autopilot-loop

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

Run one autopilot iteration using Claude Code's native /loop:

Check status:
```
mcp__claude-flow__autopilot_status
```
If all tasks complete or max iterations reached, call
```
mcp__claude-flow__autopilot_disable
```
and stop
Get prediction:
```
mcp__claude-flow__autopilot_predict
```
for the optimal next action
Execute the predicted task (spawn agent, edit code, run tests, etc.)
Log via
```
mcp__claude-flow__autopilot_log
```

Schedule next:

ScheduleWakeup({ delaySeconds: 270, reason: "next autopilot iteration" })

使用Claude Code原生的/loop运行一次自动驾驶迭代：

安排下一次迭代：

ScheduleWakeup({ delaySeconds: 270, reason: "next autopilot iteration" })

Always use delay 270s (under 300s cache TTL) to keep the prompt cache warm between iterations.

始终使用270秒的延迟（低于300秒的缓存TTL），以在迭代之间保持提示缓存的热度。

Autopilot discovers tasks from:

Configure:

mcp__claude-flow__autopilot_config({ taskSources: ["team-tasks", "swarm-tasks"] })

自动驾驶功能从以下来源发现任务：

配置方式：

mcp__claude-flow__autopilot_config({ taskSources: ["team-tasks", "swarm-tasks"] })