Plugin Eval
Plugin Eval helps you test Codex skills and plugins. Ask in chat to evaluate one, and it explains the score, what to fix first and the token budget, measures real token usage and can benchmark the plugin. It's both a Codex plugin and a local Node.js command-line tool.
Skills (5)
- plugin-eval, evaluate-plugin, evaluate-skill, improve-skill, metric-pack-designer.
- Example prompts: “Evaluate this plugin” and “Why did this score that way?”
- Reports are local-first.
- The CLI needs Node.js 20 or later.
- The package is marked private, so the README says to run it from a local checkout (
node ./scripts/plugin-eval.js) rather than npm.
- Capabilities in the manifest: Interactive, Write.
- Nothing else about access is stated on the listing.
- Publisher: OpenAI (author: OpenAI Codex).
- Repository: openai/plugins, folder plugins/plugin-eval.
- License: MIT (plugin.json).
Taken from the plugin's README and plugin.json in openai/plugins on GitHub. Facts marked "from the source code, not the listing" come from the item's public source files on GitHub or n8n. Anything stated nowhere is marked "Not stated".
More Codex templates
- Build Web Apps by OpenAI
- GitHub by OpenAI
- Codex Security by OpenAI
- Build iOS Apps by OpenAI
AgentScout links to the original public listings and doesn't host copies. We aren't affiliated with xAI, Anthropic, OpenAI, OpenClaw, Cursor, n8n or the creators listed. Names and logos belong to their owners. Official logos come from the item's own repo or listing, or its publisher's official account; Grok Bot cards show the creator's photo from the x.ai marketplace; the rest are icons made by AgentScout. Listings checked Oct 19, 2026.