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-guard-guidegit 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-guard-guide)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-guard-guide"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-guard-guide/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-guard-guide"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-guard-guide.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 | $0.00034 | $0.01298 |
| Opus 5 | $0.00017 | $0.00649 |
| Sonnet 5 | $0.00007 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
mandu-guard-guide 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu Guard Guide
Mandu Guard 아키텍처 강제 시스템의 상세 가이드. 6개 프리셋, 위반 유형별 수정 방법, 레이어 규칙을 다룹니다.
가드레일 3축 (중요)
Mandu 의 품질 가드레일은 단일 도구가 아니라 3축 병렬:
| 축 | 무엇을 잡나 | 도구 | 이 skill |
|---|---|---|---|
| Guard | 아키텍처 / 레이어 / import 규칙 | mandu guard |
여기 (지금) |
| Typecheck | 타입 에러 | tsgo / mandu check |
mandu-mcp-verify |
| Lint | 코드 품질 (any / unused / promise-leak 등) | oxlint |
mandu-lint |
세 축은 서로 겹치지 않고 상호보완. Guard 는 "B 레이어가 A 를 import 해도 되나?" 를 보고, lint 는 "이 함수 파라미터가 any 인가?" 를 보고, typecheck 는 "이 unknown 을 진짜로 string 으로 좁혔나?" 를 본다. 어느 하나를 꺼두면 다른 축이 잡지 못하는 구멍이 열림. mandu check 가 셋 모두를 한 번에 실행한다.
6 Presets
mandu (default)
FSD + Clean Architecture 하이브리드. 프론트엔드와 백엔드 모두 커버.
// mandu.config.ts
export default { guard: { preset: "mandu" } };
fsd (Feature-Sliced Design)
프론트엔드 전용. 7계층 레이어 구조.
app > pages > widgets > features > entities > shared
clean (Clean Architecture)
백엔드 전용. 의존성 역전 원칙.
api > application > domain > infra > core > shared
hexagonal (Ports & Adapters)
포트와 어댑터 패턴. domain이 중심, adapters가 외부 의존성 처리.
adapters > ports > application > domain
atomic (Atomic Design)
UI 컴포넌트 전용. atoms -> molecules -> organisms -> templates -> pages.
cqrs (Command Query Responsibility Segregation)
명령과 조회를 분리. command, query, event, dto 전용 구조.
Violation Types and Fixes
LAYER_VIOLATION (error)
상위 레이어가 하위 레이어를 import하는 것만 허용.
// BAD: shared가 features를 import (하위 -> 상위)
// src/shared/utils/helper.ts
import { useAuth } from "@/features/auth"; // VIOLATION
// FIX: 의존 방향 반전, 또는 shared에 인터페이스 정의
// src/shared/types/auth.ts
export interface AuthContext { userId: string; }
FORBIDDEN_IMPORT (error)
클라이언트 코드에서 서버 전용 모듈 import 금지.
// BAD: island에서 fs import
// app/editor.island.tsx
import fs from "fs"; // VIOLATION
// FIX: 서버 로직은 slot으로 분리
// spec/slots/editor.slot.ts
import fs from "fs"; // OK (server-only)
WRONG_SLOT_LOCATION (warning)
Slot 파일이 잘못된 위치에 있음.
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 · 170 lines · 34 tokens per session scan A bcd2d923fde9
mandu-guard-guide is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 13d ago), licensed MPL-2.0. It adds 34 tokens to every session and 1,298 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-analyze
Run TrueCourse architecture analysis on this repository.
code-review
A review process for a pull request, which is a proposed set of code changes. It examines the changed code and its surrounding files for bugs, security problems, design issues, and lint errors.
security-audit
A security review skill for examining code changes in a pull request, which is a proposed set of changes awaiting approval. It reports issues such as injection, exposed secrets, unsafe authentication, weak cryptography, vulnerable dependencies, and infrastructure mistakes.
code-governance
A review skill that checks pull-request changes for software licenses, personal information, compliance details, and an audit trail. An audit trail is a record showing what was checked and why.
Architecture Reviewer
Architecture Reviewer delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.
architecture-governance
Keep code changes conformant to a repo's real, declared architecture using ArchSteer. Use when starting work in an unfamiliar repo, before finishing/committing an architecturally significant change (new dependency, new data access, new external call, new layer), or when asked about a codebase's architecture, layers…