goal-plan

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Goal Plan

目标计划

Create and execute intelligent plans using Goal-Oriented Action Planning (GOAP).

使用目标导向行动计划（GOAP）创建并执行智能计划。

When to use

适用场景

When you have a complex objective that requires multiple steps, has dependencies between steps, and may need adaptive replanning as conditions change.

当你有一个复杂目标，需要多个步骤、步骤间存在依赖关系，且可能需要根据条件变化进行自适应重规划时。

Steps

步骤

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
```

定义目标状态 — “完成”是什么样子？列出具体的成功标准
评估当前状态 — 目前的实际情况是什么？已有的资产、代码、基础设施有哪些？
识别差距 — 当前状态与目标状态之间需要做出哪些改变？
盘点可用行动 — 列出所有可用行动，包含：
- 前置条件（执行此行动前必须满足的条件）
- 效果（执行此行动后会达成的结果）
- 成本估算（时间、复杂度、风险）
生成计划 — 通过状态空间中的A*算法找到最优行动序列

记录轨迹 — 调用

mcp__claude-flow__hooks_intelligence_trajectory-start

开始追踪

创建任务 — 为计划中的每个行动调用
```
mcp__claude-flow__task_create
```
执行计划 — 按照依赖顺序完成任务：
- 执行每个行动前：验证前置条件是否仍然满足
- 执行每个行动后：验证是否达成预期效果
- 通过
```
mcp__claude-flow__hooks_intelligence_trajectory-step
```
  记录每个步骤
监控与重规划 — 如果某个行动失败或产生意外结果：
- 重新评估当前状态
- 从新状态重新计算最优路径
- 更新剩余任务

完成轨迹记录 — 调用

mcp__claude-flow__hooks_intelligence_trajectory-end

存储成功计划 — 使用命名空间
```
goap-plans
```
调用
```
mcp__claude-flow__memory_store
```

Plan output format

计划输出格式

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]

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

重规划触发条件

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

行动失败（前置条件不再满足）
检测到意外副作用
新信息改变了目标定义
成本超出阈值
外部依赖不可用