agent-messaging
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.
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 3.3w
- Forks
- 3.9k
01 前言 Front Matter
- name
- agent-messaging
- description
- 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.
02 资源文件 17
- 参考文档agents/analyzer.md10.1 KB
- 参考文档agents/comparator.md7.1 KB
- 参考文档agents/grader.md8.8 KB
- 资产文件assets/eval_review.html6.9 KB
- 脚本eval-viewer/generate_review.py16.0 KB
- 参考文档eval-viewer/viewer.html43.9 KB
- 许可证LICENSE.txt11.1 KB
- 参考文档references/schemas.md11.8 KB
- 脚本scripts/__init__.py—
- 脚本scripts/aggregate_benchmark.py14.0 KB
- 脚本scripts/generate_report.py12.5 KB
- 脚本scripts/improve_description.py10.9 KB
- 脚本scripts/package_skill.py4.1 KB
- 脚本scripts/quick_validate.py3.9 KB
- 脚本scripts/run_eval.py11.2 KB
- 脚本scripts/run_loop.py13.3 KB
- 脚本scripts/utils.py1.6 KB
03 SKILL.md 正文
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
04 同仓库更多 Skills
wealthville-pool-scoring
Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter/Hold/Exit/Reduce/Avoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.
technical-debt-auditor
Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO/FIXME/HACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like "where should I focus refactoring", "find code smells", "audit my codebase", "what technical debt do we have", "prioritize cleanup work", or asks about code quality metrics. Also trigger when the user mentions "code rot", "legacy cleanup", "refactoring priorities", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say "technical debt" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.
readonly-sql-guard
Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production/ERP/analytics database (a "query" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write/DDL/side-effect/transaction-escape risks. Checks what a statement CALLS, not just its shape.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.