A production-grade AI Agent Harness engineering template providing a reliable, observable, and recoverable Agent runtime environment.
Instructions file CodexOpenCode
Instructions for a six-role multi-agent system: Coordinator, Planner, Reviewer, Executor, Evaluator, and Memory Curator. The roles divide work such as understanding requests, planning, coding, checking results, and preserving useful context.
Instructions file
A project guide for an AI-agent harness, meaning software that runs and coordinates coding or research agents. It describes skills, session hooks, multiple agents, tool connections, memory, and built-in checks, with commands for setup and verification.