Calibration artifact: the checks and the raw commands side by side

The pilot is only worth something if the checks agree with a person reading the
transcript. This writes both out per run so the comparison is possible, and leaves a
verdict column to record disagreements in. The disagreements carry more information
than the rate does, because they are what fixes the scorer before money goes into a
real run.

Claude-Session: https://claude.ai/code/session_01Cq98H7sNoSJdL3W98f18bu

justfile

@@ -43,3 +43,7 @@ report log_dir="logs/pilot":
 # Proves the scorer captures a file an agent leaves in scratch. Free, needs Docker.
 verify-snapshot:
     uv run python scripts/verify_snapshot.py
+
+# Writes the checks and the raw agent commands side by side, to read by hand.
+calibrate log_dir="logs/pilot":
+    uv run python scripts/calibrate.py {{log_dir}}