Mandu Testing

SkillDev tools

Select and run evidence-bearing Bun tests for Mandu changes.

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 Testing skill

What this skill tells your AI

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

Use after planning identifies the changed behavior or verification recommends a test.

Prefer the smallest test that executes the changed contract, then expand to the affected package and Golden Path.
Use bun test; do not substitute npm or pnpm runners.
Test failure paths, scope preservation, and generated-output invariants.
Do not treat a dry run, fixture string, or missing measurement as successful runtime evidence.
ATE and browser-healing experiments are Labs and not part of stable testing.

Finish with mandu.agent.verify --changed --json --write.

Advanced