跳到正文
cccskills
免费在 GitHub 公开

agent-observe

Read-only observation of an agent's parent, siblings, and direct children. Use to inspect family status and bounded recent-message previews without mutating sessions.

中文简介正在准备中。当前显示原文说明。

karanmrn/karanagentskills星标 4(GitHub 4 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(3)

  • SKILL.md2.3 KB
  • pyproject.toml335 B
  • src/agent_observe/__init__.py1.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Agent Observe

Observe the current agent's nuclear family through the local daemon: parent, siblings, direct children, and self. Observation is currently limited to family members in the same worker; root siblings in other workers are not observable yet. This skill is read-only: it can list family sessions, inspect one session, and fetch bounded recent message previews. It cannot prompt, steer, clear, kill, rename, or otherwise mutate another session.

Call directly from the kernel:

children = await rlm.list_subagents()
child = next((item for item in children if item.active_session_id), None)
if child is not None:
    worker = await agent_observe.get_agent(child.session_name)
    recent = await agent_observe.recent_messages(child.session_name, limit=6)
    # Deletion is a parent-owned RLM operation, not an observe mutation:
    await rlm.delete_subagent(child)

API

  • await agent_observe.list_agents() returns current and agents. Each agent includes active session id, session id, optional name, runtime kind, cwd, status, streaming state, message count, pending count, and a latest message preview. The list is restricted to self, parent, siblings, and direct children. For direct children, await rlm.list_subagents() also exposes parent-owned lifecycle handles.
  • await agent_observe.get_agent(target) returns agent, where agent contains one agent summary. target is resolved like other live-session selectors: active id, session id/name, or unambiguous suffix.
  • await agent_observe.recent_messages(target, limit=8, max_chars=800) returns up to limit recent bounded message previews for the target session. limit must be 1-50, and max_chars must be 80-2000.

Safety

  • This skill is read-only and exposes no mutation commands.
  • Targets outside the nuclear family are rejected; transcript reads follow the same family rule as messaging.
  • Message access is bounded by count and per-message character limit.
  • Prefer status and recent previews for orchestration. Ask the user before using observed context to steer or message another session.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.

中文简介正在准备中。当前显示原文说明。

karanmrn/karanagentskills42026年8月28日 更新

Automate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.

中文简介正在准备中。当前显示原文说明。

karanmrn/karanagentskills42026年8月28日 更新

1password

免费

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

中文简介正在准备中。当前显示原文说明。

karanmrn/karanagentskills42026年8月28日 更新

Build integrated IS/BS/CF financial workbooks in Excel.

中文简介正在准备中。当前显示原文说明。

karanmrn/karanagentskills42026年8月28日 更新

9router

免费

Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTER_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability SKILL.md from the URLs below when needed.

中文简介正在准备中。当前显示原文说明。

karanmrn/karanagentskills42026年8月28日 更新

Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.

中文简介正在准备中。当前显示原文说明。

karanmrn/karanagentskills42026年8月28日 更新

查看 karanmrn 的全部技能

报告此技能的问题