What problem does it solve? When an organization runs multiple Squad instances across different repositories, agents lack a standard way to discover each other, share context, and hand off work without creating tight coupling or leaking internal state. ## Core Features & Use Cases - Squad Discovery: Locate other squads via .squad/manifest.json files, upstream configs, or a central registry, and read their declared capabilities. - Work Delegation Protocol: Create properly labeled cross-squad issues in target repositories using gh issue create, with acceptance criteria and links back to the originating work. - Feedback Loop Tracking: Poll delegated issue status with gh issue view and update the originating squad's orchestration log until completion. - Use Case: A frontend squad needs a Prometheus metrics endpoint added to a service owned by the platform squad. The agent discovers the platform squad's manifest, verifies it accepts issues, and delegates the task with full context and acceptance criteria. ## Quick Start Ask the agent to discover available squads and delegate a task to the appropriate squad using the cross-squad handoff protocol.
