Agent Plugins package your skills, tools, and more

Summary

Agent Plugins 1.0.0 is an open, vendor-neutral specification for packaging Agent Skills and MCP servers into portable plugins, addressing incompatible wrappers that force authors to maintain client-specific copies. It defines a plugin as a directory with plugin.json, skills/ subdirectories, mcp.json, and client-owned reverse-domain extension namespaces. The manifest fixes component locations, requires explicit MCP server types for stdio, Streamable HTTP, or legacy HTTP+SSE, and lets skills continue loading when an MCP entry fails. Version 1 deliberately excludes installation, distribution, permissions, sandboxing, trust verification, and user experience, leaving those concerns to clients and related ecosystem layers such as discovery and catalogs. Google is joining the Core Maintainers and says Agents CLI and Data Agent Kit support the format, while more product integrations are expected.

Takeaways

1. 1

   A valid plugin uses plugin.json, skills/ with one subdirectory per skill, and mcp.json; the manifest cannot relocate or inline components.

2. 2

   MCP entries must declare their type, covering stdio, Streamable HTTP, and legacy HTTP+SSE, while a failed server entry does not prevent the client from loading the plugin's skills.

3. 3

   Agent Plugins v1 defines packaging only; discovery, catalogs, installation, policy, permissions, sandboxing, trust, and approval UX remain separate concerns.