Test Claude Code plugin and skill triggering with staged eval runs using cc-plugin-eval

Run staged evaluations against a Claude Code plugin to verify that skills, agents, commands, hooks, and MCP components trigger when they should.

Prerequisites

Node.js 20+, Anthropic API key, Claude Code plugin directory

Installation

Use the upstream install or setup path that matches your environment:

• git clone https://github.com/sjnims/cc-plugin-eval.git
• npm install
• npm run build
• npx cc-plugin-eval run -p ./path/to/your/plugin --dry-run

Requirements and caveats from upstream:

• 
• Node.js >= 20.0.0

Basic usage or getting-started notes:

• An Anthropic API key

• bash

• Clone the repository

• Source: https://github.com/sjnims/cc-plugin-eval

• Extracted from upstream docs: https://raw.githubusercontent.com/sjnims/cc-plugin-eval/HEAD/README.md

Documentation

• https://github.com/sjnims/cc-plugin-eval

Source

• Agent Skill Exchange