reward-guard

Name: reward-guard
Availability: InStock
Author: m2ai-jp

Validates state transitions with technical, consistency, and completeness checks before marking tasks done.

Updated Aug 23, 2026

Search Tags:#quality control #validation #task completion #scope management #evidence-based #critic review

Ready to run

npx skills add https://github.com/M2AI-jp/thanks4claudecode-fresh --skill reward-guard

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: reward-guard
Source: https://github.com/M2AI-jp/thanks4claudecode-fresh/tree/main/.claude/skills/reward-guard
Command: npx skills add https://github.com/M2AI-jp/thanks4claudecode-fresh --skill reward-guard

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, and includes scripts (resource) and references (resource) components.

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.

Frequently Asked Questions about reward-guard

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I prevent marking tasks as complete without proper evidence?▼

Task completion requires evidence-based validation through three mandatory checks: technical validation, consistency verification, and completeness assessment. This Skill enforces all three before allowing state transitions to done, blocking premature declarations.

What does scope creep detection do in task validation?▼

Scope creep detection identifies unauthorized changes to task boundaries during completion. The Skill verifies that task scope remains aligned with original specifications, preventing hidden expansions that invalidate completion criteria.

Why should a critic agent review task completion?▼

Critic agent review provides independent validation that evidence meets completion standards and state transitions are justified. This actor-free control ensures objective assessment before marking tasks done, eliminating self-reward bias.

Can I use this Skill to audit completed tasks automatically?▼

Yes. The Skill activates via pre-tool scripts for trigger-based invocation, automatically enforcing validation and critic review whenever task completion is attempted. This creates an auditable record of all state transitions.

What happens if validation fails during task completion?▼

Failed validation blocks the state transition to done. The Skill returns specific validation failures—technical, consistency, or completeness gaps—allowing you to address deficiencies before resubmitting for completion.

Does this require additional tools beyond what I have?▼

The Skill depends on jq for data processing and requires a critic SubAgent for review. If you have jq installed and access to a critic agent, the Skill integrates directly into your completion workflow.