intelligence-route

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Intelligence Routing

智能路由

Route tasks to the best agent and model based on learned patterns.

基于学习到的模式将任务分配给最佳Agent和模型。

When to use

使用场景

Before starting any task, use intelligence routing to get the optimal agent type, model tier, and confidence score. This replaces manual agent selection with data-driven decisions.

在启动任何任务之前，使用智能路由获取最优Agent类型、模型层级和置信度评分。这将以数据驱动的决策替代手动选择Agent的方式。

Steps

步骤

Get routing recommendation — call
```
mcp__claude-flow__hooks_route
```
with the task description
Check model recommendation — call
```
mcp__claude-flow__hooks_model-route
```
for the optimal model tier (Haiku/Sonnet/Opus)
Search for similar patterns — call
```
mcp__claude-flow__hooks_intelligence_pattern-search
```
to find past successes
Predict outcome — call
```
mcp__claude-flow__neural_predict
```
with the task description
Spawn the recommended agent at the recommended model tier
Record outcome — after task completes, call
```
mcp__claude-flow__hooks_model-outcome
```
to train the router

获取路由推荐 — 调用
```
mcp__claude-flow__hooks_route
```
并传入任务描述
查看模型推荐 — 调用
```
mcp__claude-flow__hooks_model-route
```
获取最优模型层级（Haiku/Sonnet/Opus）
搜索相似模式 — 调用
```
mcp__claude-flow__hooks_intelligence_pattern-search
```
查找过往成功案例
预测结果 — 调用
```
mcp__claude-flow__neural_predict
```
并传入任务描述
启动推荐的Agent — 使用推荐的模型层级
记录结果 — 任务完成后，调用
```
mcp__claude-flow__hooks_model-outcome
```
来训练路由系统

3-Tier Model Routing

三层模型路由

Tier	Handler	When
1	Agent Booster (WASM)	Simple transforms — skip LLM entirely
2	Haiku	Low complexity tasks (<30%)
3	Sonnet/Opus	Complex reasoning, architecture, security

层级	处理器	使用场景
1	Agent Booster (WASM)	简单转换操作 — 完全跳过LLM
2	Haiku	低复杂度任务（<30%）
3	Sonnet/Opus	复杂推理、架构设计、安全相关任务

CLI alternative

CLI替代方案

bash

npx @claude-flow/cli@latest hooks route --task "description"
npx @claude-flow/cli@latest hooks pre-task --description "description"
npx @claude-flow/cli@latest hooks explain --topic "routing decision"

bash

npx @claude-flow/cli@latest hooks route --task "description"
npx @claude-flow/cli@latest hooks pre-task --description "description"
npx @claude-flow/cli@latest hooks explain --topic "routing decision"

Viewing intelligence stats

查看智能统计数据

Call

mcp__claude-flow__hooks_intelligence_stats

or:

bash

npx @claude-flow/cli@latest hooks intelligence stats

调用

mcp__claude-flow__hooks_intelligence_stats

或：

bash

npx @claude-flow/cli@latest hooks intelligence stats