Back to Details

loop-worker

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
Use 
/loop
for in-session periodic workers. Cache-aware delays keep prompt cache warm:
  • Delay formula: 
    min(270, cache_ttl * 0.9)
    -- default 270s
Dispatch a worker via MCP: 
mcp__claude-flow__hooks_worker-dispatch({ trigger: "WORKER_NAME" })
Then schedule the next iteration: 
ScheduleWakeup({ delaySeconds: 270, reason: "next WORKER_NAME iteration" })
使用
/loop
实现会话内周期性工作进程。缓存感知延迟可保持提示缓存处于活跃状态：
  • 延迟公式：
    min(270, cache_ttl * 0.9)
    -- 默认270秒
通过MCP调度工作进程：
mcp__claude-flow__hooks_worker-dispatch({ trigger: "WORKER_NAME" })
然后调度下一次迭代：
ScheduleWakeup({ delaySeconds: 270, reason: "next WORKER_NAME iteration" })

Available Workers

可用工作进程

WorkerIntervalDescription
audit270sSecurity analysis
optimize270sPerformance optimization
consolidate600sMemory consolidation
predict270sPredictive preloading
map600sCodebase mapping
testgaps270sTest coverage analysis
document600sAuto-documentation
benchmark600sPerformance benchmarking
MCP tool responses include 
[LOOP_SUGGESTION]
and 
[CRON_SUGGESTION]
hints -- follow them.
工作进程间隔描述
audit270秒安全分析
optimize270秒性能优化
consolidate600秒内存整合
predict270秒预测性预加载
map600秒代码库映射
testgaps270秒测试覆盖率分析
document600秒自动文档生成
benchmark600秒性能基准测试
MCP工具响应包含
[LOOP_SUGGESTION]
和
[CRON_SUGGESTION]
提示——请遵循这些提示。