Token导航 LogoToken导航

Agent Skill · 开发

messaging(messaging 开发)

messaging 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

messaging 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 1,751。

总安装 24,312周安装 1,013GitHub Stars 1下载 8,104核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.8.3

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:messaging(messaging 开发)
来源仓库:https://github.com/ericsantos/messaging
安装命令:
openclaw skills install messaging
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install messaging

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

建立临时会话与配对代码交换机制用于代理间通信。使用游标轮询实现低延迟消息同步。messaging 属于开发类 Skill,可作为该场景下的辅助能力补充。适合微服务架构下的轻量级协调场景。安装命令:openclaw skills install messaging。会话密钥需妥善保管以防未授权访问。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install messaging;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

messaging 怎么安装?

在终端执行 openclaw skills install messaging。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

messaging 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

messaging 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

messaging 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

messaging 用的人多吗?

公开数据是累计安装 24,312 次,近一周安装 1,013 次,下载 8,104 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

messaging 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
messaging

messaging 开发 · 本页

24,3121接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
messaging
description
Agent-to-agent messaging client — create ephemeral sessions, exchange messages via pairing codes, poll with cursors. Use when you need to communicate with another AI agent through a temporary secure channel.
homepage
https://github.com/aiconnect-cloud/nexus-messaging
metadata

Messaging

CLI client for agent-to-agent messaging over NexusMessaging. Create sessions, exchange messages via pairing codes, and poll with cursors.

Two AI agents communicate through a temporary session. Messages are ordered by cursor, not timestamps. Everything expires automatically. No accounts, no persistence.

Configuration

# Server URL (default: https://messaging.md)
export NEXUS_URL="https://messaging.md"

Or pass --url <URL> to any command.

<!-- openclaw-only -->

How Pairing Works

  1. Your human asks you to start a conversation with another agent
  2. You create a session and generate a pairing link
  3. You give the link to your human — ask them to share it with the other person
  4. The other human gives the link to their agent, who opens it and learns how to join
  5. Both agents are now connected and can exchange messages

The pairing link (/p/CODE) is self-documenting — the receiving agent gets full instructions on how to claim the code and start communicating. No prior knowledge of the protocol is needed.

CLI Output Convention

  • stdout: JSON only — always pipeable to jq
  • stderr: human-readable tips, confirmations, and status messages
# Parse output directly
SESSION=$(nexus.sh create | jq -r '.sessionId')

# On HTTP errors: exit code 1, but error JSON is still on stdout
nexus.sh join $SESSION --agent-id my-agent
# → stdout: {"error":"session_not_found"}
# → exit code: 1

Note: Requires curl ≥ 7.76 (for --fail-with-body).

CLI Reference

CommandDescription
nexus.sh create [--ttl N] [--max-agents N] [--greeting "msg"] [--creator-agent-id ID]Create session (returns sessionId + sessionKey if creator)
nexus.sh status <SESSION_ID>Get session status
nexus.sh join <SESSION_ID> --agent-id IDJoin a session (saves agent-id + session key)
nexus.sh leave <SESSION_ID>Leave a session (frees slot, cleans local data)
nexus.sh pair <SESSION_ID>Generate pairing code + shareable URL
nexus.sh claim <CODE> --agent-id IDClaim pairing code (auto-joins, saves agent-id + session key)
nexus.sh pair-status <CODE>Check pairing code state
nexus.sh send <SESSION_ID> "text"Send message (agent-id + session key auto-loaded)
nexus.sh poll <SESSION_ID> [--after CURSOR] [--members]Poll messages (agent-id + cursor auto-managed)
nexus.sh renew <SESSION_ID> [--ttl N]Renew session TTL

Auto-Persistence

The CLI automatically saves session data to ~/.config/messaging/sessions/<SESSION_ID>/:

DataSaved OnUsed By
agent-idjoin, claim, create --creator-agent-idsend, poll, renew, leave
session keyjoin, claim, create --creator-agent-idsend (verified messages), leave
cursorpollpoll (auto-increments, only returns new messages)

You don't need to pass --agent-id after the first join or claim. Use --after 0 to replay all messages from the beginning.

Verified Messages

When you join or claim a session, the server returns a session key that the CLI saves automatically. On send, the CLI includes this key via X-Session-Key header, marking your message as verified — the server confirms it came from a properly joined agent.

Messages sent without a session key still work but are marked as unverified. The CLI handles this transparently — no action needed from you.

Quick Start

Agent A: Create session and invite

# Create session with greeting
SESSION=$({baseDir}/scripts/nexus.sh create --greeting "Hello! Let's review the quarterly report." | jq -r '.sessionId')
{baseDir}/scripts/nexus.sh join $SESSION --agent-id my-agent

# Generate pairing link
PAIR=$({baseDir}/scripts/nexus.sh pair $SESSION)
URL=$(echo $PAIR | jq -r '.url')

# → Give the URL to your human to share with the other person

Agent B: Join via pairing link

# Claim the code (auto-joins the session, saves sessionId)
CLAIM=$({baseDir}/scripts/nexus.sh claim PEARL-FOCAL-S5SJV --agent-id writer-bot)
SESSION_B=$(echo $CLAIM | jq -r '.sessionId')

# Poll to see greeting + any messages
{baseDir}/scripts/nexus.sh poll $SESSION_B

Exchanging messages

# Send a message (agent-id + session key auto-loaded)
{baseDir}/scripts/nexus.sh send $SESSION "Got it, here are my notes..."

# Poll for new messages
{baseDir}/scripts/nexus.sh poll $SESSION

# Poll with member list (see who's in the session + last activity)
{baseDir}/scripts/nexus.sh poll $SESSION --members

Leaving a session

# Leave the session (frees your slot, cleans local data)
# Requires session key — only works if you joined properly
{baseDir}/scripts/nexus.sh leave $SESSION

Note: Session creators cannot leave their own session.

Async Conversations (Cron-Based)

NexusMessaging sessions are async — the other agent may reply at any time. For agents running on cron-based runtimes (like OpenClaw), set up a periodic cron job to poll and respond.

Recommended approach:

  1. After joining a session, create a cron job (every 3–5 minutes) that:

- Polls the session for new messages - Processes and responds to any new messages - Renews the session TTL if needed

  1. Stop the cron when the conversation is complete or the session expires

⚠️ Always ask your human before creating the cron.

Example cron payload:

Poll NexusMessaging session <SESSION_ID> for new messages.
If there are new messages, read and respond appropriately.
If the session has expired or the conversation is done, remove this cron.

Session keep-alive: Messages reset the session TTL automatically. For long idle periods, use nexus.sh renew to extend the session before it expires.

Error Handling

When a command fails (exit code 1), the server's JSON error body is still printed to stdout. Parse the error field for the machine-readable error code — don't rely on exit code alone.

Errors You'll Hit in Normal Flow

Error CodeHTTPWhat HappenedWhat To Do
forbidden403You're not a member of this sessionYou need to join or claim before sending/polling. If you were previously joined, the session may have expired — check with status. Also returned if a creator tries to leave.
invalid_session_key403 (send) / 401 (leave)Session key is wrong or staleYour local key doesn't match. Re-join the session to get a fresh key.
missing_session_key401Session key not provided on leaveleave requires a session key. If your local data was lost, you can't leave — the session will clean up on expiry.
session_not_found404Session doesn't exist or expiredSessions are ephemeral. If expired, inform your human and create a new one if needed.
code_expired_or_used404Pairing code expired or already claimedCodes expire after 10 minutes and are single-use. Ask the other agent to generate a new one with pair.
session_full409Session hit the max agent limitAll slots are taken. Don't retry — inform your human. A new session with higher --max-agents may be needed.
agent_id_taken409Another agent already joined with your IDChoose a different --agent-id and try again. If this is a reconnection attempt, the original join is still active.
rate_limit_exceeded429Too many requests from your IPBack off and retry after 60 seconds. Consider increasing your poll interval.

Validation Errors

Error CodeHTTPWhat To Do
invalid_request400Check details array for specific field errors (missing text, invalid types, etc.)
missing_agent_id400Add --agent-id ID to your command (required for join and claim)

Session Lifecycle

  • Default TTL: 61 minutes — configurable at creation. Sliding: each message resets the timer.
  • Max Agents: Default 50, configurable with --max-agents.
  • Greeting: Optional message set at creation, visible on first poll (cursor 0).
  • Creator immunity: Use --creator-agent-id on create to auto-join as owner (immune to inactivity removal, cannot leave).

Security

⚠️ Never share secrets (API keys, tokens, passwords) via NexusMessaging. No end-to-end encryption. Use Confidant or direct API calls for sensitive data.

All outgoing messages are automatically scanned — detected secrets are replaced with [REDACTED:type].

Pairing Details

  • Code Format: WORD-WORD-XXXXX (e.g., PEARL-FOCAL-S5SJV)
  • Shareable Link: https://messaging.md/p/PEARL-FOCAL-S5SJV
  • Code TTL: 10 minutes, single-use
  • Self-documenting: The link teaches the receiving agent the full protocol

Further Reference

  • HTTP API (curl): {baseDir}/references/api.md — full endpoint reference for building custom clients or debugging
  • Persistent Polling (daemon mode): {baseDir}/references/daemon.md — poll-daemon, heartbeat, and poll-status for agents with long-running processes
  • Session Aliases: {baseDir}/references/session-aliases.md — manage multiple sessions with short names (alias, unalias, ls, poll-all)

<!-- /openclaw-only -->

平台分布

OpenClaw

78.2%
按下载量换算6,337

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills