360 Secure SkillHub
360 安全技能中心

mo-watchdog

仅当用户明确点名 mo-watchdog 或 Meta-O watchdog 时启用;以只读方式扫描或查看指定 Orca 会话,在获得精确目标授权且原生状态未变时发送提醒;异常或过期状态则安全失败并报告。

shkarupa-alex
热度 0.00
最近更新 2026-10-19 06:55:55
分类:自动化依赖:代码执行 / 读写文件 / 第三方 API应用场景:工作流 / 自动化脚本

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 shkarupa-alex/meta-o/mo-watchdog
Metadata
name
mo-watchdog
description
Use only when the user explicitly requests mo-watchdog or Meta-O watchdog; observe Orca sessions and nudge only an authorized exact target.
license
MIT
metadata
{"repository":"https://github.com/shkarupa-alex/meta-o","source_tree":"d126fa3b40691477444c271aa0d9d2c1bd8d43e8"}

Watch backend sessions

Read Watchdog behavior and Обратная связь о методологии completely; friction you hit belongs in your final answer to the user, never in an Issue. Start only after the user explicitly names Meta-O watchdog or mo-watchdog; a generic monitoring question does not activate this skill.

Use scripts/mo-watchdog.sh target --backend orca --session <id> for one session or scripts/mo-watchdog.sh scan for all reachable Orca sessions. Observation is read-only. An explicit nudge additionally requires --nudge <message> and exact target authorization; the script re-reads native state and suppresses the nudge when that state changed. It reserves a bounded private digest before delivery and suppresses the same message, an ambiguous attempt, or a saturated unchanged state across later invocations. Nudges return after native delivery; agent completion is observed separately.

Treat malformed or stale native state as a typed unsafe observation: report it, fail closed, and do not nudge or guess the target state.

Do not inspect tracked project content or private provider state. Report the native locator, classified state and action. Pattern misses are refined from observed failures rather than hidden behind a support claim.

Meta-O calls

  • none