reward-guard

What problem does it solve?

This Skill prevents premature task completion declarations by enforcing evidence-based validation through 3-point verification and critic reviews before marking anything as done.

Core Features & Use Cases

• Evidence Enforcement: Requires technical, consistency, and completeness validation for every subtask
• Critic Integration: Mandates critic agent review before state transitions to done
• Scope Protection: Detects and prevents unauthorized scope changes
• Use Case: When marking a task as complete, this Skill ensures you have concrete evidence for each completion criterion, has been reviewed by the critic agent, and hasn't secretly expanded scope - preventing "it feels done" declarations.

Quick Start

The reward-guard skill automatically activates when you try to mark tasks as done, enforcing evidence-based validation and critic review to prevent self-reward fraud.