PulseAugur
EN
LIVE 22:43:29
日本語(JA) Anthropic、Claude Codeのプラグイン評価コマンド「claude plugin eval」を紹介 https:// gihyo.jp/article/2026/09/claud e-plugin-eval?utm_source=feed # gihyo # 技術評論社 # gihyo_jp # AI #

Anthropic launches Claude Code plugin evaluation tool

By PulseAugur Editorial · [2 sources] ·

Anthropic has introduced a new command-line tool, `claude plugin eval`, designed to evaluate the performance of plugins used with Claude Code. This tool allows developers to test how effectively their plugins are triggered and utilized by Claude models, comparing performance with and without the plugin active. The evaluation process includes six types of graders, four of which are free and analyze aspects like tool usage and file existence, while two require billing a judge model to assess response quality and compare against reference answers. The primary metric is Delta (Δ), which quantifies the plugin's contribution to the outcome, helping developers identify issues such as skills not triggering on natural language phrasing. AI

IMPACT This tool aims to streamline plugin development and improve the reliability of Claude's ability to utilize external tools.

RANK_REASON The cluster describes a new tool released by Anthropic for evaluating plugins within their Claude Code environment.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Anthropic launches Claude Code plugin evaluation tool

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a new tool released by Anthropic for evaluating plugins within their Claude Code environment.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
47 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No-Plugin Baseline, and a CI Gate for Skills

    <p>Anthropic has published a new plugin evals workflow for Claude Code. The claude plugin eval command runs a plugin against realistic prompts, grades what Claude produced, and compares the result with a run where the plugin is not loaded. It answers 3 questions plugin developers…

  2. Mastodon — mastodon.social TIER_1 日本語(JA) · [email protected] ·

    Anthropic introduces Claude Code plugin evaluation command "claude plugin eval"

    Anthropic、Claude Codeのプラグイン評価コマンド「claude plugin eval」を紹介 https:// gihyo.jp/article/2026/09/claud e-plugin-eval?utm_source=feed # gihyo # 技術評論社 # gihyo_jp # AI # Claude_Code # Plugins

    LINKS gihyo.jp/…/claude-plugin-eval

RELATED ENTITIES

RELATED TOPICS