My Brain Wiki

agent-plugins-org-2026

3分钟阅读

title: Agent Plugins description: A portable package format for reusable components that extend AI agents.

Agent Plugins

Agent Plugins is an open, vendor-neutral standard for packaging reusable components into portable plugins. Its version 1.0.0 specification defines a shared format for Agent Skills and MCP servers that compatible clients can discover and load consistently.

Why Agent Plugins?

AI agent clients have developed their own plugin formats, even when plugins contain the same underlying components. Authors must rearrange or duplicate those components for each client, so a plugin packaged for one client may need adaptation before another can use it.

Agent Plugins defines a small interoperability floor for the parts that can be portable across clients. Shared components can use one predictable structure, while distribution, installation, permissions, user experience, and client-specific capabilities remain under each client’s control.

The portable package

An Agent Plugin is a directory with a required manifest and optional components in fixed locations:

my-plugin/
├── plugin.json
├── skills/
│   └── summarize/
│       ├── SKILL.md
│       ├── scripts/
│       └── references/
├── mcp.json
└── com.example.client/
    └── hooks/
  • plugin.json identifies the plugin and the Agent Plugins version it targets.
  • skills/ contains Agent Skills in the format defined by the Agent Skills specification.
  • mcp.json describes stdio, Streamable HTTP, or legacy HTTP+SSE MCP servers.
  • Reverse-domain extension namespaces let individual clients add behavior without changing the portable core.

Open development

Agent Plugins is openly licensed and developed in public. Its initial Technical Steering Committee includes Core Maintainers from Amazon, Cursor, Microsoft, OpenAI, and Vercel.

Proposals and technical decisions are public, and participation is open to the broader ecosystem. Ideas for new features and material changes begin in GitHub Discussions, where proposals can establish a concrete portability need and implementer support.

Specification Summary (v1.0.0)

Conformance

  • Spec version: 1.0.0 (Working Draft)
  • Uses RFC 2119 / RFC 8174 conformance language (MUST, SHOULD, MAY)

Plugin Package Model

  • Plugin is a directory rooted at a single filesystem location
  • Must include plugin.json manifest at plugin root
  • Filesystem paths MUST remain within plugin root (symlinks validated)
  • Configuration paths must begin with ./ and resolve within plugin root

Manifest (plugin.json)

Required fields: $schema, name Optional fields: version, description, author, homepage, repository, license, keywords, extensions Schema: closed (unknown top-level fields reported and ignored) Schema URL: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

Component Types

  1. Agent Skills — skills/ directory, format defined by Agent Skills specification
  2. MCP Servers — mcp.json manifest, supports stdio, Streamable HTTP, legacy HTTP+SSE transports

Client Extensions

  • Reverse-domain namespaces (e.g., com.example.client/)
  • Each client can add behavior without changing the portable core
  • Extension data goes under extensions in manifest or dedicated top-level directories

Compatible Clients

  • VS Code — supports Agent Skills + MCP stdio/Streamable HTTP/legacy SSE

Technical Steering Committee

  • Amazon, Cursor, Microsoft, OpenAI, Vercel (Core Maintainers)

Repository

For a semantic overview of all documentation, see the Agent Plugins specification repository.

关系图谱