17 pages for plugin eval.

Claude Code changelog Claude Code CLI · in the page changelog …ded `--disallow-tools` and a `disallowed_tools` case field to `claude plugin eval` to keep specific built-in tools, such as Agent, out of eval runs * Added support for turning off the attribution bloc… Error reference Claude Code CLI · in the page errors …e errors](#feedback-is-disabled-by-your-organizations-policy) | | `` `plugin eval` is currently in early access `` / `` `plugin eval` is currently unavailable `` | [Plugin errors](#plugin-eval-is-curr… Test plugins with evals Claude Code CLI · in the page plugin-evals …> Write eval cases for your Claude Code plugin, run them with claude plugin eval, grade the results, compare against a no-plugin baseline, and gate CI on the score. The `claude plugin eval` shell co… Plugin commands reference Claude Code CLI · in the page plugins/cli-reference …— run `claude plugin prune -y` to remove.``, removing nothing | ### plugin eval Run a plugin's [eval cases](/docs/en/plugin-evals) and report scored results. Requires Claude Code v2.1.269 or later.… Create a Claude Code plugin Claude Code CLI · in the page plugins/create …out errors can still fail to steer Claude the way you intend. `claude plugin eval`, which you run in your shell, runs your test cases with and without the plugin and scores the difference. See [Test p… Plugin manifest reference Claude Code CLI · in the page plugins/manifest-reference …different-eval-directory) when it isn't the default `evals/`. `claude plugin eval --eval-dir` overrides it | In the Type column, a path is a string relative to the plugin root, such as `"./custom/com… Publish and distribute a plugin Claude Code CLI · in the page plugins/publish …. **6. Run your eval suite** If you have an eval suite, run `claude plugin eval` in your shell. It runs the plugin's test cases and scores the results, which catches regressions when you change the… Troubleshoot plugins Claude Code CLI · in the page plugins/troubleshooting …en/plugin-evals#create-your-first-eval-suite) and run it with `claude plugin eval` after each description change. ### `<directory> is not a plugin or skill folder` from `claude plugin eval init` You… Extend Claude with skills Claude Code CLI · in the page skills …ides**: `skillOverrides` doesn't apply to plugin skills. Use [`claude plugin eval`](/docs/en/plugin-evals#the-no-plugin-baseline) instead, which repeats each run with no plugin loaded. Two tools auto… Create custom subagents Claude Code CLI · in the page sub-agents …across realistic prompts instead of checking one at a time: [`claude plugin eval`](/docs/en/plugin-evals) runs each prompt with and without the plugin and scores the results. ### Invoke subagents ex… Week 37 · September 7–11, 2026 Claude Code CLI · in the page whats-new/2026-w37 # Week 37 · September 7–11, 2026 > Test your plugins with claude plugin eval and pop Claude Code Desktop panes out into their own windows. Releases [v2.1.263 → v2.1.269](/docs/en/changelog#2-1-263)… What's new Claude Code CLI · in the page whats-new/index …ent, see the [changelog](/docs/en/changelog). **Week 37** **`claude plugin eval`**: run your plugin against a suite of test cases, score the results, and compare against a no-plugin baseline. `claud… Build for Claude Claude Documentation · in the page build/overview …try its skills and commands before it's in a repository * **[`claude plugin eval`](https://code.claude.com/docs/en/plugin-evals)**: run eval cases you write and compare Claude's results with and with… Plugin structure and testing Claude Documentation · in the page plugins/build …its skills improve Claude's output, write eval cases and run [`claude plugin eval`](https://code.claude.com/docs/en/plugin-evals) in Claude Code, which grades the results and compares them against a r… Plugin pre-submission checklist Claude Documentation · in the page plugins/pre-submission-checklist …are the output with what Claude produces without the plugin. [`claude plugin eval`](https://code.claude.com/docs/en/plugin-evals) runs that comparison for the whole plugin in Claude Code, and [Measure… Build your first plugin Claude Documentation · in the page plugins/quickstart …plugin's components load in chat, Cowork, and Claude Code * [`claude plugin eval`](https://code.claude.com/docs/en/plugin-evals): write eval cases and compare the plugin's results against a run witho… Create custom skills Claude Documentation · in the page skills/how-to …test the whole plugin from the Claude Code command line with [`claude plugin eval`](https://code.claude.com/docs/en/plugin-evals), which grades eval cases you write and compares against a run without…