Skip to content
v0.15.29-codex.2MIT

Lauren Tan's pstack workflows adapted for native Codex skills and subagents.

benchmark-checklist

Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.

Read SKILL.md at the source

Pinned to revision ac6526d21fd2, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.