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-explaingit 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-explain)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-explain"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-explain.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.01110 |
| Opus 5 | $0.00019 | $0.00555 |
| Sonnet 5 | $0.00008 | $0.00222 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
mandu-explain 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 7d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu Explain
Mandu 프레임워크의 핵심 개념 18가지를 설명하는 레퍼런스.
Core Concepts
1. Island Architecture
페이지의 대부분은 정적 HTML로 서버 렌더링하고, 인터랙티브한 부분만 JavaScript를 로드하는 패턴.
[Static HTML] [Static HTML] [Island: JS] [Static HTML]
장점: 초기 로딩 속도, 작은 번들 크기, SEO 친화적.
2. Filling (Mandu.filling())
API 핸들러를 체이닝으로 작성하는 API. Express의 미들웨어와 유사하지만 타입 안전.
Mandu.filling().guard(authCheck).get(handler).post(handler)
3. Guard
아키텍처 규칙을 코드 레벨에서 강제하는 시스템. import 방향, 파일 위치, 금지된 의존성을 검사.
bunx mandu guard arch # 전체 프로젝트 검사
4. Contract
Zod 스키마 기반 API 계약. 클라이언트-서버 간 타입을 공유하고 런타임 validation을 수행.
// src/shared/contracts/user.contract.ts
export const CreateUser = z.object({ name: z.string(), email: z.string().email() });
5. Slot
서버에서 렌더링 전에 실행되는 데이터 로더. spec/slots/*.slot.ts에 위치.
// spec/slots/dashboard.slot.ts - page 렌더링 전에 데이터를 fetch
export default Mandu.filling().get(async (ctx) => ctx.ok({ stats: await getStats() }));
6. SSR (Server-Side Rendering)
모든 페이지를 서버에서 HTML로 렌더링. app/layout.tsx에서 <html>/<head>/<body> 태그 불필요 (자동 생성).
7. Streaming SSR
서버에서 HTML을 청크 단위로 스트리밍. 첫 바이트 시간(TTFB)을 단축.
8. Hydration
서버 렌더링된 HTML에 JavaScript 인터랙티비티를 부착하는 과정.
Priority: immediate > visible > idle > interaction
9. FS Routes
파일 시스템 기반 라우팅. app/ 폴더 구조가 URL이 됨.
app/page.tsx->/app/users/[id]/page.tsx->/users/:id
10. Layout
페이지를 감싸는 공통 UI 래퍼. <html>/<head>/<body> 사용 금지.
export default function Layout({ children }) {
return <div className="min-h-screen">{children}</div>;
}
11. Route Groups
(name) 괄호로 감싼 폴더는 URL에 영향 없이 라우트를 그룹화.
app/(auth)/login/page.tsx -> /login
app/(auth)/signup/page.tsx -> /signup
12. MCP (Model Context Protocol)
AI 에이전트가 프레임워크 도구를 직접 호출하는 인터페이스.
@mandujs/mcp가 50+ 도구를 제공: negotiate, generate, guard, brain 등.
13. ATE (Automated Test Engine)
API 엔드포인트의 테스트를 자동 생성하는 엔진.
14. Brain
코드 분석 및 진단 시스템. 프로젝트 구조, 의존성, 성능 이슈를 분석.
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.
- 7d ago First seen · 127 lines · 38 tokens per session scan A 67d6d9cb8028
mandu-explain is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 11d ago), licensed MPL-2.0. It adds 38 tokens to every session and 1,110 once invoked, about $0.0002 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
learner
Pattern learner. Activated when the user says "learn from this", "what patterns", "improve skills", "retrospective", "session review", or wants to extract reusable patterns from recent work to improve the project's skills and conventions.
create-conceptmap
You are an intelligent assistant specialized in knowledge visualization and educational data structuring.
analyze-answers
You are a PHD expert on the subject defined in the input section provided below.
analyze-debate
You are a neutral and objective entity whose sole purpose is to help humans understand debates to broaden their own views.
analyze-cfp-submission
You are an AI assistant specialized in reviewing speaking session submissions for conferences.
create-diy
You are an AI assistant tasked with creating "Do It Yourself" tutorial patterns.