Secure AI Multi-Agent Coding Workflow Template Released

A reference architecture for AI agent orchestration, trust measurement, and tool integration has been released as a template. It is designed for experienced developers working with autonomous AI agents. The template demonstrates how to run a council of AI agents across a shared codebase with board-driven task delegation, automated PR review, security hardening, and containerized tooling. It also includes standalone research packages for sleeper agent detection, autonomous economic agent simulation, and cross-platform runtime injection. The template emphasizes the importance of AI safety training and understanding the risks associated with AI agents. It provides a container-first approach, running all tools and CI/CD operations in Docker containers for maximum portability. The maintainer provides no guidance, consultation, or feature development, and no external contributions are accepted. This policy exists as a legal protection given the nature of the codebase. The template is released under a public domain dedication, allowing users to fork and adapt it freely. This project follows a container-first approach, ensuring portability and full control over runners.