mandu-guard

mandu-guard is a skill for Claude Code, Codex from konamgil/mandu. It costs 43 tokens per session (992 once invoked), scanned A, original, MPL-2.0.

An architecture-checking system for Mandu that enforces which software layers may depend on one another and where files belong.

In plain words
What is it for?
Use it to verify changed files, inspect dependency or layer errors, explain violations, and repair allowed source files.
Why use it?
It identifies architecture violations and provides a defined process for repairing them without hiding the problem by weakening the rules.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to verify changed files, inspect dependency or layer errors, explain violations, and repair allowed source files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/konamgil/mandu/mandu-guard
Install

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.

Any agent
npx skills add konamgil/mandu --skill mandu-guard
Clone the repo
git clone --depth 1 https://github.com/konamgil/mandu

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mandu-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/konamgil/mandu/mandu-guard/github.svg)](https://agentmods.dev/skills/konamgil/mandu/mandu-guard)
Your own site
<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-guard"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-guard/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.

agentmods 80×15 button for mandu-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-guard"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.00992
Opus 5 $0.00022 $0.00496
Sonnet 5 $0.00009 $0.00198
Haiku 4.5 $0.00004 $0.00099

Measured 10d ago against content hash 9cad379c92df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mandu-guard scanned grade A with 1 finding 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 10d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

| `FORBIDDEN_IMPORT` | Forbidden import (fs, child_process, etc.) |
docs/archive/skills/mcp-v0/mandu-guard/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mandu Guard

Mandu Guard는 아키텍처 규칙을 강제하는 시스템입니다. 레이어 간 의존성을 검사하고 위반을 실시간으로 감지합니다.

Agent Workflow Contract

This skill is a Domain addendum. It must not replace mandu-agent-workflow. Use it only after mandu.agent.verify reports guard diagnostics or mandu.agent.plan selects the guard domain.

Canonical workflow step: verify -> repair.

Preferred MCP tools:

Step Tools
plan mandu.agent.plan
verify mandu.agent.verify, mandu.guard.check, mandu.guard.explain
repair mandu.agent.repair, mandu.guard.heal

Allowed file edits:

  • Source files that violate import/layer rules
  • mandu.config.* guard settings only when the plan explicitly changes policy
  • Generated files are not direct-edit targets

Verification command:

mandu agent verify --changed --json --write

Common failures:

  • Running low-level guard commands before reading the agent verify report
  • Weakening guard config instead of fixing the import boundary
  • Directly editing generated files to silence diagnostics

Repair path:

mandu agent repair --from .mandu/agent-verify.json --json

When to Apply

Reference these guidelines when:

  • Setting up architecture rules
  • Checking layer dependencies
  • Validating import paths
  • Running architecture checks in CI
  • Configuring guard presets

Rule Categories by Priority

Priority Category Impact Prefix
1 Layer Rules CRITICAL guard-layer-
2 Presets HIGH guard-preset-
3 Validation HIGH guard-validate-
4 Configuration MEDIUM guard-config-

Quick Reference

1. Layer Rules (CRITICAL)

  • guard-layer-direction - Dependencies flow downward only
  • guard-layer-violation - Detect and fix layer violations
  • guard-layer-same-level - Restrict same-layer imports

2. Presets (HIGH)

  • guard-preset-mandu - FSD + Clean hybrid (default)
  • guard-preset-fsd - Feature-Sliced Design
  • guard-preset-clean - Clean Architecture
  • guard-preset-hexagonal - Hexagonal/Ports & Adapters

Read the full file on GitHub · 163 lines

Files

What ships with it

7 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.

Changes

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.

  1. 10d ago First seen · 163 lines · 43 tokens per session scan A 9cad379c92df

Subscribe to this mod's changes

mandu-guard is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 13d ago), licensed MPL-2.0. It adds 43 tokens to every session and 992 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories