Plugin / OpenAI

Plugin Eval for Codex

Start from chat, then evaluate or benchmark locally.

Docs reviewedChecked 2026-09-20Runtime not tested

What it adds

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.

codexpluginskillevaluationqualitybudget

Get set up

  1. Open Plugins in Codex and search for this plugin.
  2. Install it and complete any account authorization it asks for.
  3. Start a new thread to use it.
/plugins
Review before running
Read the installation source

Before you install

    Compatibility & limitations

    Documented for ChatGPT desktop app, Codex CLI, ChatGPT web

    Cursor: Not confirmed for Cursor.

      This listing is based on source documentation. We have not installed or runtime-tested this asset.

      How it fits together

      Finishing a Development Branch · SkillUse when implementation is complete, all tests pass, and you need to decide how to integrate the work.Plugin Creator · SkillCreate and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, and baseline placeholders...Lovable · PluginBuild apps and websites.NVIDIA · PluginGuided help for NVIDIA AI, GPU, robotics, simulation, and 3D workflows.OpenAI Ads Conversions · PluginSet up OpenAI Ads Pixel and CAPI tracking.OpenAI Developers · PluginDevelop AI apps, agents, and ChatGPT Apps with OpenAI best practices.

      Sources & provenance

      Reviewed 2026-09-20. Source revision: main (mutable; commit not pinned).