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-guardgit 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)<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.
<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>- 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 | $0.00043 | $0.00992 |
| Opus 5 | $0.00022 | $0.00496 |
| Sonnet 5 | $0.00009 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
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.) | 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 onlyguard-layer-violation- Detect and fix layer violationsguard-layer-same-level- Restrict same-layer imports
2. Presets (HIGH)
guard-preset-mandu- FSD + Clean hybrid (default)guard-preset-fsd- Feature-Sliced Designguard-preset-clean- Clean Architectureguard-preset-hexagonal- Hexagonal/Ports & Adapters
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.
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.
- 10d ago First seen · 163 lines · 43 tokens per session scan A 9cad379c92df
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.
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…