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-create-featuregit 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-create-feature)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-create-feature"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-create-feature.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 | $0.00036 | $0.00755 |
| Opus 5 | $0.00018 | $0.00378 |
| Sonnet 5 | $0.00007 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
mandu-create-feature 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.
What it actually says
Mandu Create Feature
Mandu 프로젝트에 새 피처를 생성하는 5단계 워크플로우. MCP 도구 파이프라인을 통해 페이지, API, Island을 자동 스캐폴딩합니다.
5-Phase Workflow
Phase 1: Negotiate (요구사항 분석)
MCP 도구 mandu_negotiate를 호출하여 피처 요구사항을 분석합니다.
mandu_negotiate({ description: "사용자 프로필 페이지와 편집 기능" })
결과: 필요한 라우트, 컴포넌트, API 엔드포인트 목록이 반환됩니다.
Phase 2: Add Routes (라우트 생성)
분석 결과를 바탕으로 mandu_add_route로 라우트를 생성합니다.
mandu_add_route({ path: "/users/[id]", type: "page" })
mandu_add_route({ path: "/api/users/[id]", type: "api" })
파일 생성 규칙:
- Page:
app/users/[id]/page.tsx - API:
app/api/users/[id]/route.ts - Layout:
app/users/layout.tsx
Phase 3: Create Contracts (타입 계약)
mandu_create_contract로 API 계약을 정의합니다.
mandu_create_contract({
name: "user",
methods: ["get", "patch"],
fields: { name: "string", email: "string", avatar: "string?" }
})
생성 위치: src/shared/contracts/user.contract.ts
Phase 4: Generate Scaffold (코드 생성)
mandu_generate로 전체 스캐폴드를 생성합니다.
mandu_generate({ spec: negotiateResult })
생성되는 파일:
.mandu/generated/server/- 서버 코드.mandu/generated/web/- 클라이언트 코드spec/slots/*.slot.ts- 서버 데이터 로더app/**/*.island.tsx- Island 컴포넌트
Phase 5: Guard Heal (아키텍처 검증)
mandu_guard_heal로 생성된 코드의 아키텍처 규칙 준수를 검증합니다.
mandu_guard_heal({ autofix: true })
위반 사항이 있으면 자동 수정을 시도합니다.
Quick Recipes
새 페이지 추가
negotiate → add_route(page) → generate
새 API + 페이지
negotiate → add_route(page) → add_route(api) → create_contract → generate → guard_heal
Island 추가
negotiate → add_route(page) → generate → island 파일에 "use client" 확인
Key Rules
- 항상
mandu_negotiate부터 시작 (분석 없이 직접 생성하지 않기) - API 엔드포인트에는 반드시 contract 생성
- 생성 후
mandu_guard_heal로 검증 - Layout에
<html>/<head>/<body>태그 사용 금지 - Island 파일은
@mandujs/core/client에서 import
See also
mandu-mcp-create-flow— MCP 도구 오케스트레이션 순서 (negotiate → contract → generate)mandu-mcp-verify— 생성 직후 자동 검증 루프
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 · 106 lines · 36 tokens per session scan A 08f8eb33392b
mandu-create-feature is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 11d ago), licensed MPL-2.0. It adds 36 tokens to every session and 755 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
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
truecourse-list
List TrueCourse violations found in this repository.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
flash-reel
Generates a 30-second 9 16 cinematic reel from a user prompt (setting + vibe + rough storyline). Flash Reel — 30s Cinematic Reel Skill When to use User provides: a setting, a vibe/mood, and optionally a rough storyline. They want a 30 second 9:16 reel with hard cuts every 3-4 seconds, anchored by one or more…
kling-3-prompt-director
Production-ready Kling 3.0 video prompt director using the canonical 9-field formula. Includes locked character/environment specs for the Crococopter and Swa & Danny universes. Trigger on any request pairing "Kling" with prompt-related verbs.