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 kohj1018/agentic-dev-harness --skill bootstrap-designgit clone --depth 1 https://github.com/kohj1018/agentic-dev-harnessWrote 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/kohj1018/agentic-dev-harness/bootstrap-design)<a href="https://agentmods.dev/skills/kohj1018/agentic-dev-harness/bootstrap-design"><img src="https://agentmods.dev/badge/skills/kohj1018/agentic-dev-harness/bootstrap-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/kohj1018/agentic-dev-harness/bootstrap-design"><img src="https://agentmods.dev/badge/skills/kohj1018/agentic-dev-harness/bootstrap-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 | $0.00050 | $0.12298 |
| Opus 5.5 | $0.00020 | $0.04919 |
| Sonnet 5.5 | $0.00010 | $0.02460 |
| Haiku 4.5 | $0.00005 | $0.01230 |
Grade A, and why
bootstrap-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 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/bootstrap-design
모드: How-to (UI 시각 결정 라운드) 패턴:
discover-product차용 —context: fork를 명시하지 않아 메인 세션이 R0~R6를 직접 운전한다. R0 방향 리서치·값 grounding은Agent도구로 researcher(디자인 레퍼런스 모드) + 분해·시안 authoring은 designer 단발 sub-call 위임(ADR-058). 종료 후 사용자가/clear권장. **R0 캡처(capture-refs)·R6 테마 배선(builder 단발)**은 Bash·코드 작성이 필요해 각각 메인 세션 실행·builder 위임이다(designer는 Bash 없음). 라운드 구조·R0 리서치·수용 게이트·시안 카드 SSOT는 ADR-058(design workflow). DESIGN.md 내용(8섹션+Motion / 3-tier 토큰 / Don'ts / 정체성·a11y·category state·responsive)·인터페이스 할당 SSOT는 ADR-073.
트리거
/bootstrap-stack종료 출력에 "frontend 감지됨./bootstrap-design권장" 텍스트 한 줄. 사용자 발화로 시작.- 비-UI 프로젝트(API server·CLI 등)는 호출되지 않음 — UI surface 가 없어 design 산출물이 불필요하기 때문이며 ADR-031 직접 지원 범위와는 무관하다(API server·CLI 도 직접 지원 6종에 포함 — ADR-031#amend-1).
- 본 skill은 baseline placeholder DESIGN.md를 채우는 흐름. 비-UI 프로젝트는 fork 직후 DESIGN.md를 삭제했음을 전제. 파일 부재 시 작업 중단 + 사용자에게 보고.
Codex: 본 skill은 wrapper 미보유(자연어 호출) — Codex에서는 "Follow .claude/skills/bootstrap-design/SKILL.md"로 호출한다(목록 SSOT = README, ADR-010#amend-3·#amend-4). 본문의 Agent 위임(R0 researcher 디자인 레퍼런스 조사 · R0~R2 designer authoring · R2-1.5 reviewer 구별성 비평 · R2-G/R6 reviewer 픽셀 판정 · 게이트 repair designer 재생성)은 Codex에 persona 매핑이 없어 메인 세션이 각 persona 파일(researcher.md/designer.md/reviewer.md)을 읽고 순차 인라인 수행하며 생략하지 않는다(ADR-010). 동일 세션 degrade 계약 (ADR-058 D5): (a) designer→reviewer 페르소나 전환을 명시적 단계로 끊고, (b) 그 라운드 산출물과 최종 출력에 under-verified: 동일 세션 감사를 명시하며, (c) 완전 독립 감사가 요구되면 승인 보류한다. 결정적 렌더 게이트(STACK_SETUP_PLAN.md ## Design Gate Adapter의 ready command)는 세션 격리와 무관하게 그대로 실행되므로 배포불가 결함(serious/critical axe·320 geometry)은 Codex 경로에서도 차단된다.
모드
--fast: R0(Layer A/B minimal — 있으면 사용자 힌트 우선, 없으면 자율 조사 1~2개로 최소 grounding + minimal 노트) + R1(원칙 1줄 + voice 기본값 확인 1회) + R3(토큰) + R5(저장 — 축약 섹션, §10 포함). 갤러리 라운드(R0-G)·R2 concept·R4·R6-2 reviewer 픽셀 판정 생략 — R6-1 테마 배선·쇼케이스·게이트는 수행(_theme/manifest.json이 design-milestone 필수 입력) — R5 저장은 생략하지 않는다. R1은 완전 생략 금지(minimal 1줄). 게이트는 산출물 기준 —--fast는 R2(concept) 미생성이라 R2-G 게이트 적용 대상 없음(N/A, ADR-058 D3).--fast에서 concept이 필요하면 종료 후 명시 발화로 R2 단독 수행. 종료 출력에 «## 7미작성 —/design-milestone전에 R4 단독 수행 권장» 한 줄을 낸다:--fast는 R4(컴포넌트 인벤토리)를 생략하는데/design-milestoneR3 브리프의 «재사용 vs 신규» 와 ADR-073 D8 의 인터페이스 요소 등록 계약은## 7이 채워져 있음을 전제한다. 인용할 대상이 없으면 모든 요소가 «신규» 가 되어 미등록 신규 UI 가 구조적으로 재발한다(dogfood Round 11 발견 21 계열).- 기본: R0~R6 모두.
--update: 기존 DESIGN.md가 있을 때의 부분 갱신/재디자인 모드(아래## --update 모드). 처음부터 R0~R6를 다시 돌지 않는다. 프로필 추가·공유 모드 변경·폰트 교체는 R1 브리프 재실행 + R6 재검토(ADR-073 D11); 토큰·컴포넌트가 바뀌면 R6-1 배선을 delta 재생성한다(생략 금지); §10이 v1 형식(언어 블록·용어 사전 없음)인 기존 fork는 R5에서 §10 v2로 마이그레이션(기본값 채움 + 확인 1회 — 구 plan-milestone R5의 §10 신설 경로 승계).
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.
- 1mo ago Changed · +16 lines 1f330d0d87f2
- 1mo ago First seen · 239 lines · 50 tokens per session scan A aa4397bbe22f
bootstrap-design is a skill published in the GitHub repository kohj1018/agentic-dev-harness (2 stars, last pushed 24d ago), licensed MIT. It adds 50 tokens to every session and 12,298 once invoked, about $0.0002 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
kirby-panel-and-blueprints
Designs Kirby 6 blueprints and Panel UI, including reuse/extends, programmable blueprints, value/display fields and areas. Use when changing Panel schemas or migrating legacy sections.
unity-ui-art-and-motion-production
Use when new or revised Unity UI visuals, icons, panels, 9-slice sprites, component states, HUD or menu layouts, popup motion, screen transitions, or flattened UI screenshot decomposition must be produced through Figma and integrated into uGUI, NGUI, or UI Toolkit; not for UI debugging, localization-only work…
hipson-visual-experience-director
Use for visual direction, premium UI/UX art direction, motion interaction design, Codex-ready implementation briefs, and visual QA for web experiences.
hipson-premium-ui-ux
Use for premium UI/UX review and implementation planning in Hipson frontend projects, especially screenshot-backed landing pages, forms, visual polish, accessibility, responsive behavior, and design-agent packets.
hipson-creative-frontend-motion-architect
Use for premium creative frontend, motion UI, scroll-driven animation, scrollytelling, cinematic landing pages, microinteractions, and implementation-ready prompts for React/Next.js frontend agents.
figma-generate-design
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the…