Auto-continue Codex CLI after a usage limit

Codex hit its usage limit halfway through a refactor. The reset’s four hours away and you’d rather be asleep than babysitting it.

Codex CLI won’t pick it back up on its own. Agent Auto-Continue will. It’s a free macOS menu-bar app that sends “Continue” into your Codex thread as soon as the limit resets.

What Codex already does

• Plus and Business get a five-hour allowance (Pro currently has no five-hour limit), and weekly limits may apply too (OpenAI’s pricing page).
• Hit the limit mid-turn and Codex lets that turn finish, within fair use (same page).
• After that it waits for you. There’s no auto-resume setting, and the feature request to sleep until the known reset time, then carry on, is still open.

What the app adds

• When free. Codex reports its rate limits with reset times, so the app starts as soon as the limit lifts. Or pick a time and have it wait for the limit too. Nothing goes out while the limit holds.
• More than one turn. Up to a set number, or until you stop it. Turns that end at a usage limit don’t count. Add a stop phrase like TASK COMPLETE and it finishes when Codex’s last message contains it (whole words, any case, completed turns only).
• Proven delivery. Each message carries an ID the app then looks for in the thread. If it can’t tell, it marks the message unconfirmed and never resends.
• Manners. It re-checks the thread first and won’t send if it’s gone, archived or you’ve replied since. A one-off message waits up to six hours for a busy Codex.

It speaks Codex’s own app-server protocol, through the shared codex app-server daemon if one’s running, a private one if not. No fake keystrokes, no remote service, no changes to Codex (verified with codex-cli 0.159).

Set it up

1. Install the Codex CLI and sign in. If the app can’t find codex, set its path in Settings > Agents.
2. Download the disk image (button at the bottom), drag the app into Applications and open it. macOS asks once whether to open an app from the internet; choose Open.
3. Click the menu-bar icon and pick your Codex thread.
4. Choose when: When free, or a time with the “wait for it” box ticked.
5. Choose how far: Once, Up to a number of turns, or Until done. For a stop phrase, ask Codex to end its final message with it when done.
6. Press Continue. The line under it says what’ll happen.

The Codex CLI list shows CLI-created threads, codex exec runs included. T3 Code and ChatGPT app threads sit under those apps instead (both supported).

The honest limits

• Approval prompts pause it. Nobody’s there to approve, so the turn’s interrupted and the chain waits. Run Codex with approval settings you’d happily leave overnight.
• Your Mac has to be awake and the app running. Missed schedules catch up after wake, and keep-awake is opt-in.
• Quitting the app leaves a turn in the shared daemon running, but interrupts one the app started through a private server.
• Runaway chains pause. Three usage-limited turns in a row do it. So will three completed turns in a row that each took under a minute (the task may be done).

The terminal wrappers

If you live in a terminal, these work:

Tool	How it works	At a usage limit
codexc	macOS tmux wrapper; retries transient errors, queues timed prompts	Deliberately doesn’t continue
codex-auto-continue	Linux tmux watcher; sends your prompt after every completed turn	Pauses until you resume
codex-continue	Expect-style wrapper you run Codex through	Sleeps until the printed “try again at” time, types Continue

All three need Codex running in a terminal session they control, and none has a stop phrase or GUI. The app works on threads you already have and reads the reset time from Codex’s protocol, not error text. Already in a terminal and only need a “Continue” after each reset? codex-continue does that fine.