← Back to Skills Marketplace
153
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install agent-comm-monitor
Description
监控牧者与其他 Agent 的通信状态，定期检测并报告跨 Agent 消息传递的正常与异常情况。
README (SKILL.md)
Agent 通信监控 Skill
简介
此 Skill 用于监控牧者（muzhe）与其他 Agent（司辰、采诗、格物、计相、蒙正）之间的通信状态，确保跨 Agent 消息传递正常，并定期向用户报告通信情况。
触发条件
当用户要求以下情况时使用：
- "检查 Agent 通信状态"
- "验证与 XX 的通信"
- "Agent 通信报告"
- "监控通信状态"
通信测试流程
1. 单向通信测试
使用 sessions_send 工具向目标 Agent 发送测试消息：
sessions_send(sessionKey="agent:{agent_name}:main", message="【牧者通信测试】这是一条验证消息，请回复确认。测试时间：{current_time}")
2. 响应判断
| 状态 | 含义 |
|---|---|
status: "ok" + 有 reply |
✅ 双向通信正常 |
status: "ok" + 无 reply |
⚠️ 单向通信正常，回复可能延迟 |
status: "timeout" |
❌ 通信异常 |
3. 备用验证
如果 sessions_send 返回超时，使用 sessions_history 检查目标 Agent 的会话历史，确认消息是否已送达。
Agent 列表
| Agent | Session Key | 主要职责 |
|---|---|---|
| 司辰 | agent:sichen:main | 日历日程管理 |
| 采诗 | agent:caishi:main | 前沿资讯追踪 |
| 格物 | agent:gewu:main | Agent 进化管理 |
| 计相 | agent:jixiang:main | 学习管理 |
| 蒙正 | agent:mengzheng:main | 孩子教育 |
报告格式
向用户报告时使用以下精简格式：
📊 Agent 通信状态报告
| Agent | 状态 | 响应时间 |
|-------|------|----------|
| 司辰 | ✅ 正常 | \x3C1s |
| 采诗 | ✅ 正常 | \x3C1s |
| 格物 | ✅ 正常 | \x3C1s |
| 计相 | ⚠️ 待测 | - |
| 蒙正 | ✅ 正常 | \x3C1s |
🕐 检测时间：12:24
注意事项
- 异步延迟：跨 Agent 消息可能存在 1-3 秒的异步延迟
- 超时容忍：如果
sessions_send超时，等待 5 秒后重新检查会话历史 - 精简报告：向用户报告时使用表格形式，保持简洁
- 异常记录：如果发现异常，记录到 MEMORY.md 中
紧急异常处理
如果某个 Agent 连续 3 次通信失败：
- 记录到 HEARTBEAT.md 的异常日志中
- 在下次 heartbeat 时提醒用户
- 建议用户检查该 Agent 的运行状态
Usage Guidance
This skill appears to do what it says: send test messages, check session history, and produce a report. Before installing, confirm you are comfortable with the agent having access to sessions_send/sessions_history and with the skill writing log entries to MEMORY.md and HEARTBEAT.md (these may contain message contents). Consider: run it with explicit invocation only if you want to avoid automatic monitoring; verify where those log files are stored and how long they are retained; redact or avoid logging sensitive message content; and test in a non-production environment first. If you need stronger guarantees, ask the skill author how logs are protected and whether logs are shared externally.
Capability Analysis
Type: OpenClaw Skill
Name: agent-comm-monitor
Version: 1.0.0
The agent-comm-monitor skill is designed to verify communication status between different internal agents (e.g., Sichen, Caishi) using standard session management tools. The instructions in SKILL.md are well-defined, focusing on connectivity testing and status reporting without any evidence of malicious intent, data exfiltration, or unauthorized command execution.
Capability Assessment
Purpose & Capability
Name/description match the instructions: the SKILL.md calls the platform session APIs (sessions_send, sessions_history) and targets specific agent session keys to test and report cross-agent messaging — this is proportional to a communication-monitoring skill.
Instruction Scope
Instructions stay on-topic (send test messages, check session history, interpret replies). They also instruct the agent to write anomalies to MEMORY.md and HEARTBEAT.md; reading session histories and persisting logs is expected for monitoring but has privacy implications because it accesses message contents and creates persistent records.
Install Mechanism
No install spec and no code files — instruction-only behavior is low-risk from an installation perspective (nothing is downloaded or written to disk by an installer).
Credentials
The skill requests no environment variables or external credentials. Its operational needs (access to sessions_* APIs and the agent workspace) are appropriate for its stated purpose.
Persistence & Privilege
always is false and the skill is not force-included. However, it explicitly directs writing to MEMORY.md and HEARTBEAT.md (persistent workspace files) and recommends logging after repeated failures — this grants it the ability to create/modify local logs which the user should be aware of.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-comm-monitor - After installation, invoke the skill by name or use
/agent-comm-monitor - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
agent-comm-monitor 1.0.0
- Initial release: provides status monitoring between muzhe and other Agents to ensure message delivery.
- Supports testing and verifying both one-way and two-way communication with detailed status logic.
- Reports summarized results to users in a concise table format.
- Includes fallback mechanisms for communication timeouts by inspecting session histories.
- Logs abnormalities and triggers emergency handling after repeated failures, with guidance for follow-up.
Metadata
Frequently Asked Questions
What is Agent Comm Monitor?
监控牧者与其他 Agent 的通信状态，定期检测并报告跨 Agent 消息传递的正常与异常情况。 It is an AI Agent Skill for Claude Code / OpenClaw, with 153 downloads so far.
How do I install Agent Comm Monitor?
Run "/install agent-comm-monitor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Agent Comm Monitor free?
Yes, Agent Comm Monitor is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Agent Comm Monitor support?
Agent Comm Monitor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Agent Comm Monitor?
It is built and maintained by nancliu (@nancliu); the current version is v1.0.0.
More Skills