email validator
Ponytail vs caveman vs no-skill: same model, same tasks. Measures code LOC (deterministic) and token / email validator
Recent results
| Commit | Result | Score | Duration | Metadata |
|---|---|---|---|---|
| 1e356df 6 days ago | Fail | 0.00 | 0.1s | provider: openrouter:anthropic/claude-haiku-4.5, assertions: ["javascript","javascript"], judge: deterministic, couldnt_run: API error: 403 Forbidden |