ux-audit

Real-user dogfooding with emotional friction tracking, click efficiency counting, and resilience testing to produce ranked audit reports. Walk through a live web app AS a real user. The audit is interaction-first — typing, clicking, sending, watching, screenshotting. A static DOM sweep cannot produce a verdict. Most catastrophic UX bugs only surface under interaction: A DOM probe sees none of these. They require: type → wait → screenshot → diff → console-read → repeat. The previous audit method drifted toward sweep mode (faster, feels productive, blind to behaviour). v2 makes that drift impossible — the agent cannot output "Pass" without an Interaction Manifest that proves real clicks happened. The audit ends in exactly one of: If the work doesn't include a complete Interaction Manifest, the only legal verdict is Incomplete .