Index of every page on this site: llms.txt
All skills
davila7 avatar

/agent-messaging

@053feb2
Run it yourself

Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.

Use this Skill: https://skilld.dev/gh/davila7/claude-code-templates/agent-messaging

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈77 tokens for metadata: the name and description. ≈723 when used: this file.

Description uses 3.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈310 characters, or 3.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Agent 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

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert2mo5 checks · Risk HIGH
  • Gen Agent Trust Hub2mo

    The skill requires downloading and executing a shell script from a third-party GitHub repository to function. It also presents an attack surface for indirect prompt injection via its message-reading capabilities.

  • Socket2mo

    1 alert: gptAnomaly

  • Snyk2mo

    Risk: MEDIUM · 2 issues

  • Runlayer9mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 053feb2. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 9 months ago

README badge

README badge for davila7/claude-code-templates/agent-messaging