claude plugin eval: Reproducible Scoring for Claude Code Plugins
Claude Code 2.1.269 adds a claude plugin eval command that runs a plugin's own eval suite against Claude Code and produces a scored, reproducible JSON and HTML report.
What it is
The latest Claude Code release, adding a built-in plugin evaluation runner alongside output-style switching in headless and Remote Control sessions.
What it does
`claude plugin eval` runs a plugin's declared eval suite and scores the result into a JSON and HTML report; `/output-style [name]` now works over Remote Control and in cloud or headless sessions; a new `bashEditDiffEnabled` setting shows a diff of files a Bash command changed directly in the tool result. See the release notes for the full list.
Why it matters
Plugin authors previously had no standard, reproducible way to prove a plugin still works after an update; a built-in scored eval command turns that into a CI-checkable step instead of manual spot-checking.
Claude Code 2.1.265 Caps Saved Tool Output at 1GB
Claude Code 2.1.265 adds a 1GB cap on tool results saved to disk, live-reloading for a whole folder passed to --plugin-dir, and a fix for prompt-cache reuse in resumed subagents.
Claude Code 2.1.238: Readline Keybindings and a Token-Minting Hook for Plugins
Claude Code 2.1.238 adds a headersHelper setting that runs a command to mint short-lived auth headers for private plugin marketplace fetches, plus an optional readline-style Ctrl+W keybinding.
Claude Code 2.1.224 Adds Self-Hosted Runners and Zip-Based Plugin Installs
Claude Code 2.1.224 adds a self-hosted-runner command that lets Team and Enterprise plans run web, mobile, and desktop sessions on their own machines or containers, plus zip-based plugin installs with SHA-256 pinning.