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-mcp-create-flowgit 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-mcp-create-flow)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-mcp-create-flow"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-mcp-create-flow/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/konamgil/mandu/mandu-mcp-create-flow"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-mcp-create-flow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00076 | $0.01889 |
| Opus 5.5 | $0.00030 | $0.00756 |
| Sonnet 5.5 | $0.00015 | $0.00378 |
| Haiku 4.5 | $0.00008 | $0.00189 |
Grade A, and why
mandu-mcp-create-flow 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu MCP Create Flow
새 기능을 스캐폴딩할 때의 스펙 우선 레시피. "contract 없이 generate 먼저" 라는 대표적 실수를 방지하고, 가능한 한 집계 도구 (resource/feature/scaffold) 를 사용한다.
Trigger
- "만들어줘", "추가해줘", "create", "add"
- "CRUD" + 엔티티 이름
- 피처 / 라우트 / 리소스 / API 엔드포인트 / 컴포넌트 추가
mandu-create-feature또는mandu-create-apitask-shaped skill 이 활성화될 때
Decision Tree
요청의 단위를 먼저 구분한다.
요청 내용
├─ 리소스 단위 (User, Post, Comment 같은 도메인 엔티티)
│ → Track A: Resource flow
├─ 피처 단위 (페이지 + 섹션 + island + slot 세트)
│ → Track B: Feature flow
├─ 단일 라우트 (페이지 하나 또는 API 하나만)
│ → Track C: Route flow
└─ 스키마만 이미 있고 스캐폴드만 필요
→ Track D: Scaffold-only
Track A — Resource Flow (도메인 엔티티)
mandu.resource.create ← Tier-0 aggregate: resource + fields 묶음 생성
└─> mandu_create_contract ← Zod 계약 (집계 도구가 자동으로 요청하지 않을 때만)
└─> mandu_generate ← 스캐폴드 생성
└─> mandu-mcp-verify 로 전이
mandu.resource.create 인자 예:
mandu.resource.create({
name: "Post",
fields: { title: "string", content: "string", publishedAt: "datetime?" }
})
리소스가 생성되면 route / slot / contract 의 후보가 제안된다. 제안을 그대로
받아 mandu_generate 로 흘린다. 제안된 경로를 무시하고 mandu_add_route 로
손수 만들지 않는다.
Track B — Feature Flow (페이지 + island + slot)
mandu_analyze_structure ← alias of mandu.negotiate.analyze, 요구사항 → 구조 제안
└─> mandu.feature.create ← Tier-0 aggregate: 여러 라우트 + slot + island 묶음
└─> mandu_create_contract ← API 엔드포인트가 포함된 경우
└─> mandu_generate
└─> mandu-mcp-verify 로 전이
또는 단축 경로:
mandu_generate_scaffold ← alias of mandu.negotiate.scaffold,
negotiate + scaffold 를 한 번에
└─> mandu-mcp-verify
사용자가 이미 스키마를 구체적으로 제시했다면 mandu_analyze_structure 는 스킵.
"대충 사용자 프로필 페이지 만들어줘" 처럼 모호한 요청일 때만 negotiate 먼저.
Track C — Single Route Flow
mandu_add_route ← 파일 생성 (경로 규칙 자동 적용)
└─> mandu_create_contract ← API 라우트면 필수, 페이지만이면 생략 가능
└─> mandu_generate ← 스캐폴드 반영
└─> mandu-mcp-verify
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 First seen · 184 lines · 76 tokens per session scan A a4e3fe1fde87
mandu-mcp-create-flow is a skill published in the GitHub repository konamgil/mandu (47 stars, last pushed 2mo ago), licensed MPL-2.0. It adds 76 tokens to every session and 1,889 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 2026-08-30.
Other skills, from other repositories
Full Stack Engineer
Full Stack Engineer delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
frontmcp-guides
Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…
bunqueue
Use when building or operating bunqueue queues, workers, durable workflows, agent turns, MCP tools, retries, cron or dependency flows.
architecture-paradigm-microservices
Applies microservices for independent deployment and per-service scaling. Use when teams need autonomous release cycles with distinct capability scaling needs.
architecture-paradigm-event-driven
Applies event-driven async messaging to decouple producers and consumers. Use when designing real-time or multi-subscriber systems needing loose coupling.