Orchestration system for Claude Code with memory-driven planning, multi-agent coordination, Agent Teams integration, automatic learning, and comprehensive security validation (Grade A-). v2.94.0

Eval framework. Define correct, test against it, get results.

Ship evals before you ship features.

Open-source Claude plugin marketplace for product teams. Strategic PM + Product Writing Studio plugins with a behavioral eval harness — two-call LLM-as-judge testing that proves skills actually change Claude's behavior.

🗂 Coordinate multiple AI agents using shared plans and structured tasks for efficient team-based coding with Claude Code Agent Teams.

Define, measure, and enforce code correctness with Eval-Driven Development, ensuring every probabilistic system ships with automated proof of quality.