comeonoliver/skillshub/ai-maestro-agent-messaging

Claude Code and agent skill by comeonoliver/skillshub

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Send and receive messages between AI agents using AI Maestro's messaging system. Use this skill when the user asks to "send a message", "check inbox", "read messages", "notify [agent]", "tell [agent]", or any inter-agent communication.

Install

npx vskill@latest install comeonoliver/skillshub/ai-maestro-agent-messaging

SKILL.md

AI Maestro Agent Messaging

Purpose

Enable communication between AI coding agents using AI Maestro's dual-channel messaging system. Agents are identified by their agent ID or alias, with tmux session names as a fallback. Supports both SENDING and RECEIVING messages.

CRITICAL: Inter-Agent Communication

YOU ARE AN AGENT - This skill is for agent-to-agent communication, NOT human-agent communication.

IMPORTANT: Understanding "Your Messages"

When the human operator says "check your messages" or "read your messages":

  • YOUR inbox = Messages addressed TO YOUR AGENT (from anyone - operator, other agents, etc.)
  • NOT the operator's inbox = You check YOUR inbox, not the operator's

Example:

  • Human says: "Check your messages"
  • You are agent: backend-api
  • You check: ~/.aimaestro/messages/inbox/backend-api/ (YOUR inbox)
  • These are messages addressed TO backend-api (from any sender)
  • You DO NOT check: The operator's inbox or any other agent's inbox
Agent Identity
  • Your inbox = Messages addressed TO YOUR AGENT (from any sender)
  • Your agent ID = Unique identifier for this agent (can also use agent name as fallback)
  • Your agent name = The tmux session you're running in (get with tmux display-message -p '#S')
  • Your inbox location = ~/.aimaestro/messages/inbox/YOUR-AGENT-ID/ or ~/.aimaestro/messages/inbox/YOUR-AGENT-NAME/

You do NOT read:

  • ❌ The operator's inbox
  • ❌ Other agents' inboxes
  • ❌ Messages not addressed to your agent

You DO read:

  • ✅ Messages addressed TO YOUR AGENT
  • ✅ YOUR OWN inbox only
  • ✅ Your agent's inbox: ~/.aimaestro/messages/inbox/YOUR-AGENT-ID/

When to Use This Skill

Sending (Agent-to-Agent):

  • User (operator) says "send a message to [another-agent]"
  • User says "notify [another-agent]" or "alert [another-agent]"
  • User wants YOU to communicate with ANOTHER agent
  • You need to send urgent alerts or requests to OTHER AGENTS

Receiving (Check YOUR OWN Inbox):

  • User says "check my inbox" or "check my messages" = Use check-aimaestro-messages.sh
  • User says "read my messages" or "read message X" = Use read-aimaestro-message.sh <id>
  • User asks "any new messages?" = Use check-aimaestro-messages.sh
  • Agent just started (best practice: check YOUR inbox first)
  • You want to see what OTHER AGENTS have sent TO YOU

RECOMMENDED WORKFLOW:

  1. First check for unread messages: check-aimaestro-messages.sh
  2. Then read specific message: read-aimaestro-message.sh <message-id>
  3. Message is automatically marked as read after reading

Available Tools

PART 1: RECEIVING MESSAGES (YOUR OWN INBOX)

📖 QUICK START - Check and Read Messages:

bash
# Step 1: Check what unread messages you have
check-aimaestro-messages.sh
# Output shows:
# [msg-1234...] 🔴 From: backend-api | 2025-10-29 14:30
# Subject: Authentication endpoint ready
# Preview: The /api/auth/login endpoint is now...
# Step 2: Read the specific message (automatically marks as read)
read-aimaestro-message.sh msg-1234...
# Step 3: Check again - that message is now gone from unread
check-aimaestro-messages.sh
# Output: "📭 No unread messages"

⚠️ CRITICAL: What "YOUR inbox" means:

  • YOU = The AI agent running in this tmux session
  • YOUR inbox = ~/.aimaestro/messages/inbox/YOUR-AGENT-ID/ (or agent name as fallback)
  • Messages in YOUR inbox = Messages OTHER AGENTS sent TO YOU
  • NOT the operator's messages, NOT other agents' private messages

IMPORTANT: These commands check YOUR AGENT'S inbox only. They automatically:

  1. Detect your current agent ID or agent name
  2. Read from ~/.aimaestro/messages/inbox/YOUR-AGENT-ID/
  3. Show messages that OTHER AGENTS sent TO YOU
  4. Do NOT access anyone else's inbox
1. Check YOUR Inbox for UNREAD Messages (Recommended)

Command:

bash
check-aimaestro-messages.sh [--mark-read]

What it does:

  • Shows ONLY UNREAD messages in YOUR inbox (messages sent TO YOUR AGENT)
  • Automatically detects YOUR agent's session
  • Displays: priority indicator, sender, subject, preview, timestamp
  • Optional --mark-read flag to mark all messages as read after viewing
  • This is the recommended way to check messages - avoids re-reading old messages

Example:

bash
# Check unread messages without marking as read
check-aimaestro-messages.sh
# Check and mark all as read
check-aimaestro-messages.sh --mark-read

Output format:

📬 You have 3 unread message(s)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
[msg-167...] 🔴 From: backend-architect | 2025-10-29 13:45
Subject: API endpoint ready
Preview: The POST /api/auth/login endpoint is now...
[msg-168...] 🔵 From: frontend-dev | 2025-10-29 14:20
Subject: Need help with styling
Preview: Can you review the CSS for the navigation...
2. Read Specific Message and Mark as Read

Command:

bash
read-aimaestro-message.sh <message-id> [--no-mark-read]

What it does:

  • Retrieves and displays the full message content
  • Automatically marks the message as read (unless --no-mark-read flag)
  • Shows all message details: content, context, forwarding info
  • Perfect for reading a specific message after checking the list

Example:

bash
# Read message (automatically marks as read)
read-aimaestro-message.sh msg-1234567890-abc
# Peek at message without marking as read
read-aimaestro-message.sh msg-1234567890-abc --no-mark-read

Output format:

═══════════════════════════════════════════════════════════════
📧 Message: API endpoint ready
═══════════════════════════════════════════════════════════════
From: backend-architect
To: frontend-dev
Date: 2025-10-29 13:45:00
Priority: 🔴 urgent
Type: response
───────────────────────────────────────────────────────────────
The POST /api/auth/login endpoint is now deployed and ready...
───────────────────────────────────────────────────────────────
📎 Context:
{
"endpoint": "/api/auth/login"
}
✅ Message marked as read
═══════════════════════════════════════════════════════════════
3. Auto-Display on Agent Start (Legacy - DO NOT USE MANUALLY)

Command:

bash
check-and-show-messages.sh

What it does:

  • Automatically runs when you attach to a tmux session
  • Shows a summary of unread messages
  • DO NOT run this command manually - it's for auto-display only
  • For manual checking, use `check-aimaestro-messages.sh` instead

Why not use this manually?

  • It's designed for auto-display (runs on tmux attach)
  • Output format is optimized for quick glance, not interactive reading
  • Use the new commands (#1 and #2 above) for better experience

Output format:

Message: msg_1234567890_abcde
From: backend-architect ← Another agent sent this TO YOU
To: frontend-dev ← YOUR session name
Subject: Need API endpoint
Priority: high
Type: request
Status: unread
Timestamp: 2025-01-17 14:23:45
Content: Please implement POST /api/users with pagination...
4. Check for New Messages Count (Quick)

Command:

bash
check-new-messages-arrived.sh

What it does:

  • Shows count of unread messages in YOUR inbox
  • Automatically checks YOUR session's inbox
  • Quick check without full details
  • Returns "No new messages" or "You have X new message(s)"

Example:

bash
check-new-messages-arrived.sh
# Output: "You have 3 new message(s)" ← Messages sent TO YOU
5. Read Specific Message FROM YOUR Inbox (Direct File Access - Advanced)

Command:

bash
cat ~/.aimaestro/messages/inbox/$(tmux display-message -p '#S')/<message-id>.json | jq

What it does:

  • Read a specific message file from YOUR inbox
  • $(tmux display-message -p '#S') = YOUR session name (auto-detected)
  • Use jq for pretty formatting
  • Useful when you know the message ID

Directory structure:

~/.aimaestro/messages/
├── inbox/YOUR-SESSION-NAME/ # Messages TO YOU from other agents
│ └── msg_*.json
├── sent/YOUR-SESSION-NAME/ # Messages FROM YOU to other agents
│ └── msg_*.json
└── archived/YOUR-SESSION-NAME/ # YOUR archived messages
└── msg_*.json

Example:

bash
# Get YOUR session name
tmux display-message -p '#S'
# Output: frontend-dev ← This is YOU
# List all messages in YOUR inbox
ls ~/.aimaestro/messages/inbox/$(tmux display-message -p '#S')/
# Read specific message sent TO YOU
cat ~/.aimaestro/messages/inbox/$(tmux display-message -p '#S')/msg_1234567890_abcde.json | jq
4. Mark Message as Read (via API)

Command:

bash
# Get current session name
SESSION_NAME=$(tmux display-message -p '#S')
# Mark message as read
curl -X PATCH "http://localhost:23000/api/messages?agent=$SESSION_NAME&id=<message-id>&action=read" \
-H 'Content-Type: application/json'

PART 2: SENDING MESSAGES (TO OTHER AGENTS)

⚠️ CRITICAL: What "sending a message" means:

  • Operator tells YOU to send a message TO ANOTHER AGENT
  • NOT sending messages to the operator
  • Message goes to ANOTHER AGENT's inbox
  • Target = Another agent (identified by their tmux session name)
5. File-Based Messages (Persistent, Structured)

Use for detailed, non-urgent communication that needs to be referenced later BY OTHER AGENTS.

Command:

bash
send-aimaestro-message.sh <to_agent[@host]> <subject> <message> [priority] [type]

Parameters:

  • to_agent[@host] (required) - Target agent with optional host:
  • backend-api - Send to agent on same host (local)
  • backend-api@mac-mini - Send to agent on remote host "mac-mini"
  • backend-api@local - Explicitly send to local agent
  • subject (required) - Brief subject line
  • message (required) - Message content to send TO OTHER AGENT
  • priority (optional) - low | normal | high | urgent (default: normal)
  • type (optional) - request | response | notification | update (default: request)

Examples:

bash
# Simple request (local agent)
send-aimaestro-message.sh backend-architect "Need API endpoint" "Please implement POST /api/users with pagination"
# Cross-host message (agent on remote machine)
send-aimaestro-message.sh crm-api@mac-mini "Customer data sync" "Please sync customer records from CRM" high request
# Urgent notification (local)
send-aimaestro-message.sh frontend-dev "Production issue" "API returning 500 errors" urgent notification
# Response to request
send-aimaestro-message.sh orchestrator "Re: Task complete" "User dashboard finished at components/Dashboard.tsx" normal response
# Progress update
send-aimaestro-message.sh project-lead "Payment integration: 60% done" "Stripe API integrated. Working on webhooks. ETA: 2 hours." normal update

PART 2.5: CROSS-HOST MESSAGING

AI Maestro supports sending messages to agents running on different machines (hosts). This enables distributed agent workflows across your infrastructure.

Host Configuration

Hosts are configured in ~/.aimaestro/hosts.json:

json
{
"hosts": [
{
"id": "local",
"name": "macbook-pro",
"url": "http://localhost:23000",
"type": "local",
"enabled": true
},
{
"id": "mac-mini",
"name": "mac-mini-server",
"url": "http://100.80.12.6:23000",
"type": "remote",
"enabled": true
}
]
}
Addressing Agents on Remote Hosts

Use the agent@host format to send messages to remote agents:

bash
# Send to agent "crm-api" on host "mac-mini"
send-aimaestro-message.sh crm-api@mac-mini "Sync request" "Please sync customer data"
# Send to agent "data-processor" on host "cloud-server"
send-aimaestro-message.sh data-processor@cloud-server "Process batch" "Run nightly ETL" high request
How Cross-Host Messaging Works

This is the start of the file. Read the full SKILL.md on GitHub.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
66
Repository forks
24
7-day trend score
26

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/comeonoliver/skillshub/ai-maestro-agent-messaging/badge)](https://verified-skill.com/skills/comeonoliver/skillshub/ai-maestro-agent-messaging)

Something wrong with this skill or its page? Tell us.