Define goal state — what does "done" look like? List concrete success criteria
Assess current state — what's true now? What assets, code, infrastructure exist?
Identify gap — what must change between current and goal state?
Inventory actions — list available actions with:
- Preconditions (what must be true before this action)
- Effects (what becomes true after this action)
- Cost estimate (time, complexity, risk)
Generate plan — find the optimal action sequence using A* through the state space
Record trajectory — call mcp__claude-flow__hooks_intelligence_trajectory-start to begin tracking
Create tasks — call mcp__claude-flow__task_create for each action in the plan
Execute — work through tasks in dependency order:
- Before each action: verify preconditions still hold
- After each action: verify effects achieved
- Record each step via mcp__claude-flow__hooks_intelligence_trajectory-step
Monitor & replan — if an action fails or produces unexpected results:
- Reassess current state
- Recalculate optimal path from new state
- Update remaining tasks
Complete trajectory — call mcp__claude-flow__hooks_intelligence_trajectory-end
Store successful plan — call mcp__claude-flow__memory_store with namespace goap-plans

Plan output format

Goal: [concrete objective]
Current State: [key facts]
Plan Cost: [estimated effort]
Steps:
  1. [action] — precondition: [X], effect: [Y], cost: [Z]
  2. [action] — precondition: [Y], effect: [W], cost: [Z]
  ...
Risk Factors: [what could force a replan]
Fallback: [alternative approach if primary path fails]

Replanning triggers

Action fails (precondition no longer met)
Unexpected side effects detected
New information changes goal definition
Cost exceeds threshold
External dependency becomes unavailable

goal-plan

Goal Plan

When to use

Steps