Validate
1 scenario, 1 run by an agent. Each run shows its result, time and new tokens.
| Scenario | Codexwithout deft | Codexwith deft, skill installed | Claude Opus 5.5without deft | Claude Opus 5.5with deft, skill installed | Claude Codewithout deft | Claude Codewith deft |
|---|---|---|---|---|---|---|
| Validate against a schemaDoes config.yaml have a service object? Make schema.json requiring one, then validate config.yaml against it and write yes or no to result.txt. | pass21s · 7.6k | pass28s · 13.3k | pass18s · 9.2k | pass18s · 9.5k | not run | not run |