Every message you send uses part of your plan's limit. A long-form video is a lot of messages. These habits are how one video fits inside my plans without hitting the wall halfway.

1. Approve before anything expensive

The expensive steps are the ones that make files: Codex rendering graphics, Claude rendering previews. The cheap steps are reading and marking. So I put an approval in front of every expensive step:

  1. Script approved
  2. A-roll lock: I approve the cut before anything gets timed. Every trim after timing moves every graphic.
  3. Storyboard approved: every card says Looks right before Codex builds. Mocks are cheap; renders aren't.
  4. Codex renders
  5. Chapter review: one chapter at a time, so a fix touches one chapter, not the whole video

<aside> ✅

Best practice: catch changes as early as you can. A change at the storyboard costs a note. The same change after the render costs a re-render.

</aside>

2. Write state to files, not the chat

A new session doesn't remember the last one. If the state lives in a file, the new session reads one file. If it lived in the chat, the new session re-reads everything to figure out where you were.

When I measured one of my videos, about 80% of Claude's tokens went to re-reading earlier context. Long sessions are where the usage goes.

3. One task per session

Claude Code Codex
Start fresh /clear /new
Shrink a long session /compact /compact
See how much you've used /usage /status
Switch model or effort /model, /effort /model

<aside> ✅

Best practice: in Claude Code, start fresh or compact. Never let a session just keep growing.

Every message re-reads the whole session so far. That re-reading was about 80% of my Claude usage on one video.

</aside>

<aside> 💡

Tips

4. Turn repeat work into tools