Monitor account caps and move chats across tools
teivz built a local app that watches Codex and Claude Code account usage and shifts a chat to another account when one reaches its cap.
- What they did
- teivz was using a group of Codex and Claude Code logins and kept losing momentum when one ran out of allowance. To cut down on manual copying, they made a local utility with a browser-based interface on their machine. It gathers every account’s usage in one place and can move an ongoing conversation to a different account once the current one is maxed out.
- How it went
- The writeup does not give benchmarks or show whether the handoff keeps the full thread intact. It does mention extra functions such as picking accounts manually, organizing media files, searching past sessions, and tying into other services, and teivz asked others to comment on it.
- Tips
- If you want to copy the idea, first verify how the tool reconstructs context after a switch. Check whether it is actually installable or only a personal build before you plan to depend on it.
Try it yourself with Codex
Make a local app for [number] Codex and Claude Code accounts that puts usage status for each account on one screen and alerts me when any account is close to its limit. When a limit is reached, draft a short handoff summary with the current goal, files changed, and next steps, then stop and ask for my approval before anything is sent to a different account or any account settings are changed. Add optional manual account picking, session history search, media file handling, and integration hooks.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Build a five-step feature pipeline with approval gates
A solo SaaS founder used chained Claude Code commands to turn ideas into shipped features with less token use and faster turnaround.
Use a long-running agent to chase a stubborn bug
A developer let Codex work overnight against a repeatable test, using debug prints and hypotheses to track down an unexplained bug.
Use a coding agent to fix a Slack-reported bug
A Codex agent handled a Slack issue on its own, and an ops agent later confirmed the fix in the same thread.
Run agent coding jobs in a sealed local box
A developer used Codex to run an almost fully self-contained build-and-deploy workflow on a locked-down spare machine.
Match a pull request to repo style
A developer used Claude Code to bring a pull request in line with a repo’s style, but it only altered comments and left the code unchanged.
Use Claude Code to spot macOS layout bugs
A developer let Claude Code compile a Mac app, open it, and click through screens to find visual problems.