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 HYEXE/codex-plugins --skill build-design-systemgit clone --depth 1 https://github.com/HYEXE/codex-pluginsWrote 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/hyexe/codex-plugins/build-design-system)<a href="https://agentmods.dev/skills/hyexe/codex-plugins/build-design-system"><img src="https://agentmods.dev/badge/skills/hyexe/codex-plugins/build-design-system/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/hyexe/codex-plugins/build-design-system"><img src="https://agentmods.dev/badge/skills/hyexe/codex-plugins/build-design-system.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 | $0.00178 | $0.01067 |
| Opus 5.5 | $0.00071 | $0.00427 |
| Sonnet 5.5 | $0.00036 | $0.00213 |
| Haiku 4.5 | $0.00018 | $0.00107 |
Grade A, and why
build-design-system 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design System Builder
기존 제품의 언어와 API를 보존하면서 토큰, 컴포넌트, 문서와 검증이 같은 진실 원본을 공유하게 만든다. 새 라이브러리 도입보다 현재 시스템의 중복과 계약 공백을 먼저 해결한다.
시작 절차
-
저장소 지침, 현재 diff, package와 lockfile, 스타일 도구, framework, build·test 명령을 확인한다.
-
기존 CSS 변수, theme, token, primitive, component, Storybook·문서와 소비 경로를 검색해 실제 사용량을 기록한다.
-
구현 전에 다음 시스템 계약을 작성한다.
소비자와 지원 platform: 진실 원본과 생성 산출물: primitive·semantic·component token 계층: component API와 state 계약: theme·brand·dark mode 전략: 호환성·버전·마이그레이션: 문서·테스트·완료 기준: -
도구 후보가 필요하면 이 스킬 디렉터리를 기준으로
../uiux-advisor/scripts/search_toolkits.py에서 role과 ecosystem을 검색하고, 실제 도입 전 공식 문서를 다시 확인한다. -
시스템 경계와 점진적 이행은
references/design-system-workflow.md를 읽는다. -
token·component API 설계는
references/token-and-component-contracts.md를 읽는다. -
React·Vue·Svelte·vanilla 적용 차이는
references/framework-adapters.md를 읽는다.
구현 원칙
- primitive token을 제품 의미에 직접 노출하지 말고 semantic token을 안정적인 소비 계약으로 둔다.
- component token은 실제 반복과 독립적 변화 요구가 있을 때만 추가한다.
- color, spacing, typography만이 아니라 focus, motion, elevation, radius와 상태 표현도 계약에 포함한다.
- component API는 appearance와 behavior, content와 layout, controlled와 uncontrolled state를 구분한다.
- hover·focus·active·disabled·loading·error·empty·selected와 reduced-motion 상태를 문서와 테스트에 포함한다.
- 기존 공개 API와 token 이름을 한 번에 교체하지 않는다. alias, deprecation, codemod 또는 단계별 소비자 이전을 설계한다.
- 생성 산출물을 직접 편집하지 않는다. source token과 build pipeline의 소유권을 분명히 한다.
- Storybook, Style Dictionary나 새 package는 현재 프로젝트의 필요와 기존 도구로 해결할 수 없는 경우에만 추가한다.
- 웹 전용 시스템에서 불필요한 multi-platform pipeline을 만들지 않는다.
검증
- token schema, alias cycle, 누락 reference, 생성물 재현성과 source/build drift를 검사한다.
- component별 정상·경계·오류 상태와 keyboard, focus, screen reader, touch, zoom을 검증한다.
- light·dark·고대비·브랜드 theme와 긴 콘텐츠, RTL, 작은 화면을 확인한다.
- 관련 unit·interaction·visual regression, 타입 검사, 린트와 build를 실행한다.
- 변경된 token과 component의 소비자를 찾아 호환성 영향과 migration 상태를 확인한다.
- 추가 의존성, 번들·CSS 변화, 라이선스와 현재 지원 framework를 보고한다.
경계
- 디자인 시스템 원칙이나 token 계층을 설명만 하면
uiux-advisor를 사용한다. - 기존 시스템의 문제를 식별하고 우선순위만 정하면
uiux-auditor를 사용한다. - 한 화면의 hero, 배경, 카드와 텍스트 효과를 조합하면
compose-creative-ui를 사용한다. - 단일 component의 시각 전환이 핵심이면
implement-ui-motion을 사용한다. - 단일 widget의 keyboard, focus, touch, gesture와 비동기 상태 동작이 핵심이면
implement-ui-interaction을 사용한다. - chart component의 데이터 의미와 시각 인코딩이 핵심이면
build-data-visualization을 사용한다.
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.
- 1mo ago First seen · 60 lines · 178 tokens per session scan A 44df8d347585
build-design-system is a skill published in the GitHub repository HYEXE/codex-plugins (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 178 tokens to every session and 1,067 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
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…
use-design-md
Apply a Korean brand's published DESIGN.md from the ko-design-md catalog (getdesign.kr) — colors, typography, spacing, radius, components, do's & don'ts — to the UI you are building in the CURRENT project. Use this skill whenever the user wants UI built or restyled in the style of a catalogued Korean service — "토스…
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.
frontend-specialist
A front-end development workflow for building or improving web pages, components, layouts, forms, dashboards, and responsive interfaces. It covers common tools and frameworks such as React, Vue, Next.js, Tailwind, and CSS.