factory-rdr

Standardizes AI agent decision requests with options, recommendations, and audit trails.

1|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/e2its/myrmion-AI-factory --skill factory-rdr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: factory-rdr
Source: https://github.com/e2its/myrmion-AI-factory/tree/main/.claude/skills/factory-rdr
Command: npx skills add https://github.com/e2its/myrmion-AI-factory --skill factory-rdr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of inconsistent, un-auditable, or biased decision-making when AI agents pose choices to users, eliminating lost decisions, lack of transparency, and ungrounded recommendations that can lead to misalignment with project goals.

Core Features & Use Cases

  • Structured Decision Framing: Mandates 3+ options with a justified recommendation grounded in project context, governance rules, or industry defaults, plus adversarial tradeoff analysis for each option.
  • Verbatim Intent Capture: Preserves the exact user input to avoid misinterpretation of their choice.
  • Immediate Audit Trail: Ratifies decisions in the same turn by persisting to both machine-readable progress metadata and human-readable inline artifact comments for full traceability.
  • Use Case: Used across all Myrmion AI Factory agents for project setup discovery, feature scope definition, design selection, low-confidence audit calls, and DevOps environment configuration.

Quick Start

When an agent needs to pose a decision with multiple alternatives to the user, invoke the factory-rdr protocol to frame the options, capture the user's choice, and persist the ratified decision immediately.

Frequently Asked Questions about factory-rdr

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

FAQPage Schema
How do I enforce an audit trail for AI agent decision ratification?

To enforce an audit trail for agent decision ratification, use a standardized workflow that mandates multiple options, captures verbatim user intent, and persists decisions immediately to both machine-readable metadata and human-readable artifacts.

What is adversarial reasoning in AI agent governance?

Adversarial reasoning in agent governance is the process of analyzing tradeoffs for each decision option presented to a user, ensuring recommendations are grounded in project context and preventing biased or ungrounded choices.

How do I preserve user intent capture during SDLC protocol execution?

To preserve user intent capture during SDLC protocol execution, implement a mechanism that records the exact verbatim user input when ratifying decisions, preventing misinterpretation of their choices across downstream agent tasks.

Can I use structured decision framing for low-confidence audit calls?

Yes, structured decision framing applies to low-confidence audit calls by mandating at least three options with justified recommendations, ensuring transparent decision trails for project setup, feature scoping, and DevOps configuration.

Does incremental persistence support downstream coherence validation?

Incremental persistence supports downstream coherence validation by immediately ratifying decisions within the same turn, writing to progress metadata and inline artifact comments to maintain full traceability and auditability.

What are the limitations of unstructured AI agent recommendation workflows?

Unstructured recommendation workflows lead to lost decisions, lack of transparency, and ungrounded recommendations, causing misalignment with project goals and failing governance requirements for verifiable audit trails.