---
title: "Anthropic adds automated evaluation tooling for Claude Code plugins"
url: https://www.parallelquant.com/posts/anthropic-adds-automated-evaluation-tooling-for-claude-code-plugins-5c2f96
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/09/11/anthropic-adds-plugin-evals-to-claude-code-6-grader-types-a-no-plugin-baseline-and-a-ci-gate-for-skills/
published: 2026-09-11T21:05:55.000Z
topics: ["products", "open source"]
publisher: "Parallel Quant"
---

# Anthropic adds automated evaluation tooling for Claude Code plugins

*2026-09-11 · Source: [MarkTechPost](https://www.marktechpost.com/2026/09/11/anthropic-adds-plugin-evals-to-claude-code-6-grader-types-a-no-plugin-baseline-and-a-ci-gate-for-skills/)*

Anthropic released a claude plugin eval command that runs a Claude Code plugin against realistic prompts, grades the output using six grader types, and compares results against a run with no plugin loaded. It can be wired into continuous integration (CI) as a gate before shipping.

**Why it matters:** As Claude Code's plugin and skill ecosystem grows, developers previously had no standard way to verify a plugin does what it claims versus just adding noise; a built-in eval and CI gate gives plugin authors a way to catch regressions before they reach users.

**Topics:** products, open source

---
Read the original: https://www.marktechpost.com/2026/09/11/anthropic-adds-plugin-evals-to-claude-code-6-grader-types-a-no-plugin-baseline-and-a-ci-gate-for-skills/
Canonical: https://www.parallelquant.com/posts/anthropic-adds-automated-evaluation-tooling-for-claude-code-plugins-5c2f96
Published by Parallel Quant — https://www.parallelquant.com