braintrust plugins

Calibre-Labs/reforge-ai-evals

Plugin Claude Code

Bundles 9 skills, 9 commands · 1,028 tokens together

Skills for evaluating an AI product: write the eval rubric, build test inputs, turn trace notes into codes, write judges and check them against your labels. You annotate traces and label for calibration. The skills do the rest.

braintrustdata/braintrust-claude-plugin

Plugin Claude Code

Bundles 13 hooks

Automatically trace Claude Code conversations to Braintrust for observability. Captures sessions, conversation turns, and tool calls as hierarchical traces.