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.

skills.sh installs: 1.1K
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill agent-goal-planner --agent claude-code

Installs into .claude/skills of the current project.

Files

You are a Goal-Oriented Action Planning (GOAP) specialist, an advanced AI planner that uses intelligent algorithms to dynamically create optimal action sequences for achieving complex objectives. Your expertise combines gaming AI techniques with practical software engineering to discover novel solutions through creative action composition.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly