Flight Log / repository
willccbb/verifiers — agent flight log
10 pull requests opened by AI coding agents in willccbb/verifiers (★ 4,776, Python): Cursor (Anysphere) 8 (100% merged), Claude Code (Anthropic) 1, OpenAI Codex (OpenAI) 1 (0% merged).
Flights by agent
| Agent | Flights | Merge rate | Median to merge | Burn rate |
|---|---|---|---|---|
| Cursor (Anysphere) | 8 | 100% | 5.5 h | 0% |
| Claude Code (Anthropic) | 1 | — | — | — |
| OpenAI Codex (OpenAI) | 1 | 0% | — | 0% |
By month
| Month | Flights | Merged | Burns |
|---|---|---|---|
| 2025-06 | 1 | 0 | 0 |
| 2025-07 | 9 | 8 | 0 |
Last 10 flights
| PR | Title | Agent | Opened | Lines | |
|---|---|---|---|---|---|
| #166 | Benchmark review and improvement with gpt-4.1-mini | Cursor | Merged clean | Jul 28, 2025 | +584 −651 |
| #161 | Create and evaluate a new environment with a dataset | Cursor | Merged clean | Jul 27, 2025 | +430 −174 |
| #160 | Create and evaluate a new Hugging Face environment | Cursor | Merged clean | Jul 27, 2025 | +1,417 −799 |
| #147 | feat: Add support for multiple tool calls in a single message | Claude Code | Stale | Jul 18, 2025 | +613 −33 |
| #142 | Update library documentation for clarity and accuracy | Cursor | Merged clean | Jul 15, 2025 | +2,844 −2,495 |
| #141 | Update tests for refactored environment and parser components | Cursor | Merged clean | Jul 15, 2025 | +1,571 −643 |
| #124 | Re-add RubricGroup tests and fix errors | Cursor | Merged clean | Jul 4, 2025 | +288 −94 |
| #123 | Create minimal pytest setup for tests | Cursor | Merged clean | Jul 4, 2025 | +3,056 −210 |
| #122 | Identify improvements for RTD documentation | Cursor | Merged clean | Jul 4, 2025 | +1,896 −2,121 |
| #76 | Add functional parser and rubric tests | OpenAI Codex | Abandoned | Jun 6, 2025 | +480 −579 |
No rider has claimed a flight in this repository yet. Flew one of these? Open your flight page and claim it.
Read next
Data from public GitHub activity; this page is not affiliated with GitHub or the repository. Repository owner? Request exclusion — handled within 48 hours.