SWE-Lego

Use when resolving software issues, fixing bugs, or implementing fixes that need quality assurance — orchestrates automated patchgen, independent code review via subagent, and revision loop until approved or max rounds reached

Use when reviewing code changes, patches, or PRs for correctness — performs independent root-cause reconstruction before reading the patch, then compares to detect symptom fixes, missing sibling fixes, and broken dependencies

Create or reuse Hugging Face dataset PRs for `harborframework/parity-experiments` and upload Harbor parity/oracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS.