A spec is a **build plan** while you're building and a **rationale record** once you've shipped. Closing flips it from one to the other. The plan was a ladder of slices and predictions; the record is the layer of meaning the code can't hold — why this exists, what it must never break, what you tri

Run [implement-spec](../implement-spec/SKILL.md) with Codex doing the implementation passes while you orchestrate, integrate, and review. Use when the user asks to implement a spec with Codex, or to run implement-spec with Codex as the implementer.

Use an unprimed sub-agent as a second set of eyes before accepting visual work. This is for visual defects, not pixel metrics; pair it with `compare-screenshots` when you also need numbers.

Write a live eval for new or changed runner/agent behavior using red/green TDD plus a falsification check that proves the eval fails when the behavior is broken. Use whenever you add or modify behavior that should be covered by an eval, when asked to "write an eval", "add an eval", "cover this with an eval", or after landing a feature that needs end-to-end proof it works.

Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skill versus references, scripts, assets, or ordinary docs.