stbenjam/reviews
v0.0.6
Code review with specialist reviewers and runtime reproducers, plus guided eval and benchmark task walkthroughs
deep-review
Use when a deeper level of code review is requested. Multi-agent panel code review with specialist reviewers and forced runtime reproducers for all BLOCKING bug findings. Optionally posts to GitHub/GitLab as a PENDING review.
task-walkthrough
Walk through a Terminal-Bench task, internal eval, or benchmark task PR for a competent CS engineer, explain its verifier and review rubric, then check understanding with one applied question at a time. Use when the user wants to understand or present a task before reviewing it.