Sandbox
@agentplugins/agent-plugins-spec

Plugin standard for agent skills and MCP servers

Agent Plugins defines a portable package format for reusable agent extensions. A plugin starts with `plugin.json` and can expose skills through files like `skills/greet/SKILL.md`, which a compatible client can discover and load. The spec leaves user-facing behavior to the client.

1,272 stars69 forksUpdated 28d ago
Who it's for

Builders who want to package agent skills or MCP servers in a shared format.

What it delivers

You can ship agent extensions in a portable plugin structure that clients can discover and load.

What it does

Portable plugin format

Defines how to package reusable agent extensions into a distributable directory structure.

Skill discovery layout

Uses `plugin.json` plus `skills/<name>/SKILL.md` so clients can find skills consistently.

Schema definitions

Provides versioned JSON schemas for validating plugin metadata and related files.

Versioned specification

Separates the published 1.0.0 spec from the 1.1.0 working draft.

Governance documents

Includes charter and contribution docs that explain how the standard is maintained.

How to get it

  1. 1The smallest useful plugin is a directory with one skill
    hello-plugin/
    ├── plugin.json
    └── skills/
        └── greet/
            └── SKILL.md

README

Agent Plugins

Agent Plugins is an open, vendor-neutral standard for packaging reusable components that extend AI agents into distributable plugins. It defines a portable package format for Agent Skills and MCP servers.

This README is a non-normative introduction. The versioned specification defines the portable contract.

Status

Agent Plugins Specification 1.0.0 is the current published release. Agent Plugins Specification 1.1.0 is a working draft.

Quick Start

The smallest useful plugin is a directory with one skill:

hello-plugin/
├── plugin.json
└── skills/
    └── greet/
        └── SKILL.md

In plugin.json:

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "hello-plugin"
}

In skills/greet/SKILL.md:

---
name: greet
description: Greet the user and offer help.
---

Greet the user and offer help.

A client that supports skills can load the plugin by reading plugin.json and discovering skills/greet/SKILL.md. How the client exposes the skill to users or models is outside the Agent Plugins specification.

Project Documents

Files in the repo

Repository payload10 top-level entries
  • LICENSES
  • schemas
  • spec
  • AGENTS.md
  • CONTRIBUTING.md
  • FUTURE_CONSIDERATIONS.md
  • GOVERNANCE.md
  • LICENSE.md
  • MAINTAINERS.md
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More plugins

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

138k
1 add

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

82k
code-yeongyu/
oh-my-openagent

OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.

69k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

94k

Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns

4.3k