Every real run, newest first unless a column says otherwise. Open one to see the page the agent wrote, its violations and what each step cost.
Only runs of rule token-roles/wrong-role (remove).
| Task | Model | Context | Design system | Quality | Done | Steps | Cost | When ↑ |
|---|---|---|---|---|---|---|---|---|
| kyc-form | gpt-6-luna | ds-mcp | 5 | 32 | Done | 4 | $0.0033 | Nov 9, 07:37 |
2 runs match.
| transfer-form |
| gpt-6-luna |
| ds-mcp |
| 4 |
| 8 |
| Done |
| 7 |
| $0.0032 |
| Nov 9, 07:40 |