Plans are treated as first-class artifacts. Ephemeral lightweight plans are used for small changes, while complex work is captured in blog post - OpenAI's Codex execution plans 2025-10 with progress and decision logs that are checked into the repository. Active plans, completed plans, and known technical debt are all versioned and co-located, allowing agents to operate without relying on external context.
...
I wan't sure I had gotten this in my free recall, but it looks like I did. coding agent operating without external context makes it seem like they don't rely on something like github issues or Beads, but they do, also... just at a higher level.