$ trace-eval ci examples/hermes_good.jsonl --min-score 80

PASS
============================================================
  TRACE-EVAL SCORECARD  Total: 98.9/100
============================================================

DIMENSION SCORES:
  reliability           100.0  (high)
  efficiency             94.5  (medium)
  retrieval             100.0  (high)
  tool_discipline       100.0  (high)
  context               100.0  (high)

(exit code: 0)
