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 konamgil/mandu --skill mandu-uigit clone --depth 1 https://github.com/konamgil/manduWrote 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/konamgil/mandu/mandu-ui)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-ui"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-ui.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00011 | $0.00997 |
| Opus 5 | $0.00005 | $0.00498 |
| Sonnet 5 | $0.00002 | $0.00199 |
| Haiku 4.5 | $0.00001 | $0.00100 |
Grade A, and why
Mandu 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 8d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu UI Skill
Mandu Island 아키텍처에 UI 컴포넌트 라이브러리를 통합하는 가이드입니다.
Agent Workflow Contract
This skill is a Domain addendum. It must not replace mandu-agent-workflow.
Use it only after mandu.agent.plan selects UI, design, styling, component, or hydration domains.
Canonical workflow step: plan -> apply -> verify.
Preferred MCP tools:
| Step | Tools |
|---|---|
| plan | mandu.agent.plan, mandu.design.get, mandu.component.list |
| apply | mandu.agent.apply, mandu.component.add |
| verify | mandu.agent.verify, mandu.design.check, mandu.lint |
| repair | mandu.agent.repair |
Allowed file edits:
components/ui/**/*.tsx- Route-local island/client components named in the plan
- Styling utilities only when they are required by the selected component
Verification command:
mandu agent verify --changed --json --write
Common failures:
- Adding UI libraries before reading the existing design/component inventory
- Mixing server components and island-only UI imports
- Skipping accessibility or design checks for interactive components
Repair path:
mandu agent repair --from .mandu/agent-verify.json --json
핵심 원칙
- Headless First: Radix UI 기반으로 동작과 스타일 분리
- Copy-Paste: shadcn/ui 방식으로 소유권 유지
- Accessibility: WCAG 2.1 AA 수준 준수
- Island 호환: 클라이언트 컴포넌트로 올바르게 분리
권장 스택
Primitives: Radix UI (headless, accessible)
Components: shadcn/ui (copy-paste, customizable)
Icons: Lucide React
Utilities: clsx, tailwind-merge, cva
Setup Examples
Use these examples only after mandu.agent.plan selects UI library setup.
shadcn/ui 초기화
bunx shadcn-ui@latest init
✔ Would you like to use TypeScript? yes
✔ Which style would you like to use? Default
✔ Which color would you like to use as base? Slate
✔ Where is your global CSS file? app/globals.css
✔ Do you want to use CSS variables? yes
✔ Where is your tailwind.config located? tailwind.config.ts
✔ Configure import alias for components? @/components
✔ Configure import alias for utils? @/lib/utils
What ships with it
9 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.
- 8d ago First seen · 160 lines · 11 tokens per session scan A 7f8818ed3d29
Mandu UI is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 12d ago), licensed MPL-2.0. It adds 11 tokens to every session and 997 once invoked, about $0.0001 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
accessibility-auditor
Use when the user asks to audit accessibility, keyboard usability, semantics, contrast, focus behavior, or assistive-technology support in a UI. Inspect the actual rendered page and interaction states, report evidence-backed findings, and only implement fixes when explicitly requested.
ui-implementer
Use when the user asks to implement or revise a web, desktop, or mobile interface from a requirement, design, or screenshot. Inspect the existing UI architecture and real runtime first, reuse established components and tokens, and verify the rendered DOM, responsive states, and browser errors.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
real-prototype
Implement several variations of a design directly inside the running app, on the real page/route, with a live switcher to toggle between them in the browser, then recommend one and fold the winner into the real code. Variants are real implementations judged against real data, layout, and density (not an isolated…
create-design-system
You are an expert design systems architect.
ui-web
Web UI - glassmorphism, Tailwind, dark mode, accessibility.