Plugin Eval

{
  "name": "plugin-eval",
  "author": {
    "url": "https://openai.com/",
    "name": "OpenAI Codex",
    "email": "support@openai.com"
  },
  "skills": "./skills/",
  "license": "MIT",
  "version": "0.1.1",
  "homepage": "https://openai.com/",
  "keywords": [
    "codex",
    "plugin",
    "skill",
    "evaluation",
    "quality",
    "budget"
  ],
  "interface": {
    "logo": "./assets/plugin-eval.svg",
    "category": "Developer Tools",
    "brandColor": "#0F766E",
    "websiteURL": "https://openai.com/",
    "displayName": "Plugin Eval",
    "screenshots": [],
    "capabilities": [
      "Interactive",
      "Write"
    ],
    "composerIcon": "./assets/plugin-eval.svg",
    "defaultPrompt": [
      "Give me an analysis of the game studio plugin.",
      "Evaluate this plugin.",
      "Why did this score that way?"
    ],
    "developerName": "OpenAI",
    "longDescription": "Ask Codex to evaluate a plugin or skill, give you a full analysis of a named plugin such as game-studio, explain why it scored that way, show what to fix first, explain its token budget, measure real token usage, benchmark a plugin, or tell you what to run next. Plugin Eval keeps the path engineer-friendly: start with a natural chat request, then use the local `plugin-eval start` entrypoint or the routed workflow command it recommends.",
    "privacyPolicyURL": "https://openai.com/policies/privacy-policy/",
    "shortDescription": "Start from chat, then evaluate or benchmark locally",
    "termsOfServiceURL": "https://openai.com/policies/terms-of-use/"
  },
  "repository": "https://github.com/openai/plugins",
  "description": "Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking."
}