Log Model Switches for Change-Control Evidence
A model-risk review asking "which model produced this output" needs a durable answer, not a guess from the transcript. This records every applied model change — including automatic ones on resume — to a separate log a reviewer can read without replaying the whole session.
1. Save this as the hook script
#!/usr/bin/env python3
"""PostModelSwitch hook — logs every applied model change."""
import json, sys, datetime
from pathlib import Path
data = json.load(sys.stdin)
log_path = Path(data.get("cwd", ".")) / ".claude" / "model_switch_log.jsonl"
log_path.parent.mkdir(parents=True, exist_ok=True)
entry = {
"ts": datetime.datetime.utcnow().isoformat() + "Z",
"session_id": data.get("session_id"),
"from_model": data.get("from_model"),
"to_model": data.get("to_model"),
}
with open(log_path, "a") as f:
f.write(json.dumps(entry) + "\n")
sys.exit(0)
Save to a path inside your project, e.g. .claude/hooks/log-model-switches.sh, then chmod +x it.
2. Wire it into .claude/settings.json
{
"hooks": {
"PostModelSwitch": [
{
"hooks": [
{"type": "command", "command": "python3 .claude/hooks/log-model-switches.py"}
]
}
]
}
}
Before you use this
A hook runs with your local shell's permissions — review the script above before adding it, the same way you'd review any script you didn't write yourself. See our guide on hook security risks for the specific CVEs this category of feature has already produced.
Related hooks