main-skill

What problem does it solve?

It prevents agent actions from violating the project’s governance rules by centralizing decision-making, risk classification, validation, and controlled delegation to subordinate skills.

Core Features & Use Cases

• Governed orchestration: Coordinates which skills run and how session state is updated without allowing subordinate actions to contradict user instructions or agf.md.
• Risk × Impact decisioning: Classifies tasks into TURBO, CAUTION, PLANNING, or SECURITY STOP modes based on reversibility and impact, including a 3-attempt failure policy.
• Pre-flight validation and anti-hallucination: Reads agf.md and relevant memory sources before writes/commands, and verifies outcomes rather than assuming success.
• Evolution with approval: Proposes improvements in a structured format and applies changes only after explicit user approval.

Quick Start

Tell the orchestrator what you want to change in your repo and include the keyword "borabill" so it can initialize safely and propose a plan when needed.