# Claude Code Plugin Eval

By Steven Van · 2026-09-11

Creators can write test cases, score a plugin or skill's runs, and compare results with and without it enabled.

[Claude Code](<https://creatorstoolbox.com/tools/claude-code>) now includes a [plugin eval](<https://x.com/i/status/2098500999656923145>) workflow: create test cases, run a plugin or skill against them, and score the results. The same test cases can then be run with and without the plugin enabled, so a creator can see how much value it actually adds.

![](<https://pbs.twimg.com/media/HR9cG20bcAAbBP6.jpg>)

![Claude Code](<https://claude.com/images/icon-512x512.png>)

Claude Code

Anthropic's agentic coding tool — Claude in your terminal, IDE, desktop app and browser, reading and editing your codebase, running commands, opening pull requests and working on tasks in the cloud.

[View Claude Code →](<https://creatorstoolbox.com/tools/claude-code>)

Sources

[Original source](<https://x.com/i/status/2098500999656923145>)

[Read Claude Code Plugin Eval on Creators Toolbox](<https://creatorstoolbox.com/blog/claude-code-claude-code-plugin-eval>)

---
Canonical source: https://creatorstoolbox.com/blog/claude-code-claude-code-plugin-eval