Casso

How-to

How to Annotate Screenshots for OpenAI Codex

Step-by-step: mark UI regions, write short notes, and paste a vision-ready prompt into Codex without wasting turns.

Published 2026-07-24

Why Codex still needs a map

Codex can take images and paths. It cannot read your mind about which of five similar buttons is wrong. Annotation turns a screenshot into instructions.

Vision models interpret pixels; they do not magically know your priority. On a dense settings page, three toggles can look identical at a glance. A number badge and a one-line note remove the coin flip.

Step-by-step with Casso

A fast path that stays local and works with Codex CLI or any Codex surface that accepts an image or path:

  • Open the UI state you want fixed (right theme, breakpoint, and data).
  • Hotkey Casso and drag numbered boxes over each region.
  • Add a short note per box: what is wrong and what good looks like.
  • Send. Copy the prompt into Codex with the annotated image.
  • Ask Codex to change only the referenced regions unless you want a broader pass.
  • Re-run the UI, re-annotate only remaining issues, and iterate.

Prompt patterns that work

Lead with the goal, then the map: "Match spacing of [2] to [1]. Do not change colors." Avoid burying the request after a long story. One issue per region beats a paragraph that mixes five problems.

Add hard constraints when the codebase is large: "Touch only the component that renders [1]. No drive-by refactors." That keeps Codex from rewriting unrelated layout systems.

Pair marks with acceptance checks: "After the change, [1] should have 16px padding and no double border." That turns a visual complaint into a verifiable request.

Same overlay as Claude Code

Casso is not embedded in Codex or Claude Code. You keep one desktop gesture when you hop between them. That is the point of an agent-agnostic layer: the map stays the same; only the paste target changes.

Common mistakes

Most failed visual turns share the same mistakes. Avoid these and your first-pass hit rate jumps:

  • Huge full-desktop shots with a tiny target and no mark.
  • Arrows without numbers when you discuss multiple areas.
  • Notes that say "fix this" without expected behavior.
  • Uploading sensitive screens to random web tools before the agent.
  • Mixing five issues into one box so the model only fixes the first.

FAQ

Related

Try Casso free for 7 days

Numbered screen annotations for Claude Code, Codex, and other agents. 7-day free trial, then $29 once - not a subscription.