santa-method
OfficialDual-agent verification to ensure safe outputs.
Software Engineering#verification#convergence#rubric#quality-assurance#escalation#ai-safety#dual-review
Authoragentmatters
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Two independent reviewers must both pass before shipping to eliminate single-review biases and improve output quality, safety, and compliance.
Core Features & Use Cases
- Independent dual review with identical rubrics
- Convergence loop with fixed iteration cap and optional escalation
- Fresh reviewer instances per round to prevent context bleed
- Suitable for high-stakes content, production code, and policy-compliant documentation
Quick Start
Invoke the Santa Method to verify a generated artifact by running two independent reviewers against a shared rubric and iterating until both pass.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: santa-method Download link: https://github.com/agentmatters/mullai-bot/archive/main.zip#santa-method Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.