Agent Self-Care
Autonomous health monitoring and optimization for OpenClaw agents. Runs on cron or triggers manually.
Workflow
1. Check Sub-Agents
CODEBLOCK0
Kill any stale sub-agents:
- - Running >30 min without progress
- In "waiting" state
- Failed/errored
2. Check Processes
CODEBLOCK1
Kill hanging processes:
- - Running >10 min in background
- No output in 5 min
3. Check Session Health
CODEBLOCK2
Metrics to watch:
- - Context usage >80% → trigger compaction
- Tokens growing unbounded
- Session age >2 hours → suggest refresh
4. Run Optimization Script
Execute scripts/optimize.sh which:
- - Clears completed cron job artifacts
- Rotates logs if >50MB
- Reports health metrics
5. BMAD Retrospective (every 10 runs)
After 10 executions, run:
- - Score last task 1-10
- Identify gaps
- Document improvements in INLINECODE1
- Feed learnings into next run
Cron Schedule
Recommended: Every 5 minutes for active agents.
CODEBLOCK3
Output Format
Report after each run:
CODEBLOCK4
Key Principles
- 1. Always clean - Never leave stalled sub-agents or processes
- Proactive - Don't wait for user to ask
- Document - Log issues and improvements
- BMAD - Continuous self-evaluation every 10 runs
- Fast - Complete in <30 seconds
代理自我维护
针对OpenClaw代理的自主健康监控与优化。通过定时任务运行或手动触发。
工作流程
1. 检查子代理
bash
subagents action=list
终止所有失效子代理：
- - 运行超过30分钟且无进展
- 处于等待状态
- 失败/报错
2. 检查进程
bash
process action=list
终止挂起进程：
3. 检查会话健康状态
bash
session_status
监控指标：
- - 上下文使用率>80% → 触发压缩
- Token无限增长
- 会话时长超过2小时 → 建议刷新
4. 运行优化脚本
执行scripts/optimize.sh脚本，该脚本将：
- - 清理已完成定时任务的工作产物
- 日志超过50MB时进行轮转
- 报告健康指标
5. BMAD回顾（每10次运行）
每执行10次后，运行：
- - 对上次任务评分1-10分
- 识别差距
- 在memory/daily/YYYY-MM-DD.md中记录改进方案
- 将经验反馈至下次运行
定时任务计划
建议：活跃代理每5分钟执行一次。
json
{
name: agent-self-care,
schedule: {kind: every, everyMs: 300000},
payload: {kind: agentTurn, message: Run agent-self-care skill},
sessionTarget: isolated,
enabled: true
}
输出格式
每次运行后报告：
🔧 自我维护报告
- - 子代理：X活跃，Y已终止
- 进程：X运行中，Y已清理
- 上下文：X%已使用
- 健康状态：✅ 良好 / ⚠️ 警告
- 回顾：已跳过 / 已完成
核心原则
- 1. 始终清理 - 绝不遗留停滞的子代理或进程
- 主动出击 - 无需等待用户请求
- 记录归档 - 记录问题和改进方案
- BMAD - 每10次运行进行持续自我评估
- 高效执行 - 30秒内完成
