SEED is a design system that provides shared visual tokens, styling recipes, and UI components for React, iOS, Android, and Lynx, with Figma integration. It is used to build consistent products across platforms; the catalogue add-ons support agents working with its components, tools, documentation, and development workflows.
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 daangn/seed-design --skill seed-componentgit clone --depth 1 https://github.com/daangn/seed-designWrote 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/daangn/seed-design/seed-component)<a href="https://agentmods.dev/skills/daangn/seed-design/seed-component"><img src="https://agentmods.dev/badge/skills/daangn/seed-design/seed-component/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/daangn/seed-design/seed-component"><img src="https://agentmods.dev/badge/skills/daangn/seed-design/seed-component.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 | $0.00072 | $0.00721 |
| Opus 5.5 | $0.00029 | $0.00288 |
| Sonnet 5.5 | $0.00014 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
seed-component 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 24d 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.
What it actually says
SEED 컴포넌트
요청이 원하는 결과로 분기를 하나 고르고, 그 분기의 reference만 읽는다. 조회·비교·토큰 분기는 읽기 전용이다. 결과를 반환하고 끝내며, 사용자가 구현을 요청하지 않는 한 다른 분기로 넘어가지 않는다.
| 요청 결과 | 읽을 reference | 실행 |
|---|---|---|
| 한 컴포넌트의 구현·export·Registry·문서·테스트 경로만 | component-map.md | bun skills/seed-component/scripts/component-map.ts <Component> |
| React·Lynx 공개 API와 사용자 결과 차이만 | api-parity.md | bun skills/seed-component/scripts/api-parity.ts <Component> |
| 색상 토큰의 정의·alias·사용처·생성 표면 또는 대비만 (컴포넌트 없이도) | color-token-analysis.md | bun skills/seed-component/scripts/token-map.ts '<token>', token-contrast.ts |
| 새 컴포넌트 또는 한 플랫폼이 없는 포팅 | implementation-workflow.md 신규·포팅 | bun skills/seed-component/scripts/scaffold-plan.ts |
| 기존 컴포넌트의 구현·동작·구조 변경 | implementation-workflow.md 기존 구현 변경 | 경로 조회 후 필요 시 API 비교 |
| Lynx 문서·실행 예제만 (컴포넌트 동작 유지) | lynx-docs.md | 경로가 불명확할 때만 경로 조회 |
| React 문서·예제, Storybook, 생성물만 | implementation-workflow.md 짧은 경로 | 경로가 불명확할 때만 경로 조회 |
경계
- 문서·Storybook 전용 분기는 컴포넌트 구현을 요구하지 않는다. 실제 호스트 앱에서도 재현되는 API·동작 문제를 발견하면 문서용 우회 대신 기존 구현 변경으로 전환한다.
- 새 패키지, 외부 의존성, CI 설정이 필요하면 구현 전에 사용자 확인을 받는다.
- Lynx native 결과를 소스 수정 없이 독립 판정하는 일은
seed-verify-lynx-component가 맡는다. - 여러 레이어의 담당·병렬 작업·에이전트 간 협의가 요청됐거나 필요하면
seed-orchestrate-component를 함께 사용한다. - changeset·변경 계획·제출은
seed-change가 맡는다.
What ships with it
31 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.
- agents/openai.yaml 339 B
- references/AGENTS.md 1.2 KB
- references/api-design.md 16 KB
- references/api-parity.md 3.5 KB
- references/architecture-decisions.md 9.5 KB
- references/brainstorming.md 10 KB
- references/color-token-analysis.md 4.5 KB
- references/component-map.md 3.1 KB
- references/external-references.md 8.3 KB
- references/guide.md 2.2 KB
- references/implementation-steps.md 16 KB
- references/implementation-workflow.md 12 KB
- references/lynx-docs-authoring.md 9.3 KB
- references/lynx-docs.md 9.2 KB
- references/lynx-headless.md 7.6 KB
- references/lynx-patterns.md 17 KB
- references/pattern-catalog.md 6.3 KB
- references/platform-differences.md 3.9 KB
- references/platform-gate.md 4.5 KB
- references/react-patterns.md 8.1 KB
- references/recipe-patterns.md 8.4 KB
- references/review-prompts.md 10.0 KB
- references/sticking-policy.md 3.6 KB
- references/storybook.md 5.4 KB
- references/verification-checklist.md 8.5 KB
- references/visual-testing.md 2.0 KB
- scripts/api-parity.ts 36 KB runs code
- scripts/component-map.ts 27 KB runs code
- scripts/scaffold-plan.ts 11 KB runs code
- scripts/token-contrast.ts 16 KB runs code
- scripts/token-map.ts 33 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.
- 24d ago First seen · 27 lines · 72 tokens per session scan A 52e92375a364
seed-component is a skill published in the GitHub repository daangn/seed-design (1,180 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 721 once invoked, about $0.0003 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 2026-09-23.
Other skills, from other repositories
ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…
ui-components
UI component library patterns for shadcn/ui and Radix Primitives. Use when building accessible component libraries, customizing shadcn components, using Radix unstyled primitives, or creating design system foundations.
s2-docs
Look up Spectrum 2 (S2) component documentation, design guidelines, and usage patterns when building with React Spectrum or Spectrum Web Components. Use when the user mentions Spectrum, S2, React Spectrum, RSP, Spectrum Web Components, or SWC, or names a Spectrum component (Button, Picker, ComboBox, TextField…
sigil-migration
Before migrating, audit the existing project.
sigil-component
Every Sigil component lives in packages/components/src/ and follows this pattern.
instui-docs
Look up authoritative Instructure UI (InstUI, @instructure/ui-) documentation — component APIs, props, theme variables, usage examples, and guides — by querying instructure.design's plaintext docs. Use whenever the user asks how to use an InstUI component, which props/prop types exist, how to theme/style it…