360 Secure SkillHub
360 安全技能中心

Agent Oversight

该 Skill 通过运行 oversight.py 提供子代理会话监控(active/idle/hung)、文件编辑冲突协调、失败记录写入 learnings.md,并可自动终止超过 5 分钟无响应的会话;同时约定先读后改、oldText 精确匹配、单文件单代理等协调规则。

1477009639zw-blip
1477009639zw-blip
热度 47.49
最近更新 2026-05-11 17:38:03
分类:自动化依赖:代码执行 / 读写文件应用场景:自动化脚本 / 工作流 / DevOps / 任务管理

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add agent-oversight
Metadata
name
agent-oversight
description
Comprehensive AI agent oversight and management skill. Monitors sub-agents, manages file edit coordination, logs failures, kills hung sessions, and maintains oversight records.
metadata
{"openclaw":{"emoji":"🛡️","requires":{"bins":["python3"]},"always":false}}

Agent Oversight

Manages and monitors AI sub-agents. Keeps Beta's workspace clean, coordinated, and error-free.

Usage

python3 oversight.py --status
python3 oversight.py --list-sessions
python3 oversight.py --kill-hung

Features

  • Session monitoring (active/idle/hung)
  • File edit coordination (prevents conflicts)
  • Failure logging to memory/learnings.md
  • Automatic kill for >5min hung sessions
  • Coordination rules enforcement

Coordination Rules

  1. Read file before editing
  2. Exact oldText matching required
  3. One agent per file at a time
  4. Log all failures to learnings.md