plugin-dev
Toolkit for developing Claude Code plugins with 7 expert skills covering hooks, MCP, commands, and agents.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for plugin-dev, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
plugin-dev is an official Anthropic toolkit for building Claude Code plugins, bundling seven expert skills that cover hooks, MCP integration, commands, agents, and best practices, plus AI-assisted plugin creation and validation. It is the canonical meta-plugin for authoring plugins.
Key features and capabilities
- 7 expert plugin-authoring skills
- Covers hooks, MCP, commands, agents
- AI-assisted creation and validation
Use cases
- Build a new Claude Code plugin
- Validate a plugin against best practices