Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add agentmessaging/claude-pluginnpx agentmods add plugins/agentmessaging/claude-plugin/claude-plugingit clone --depth 1 https://github.com/agentmessaging/claude-pluginGrade A, and why
agent-messaging scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "agent-messaging",
"version": "0.1.3",
"description": "Agent Messaging Protocol (AMP) - Secure, cryptographically signed messaging between AI agents across different providers.",
"homepage": "https://agentmessaging.org",
"repository": "https://github.com/agentmessaging/claude-plugin",
"license": "Apache-2.0",
"author": {
"name": "23blocks",
"url": "https://23blocks.com"
},
"keywords": [
"ai-agents",
"messaging",
"federation",
"protocol",
"inter-agent-communication"
],
"skills": [
"skills/agent-messaging"
],
"commands": [
"commands/amp-init.md",
"commands/amp-identity.md",
"commands/amp-status.md",
"commands/amp-send.md",
"commands/amp-inbox.md",
"commands/amp-read.md",
"commands/amp-reply.md",
"commands/amp-delete.md",
"commands/amp-register.md",
"commands/amp-fetch.md",
"commands/amp-download.md"
],
"claude_code_version": ">=1.0.0"
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 37 lines scan A 45f8254a3237
agent-messaging is a plugin published in the GitHub repository agentmessaging/claude-plugin (5 stars, last pushed 13d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
agmsg
Cross-agent messaging via SQLite. Send messages between CLI AI agents. No daemon, no network.
local
Plugin marketplace listing 1 plugin: gopls-mcp.
thumbgate
One 👎 becomes a hard rule the agent cannot bypass. Captures thumbs-down feedback, distills it into PreToolUse Pre-Action Checks, enforced across every future Claude Code session.
videodb-skills
Plugin marketplace listing 1 plugin: videodb.
laravel-lsp
Framework-aware code intelligence for Laravel via the first-party laravel/lsp language server.
ngernthongdee
Ngernthongdee's Claude Code plugins — starting with devenv-doctor, a dev environment health check that tells you exactly what's broken and how to fix it.