBuilder, MediaQuery, or Expanded/Flexible to create a layout that adapts to different screen sizes. Use when you need the UI to look good on both mobile and tablet/desktop form factors.
omh-apple-design
This is a Hermes-native apple-design workflow skill.
axiom-audit-liquid-glass
Use when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration.
axiom-audit-ux-flow
Use when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.