Mandu Guard

SkillDev tools

Resolve Mandu architecture violations without weakening policy.

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Mandu Guard skill

What this skill tells your AI

The instructions your AI receives, as published by konamgil/mandu in skills/official/mandu-guard/SKILL.md and read by ahel’s review.

Use when planning or verification reports an import, layer, location, or generated-artifact violation.

Fix the dependency direction or file ownership that caused the diagnostic.
Do not disable a rule or broaden an allowlist unless policy change is the explicit task.
Read generated data through the runtime registry; never import or edit .mandu/generated artifacts directly.
Keep fixes inside the plan scope and preserve user changes.

Start with mandu.agent.verify, use mandu.agent.repair for structured next actions, and verify again after the repair.

Advanced