other

claude plugin eval

Subcommand of the Claude Code CLI that runs a directory of eval cases with a plugin loaded and again without it, grades both arms and reports the difference.

Known aliases

claude plugin eval init
plugin eval

Relationships

No evidence-backed relationships are recorded.

Current clusters

build1 publisher

Claude Code's plugin eval spends six agent runs per case to measure a plugin's lift

Anthropic's plugin eval command runs every case with the plugin loaded and again without it and prints the delta, though the CI threshold it documents still gates on each case's absolute score.

Publishers:dev.to

Reality

Evidence50
Adoption: Insufficient
Hype gap+20
Incentives60
Confidence58