Skip to content

A local-first multi-agent app development platform, built on PenguinHarness

848 B
Raw Blame
{
  "description": "Continual learning: a stop hook that, when the task that just ended ran more than 30 completed turns, hands a condensed excerpt of that task to a background subagent, which folds the durable findings into the agent's own skills.",
  "description_zh": "持续学习:一个 stop hook,刚结束的任务跑了超过 30 个完成的轮次时,就把该任务的浓缩摘录交给一个后台子会话,由它把值得沉淀的发现写进 Agent 自己的 Skill。",
  "short_description": "Fold a long task's findings back into the agent's skills.",
  "short_description_zh": "把长任务的发现回流进 Agent 的 Skill。",
  "version": "2026.09.29.1",
  "category": "office-productivity",
  "preinstall": false,
  "hooks": {
    "stop": [
      {
        "command": "stop.mjs",
        "timeout": 60
      }
    ]
  }
}