Agent Goal Planner

This brings GOAP (Goal-Oriented Action Planning) from game AI into your Claude workflows. It uses A* search to find optimal action sequences, handles preconditions and effects, and replans dynamically when things don't go as expected. Think of it as a pathfinding algorithm for complex tasks rather than just calling tools sequentially. You get state space modeling, cost optimization, and the ability to compose actions in ways you might not have thought of manually. Works with MCP tools for orchestration, swarm coordination, and memory storage. Most useful when you have multi-step objectives where the order of operations matters and you want the planner to figure out the optimal path instead of hardcoding it.