Agent Messaging
FreeSecurely send and receive messages between AI agents.
Free · Opens the source repo
What Agent Messaging does
The Agent Messaging skill implements the Agent Messaging Protocol (AMP), allowing AI agents to communicate securely through cryptographically signed messages. This skill is designed for developers and designers looking to facilitate inter-agent communication without relying on external services. By default, AMP operates locally, ensuring that your messaging capabilities are self-contained and straightforward to set up.
To get started, users will first need to initialize their agent's identity using the amp-init command. Once set up, sending messages to other agents is as simple as using the amp-send command, where users can specify recipients, subjects, and message bodies. The skill also supports checking an inbox with amp-inbox, reading specific messages with amp-read, and replying to messages with amp-reply. This straightforward command structure makes it easy for users to manage communications effectively.
AMP also provides flexibility in message handling. Users can set message priorities, types, and even attach files to messages, enhancing the functionality of the communication process. Security is a key focus, with Ed25519 signatures ensuring that messages are verified and private keys remaining local to the agent. Each agent operates with a unique identity, contributing to a secure messaging environment.
This skill is particularly useful for teams working with multiple AI agents that need to coordinate tasks or share information. By using AMP, developers can create robust workflows for agent interactions, making it an essential tool for anyone involved in AI orchestration or agent management.
When to use it
Use this skill when you need to facilitate message exchanges between AI agents in a secure and controlled manner.
When not to use it
This skill may not be suitable for scenarios requiring extensive external integrations or complex messaging features beyond basic communication.
What you can build with it
Team Coordination
Use AMP to enable multiple AI agents to communicate and coordinate tasks effectively within a project.
Task Notifications
Send urgent task notifications to agents to ensure timely responses and action.
Information Sharing
Facilitate the sharing of reports and documents between agents by sending messages with attached files.
How to install Agent Messaging
View source1. Install with the skills CLI
npx skills add davila7/claude-code-templates/agent-messaging --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by davila7Agent Messaging Protocol (AMP)
Send and receive cryptographically signed messages between AI agents. AMP works locally by default -- no external dependencies needed for basic messaging. Part of the AI Maestro suite.
Prerequisites
Install the AMP CLI scripts:
# From the AI Maestro plugin
git clone https://github.com/23blocks-OS/ai-maestro-plugins.git
cd ai-maestro-plugins && ./install-messaging.sh -y
Scripts install to ~/.local/bin/ (ensure it's in your PATH).
Quick Start
1. Initialize identity (first time)
amp-init --auto
2. Send a message
amp-send alice "Hello" "How are you?"
3. Check inbox
amp-inbox
4. Read a message
amp-read <message-id>
5. Reply
amp-reply <message-id> "Got it, working on it now"
Address Formats
| Format | Example | Delivery |
|---|---|---|
| Local name | alice | Same machine |
| Local qualified | alice@myorg.aimaestro.local | Within mesh |
| External | alice@acme.crabmail.ai | Via provider (requires registration) |
Core Commands
| Command | Description |
|---|---|
amp-init --auto | Create agent identity |
amp-send <to> <subject> <body> | Send a message |
amp-inbox | Check inbox (add --all for read messages) |
amp-read <id> | Read a specific message |
amp-reply <id> <body> | Reply to a message |
amp-delete <id> | Delete a message |
amp-status | Show identity and registrations |
amp-identity | Show current identity |
Message Options
# Set priority
amp-send alice "Deploy" "Ready for prod" --priority urgent
# Set type
amp-send alice "Review PR #42" "Please review" --type request
# Attach files
amp-send alice "Report" "See attached" --attach report.pdf
Message Types and Priorities
| Type | Use Case | Priority | When | |
|---|---|---|---|---|
notification | General info (default) | normal | Standard (default) | |
request | Asking for something | urgent | Immediate attention | |
task | Assigned work | high | Respond soon | |
handoff | Transferring context | low | When convenient | |
status | Progress update |
Security
- Ed25519 signatures on every message
- Private keys stay local -- never sent to providers
- Per-agent identity -- each agent has unique keypair
Full AI Maestro Experience
This skill provides basic AMP messaging. For the complete experience including federation with external providers, push notifications, attachment scanning, and 5 more skills (memory search, docs search, graph query, planning, agent management), install the full AI Maestro platform.
Protocol spec: agentmessaging.org
Frequently asked questions about Agent Messaging
Similar skills
Agent Skill Stack
Assemble compatible AI Agent Skills for workflows.
AI Team Orchestration
Streamline multi-agent development workflows.
Advisor Orchestrator Worker
Efficiently manage complex tasks with multiple AI models.
Agent Orchestrator
Automate multi-agent workflows with zero manual intervention.
Agent Governance
Implement safety and trust controls for AI agents.
Microsoft Foundry
End-to-end management for Microsoft Foundry agents.