In reply to @claudedevs

ClaudeDevs

ClaudeDevs

@claudedevs · Twitter ·

Evals call the model, so they use tokens and results vary. Pilot with `--runs 1` before a full run. Your plugin's hooks and MCP servers run as you, so only evaluate plugins you trust. Run claude update to try it. Docs: https://code.claude.com/docs/en/plugin-evals