codex-orchestrate

Codex Orchestrate — you supervise a fleet of codex exec workers

Use when the user wants Codex to actually DO work at scale (implement N gaps, research N sources, review N dimensions) and you drive it — the manual equivalent of Codex's native ultra/multi_agent, but with no slot cap and with YOUR verification gate on every result.

Read prompt.md for the full loop, the exact dispatch command, and the verification checklist. The four rules that make it work (each learned from a real failure):

1. < /dev/null on every codex exec — it blocks on stdin EOF otherwise, even with the prompt as an arg, and hangs until timeout.
2. One isolated git worktree per worker off the latest main — parallel writers to shared build/test state race; core-engine changes merge sequentially so each builds on the last.
3. Verify independently — never trust the worker's self-report. Re-run the tests yourself (a worker reported "996 passed"; the real number was 995 + 1 real failure). For core-engine changes run the FULL suite, not just the new test.
4. Dispatch via a tracked background call (run_in_background), not & inside another command, or you lose the completion signal.

One more, observed on codex-cli 0.167.0 rather than learned from a failure: codex exec resume works in the directory you run it from, not the session's. Put -C <worktree> before resume, or the follow-up edits wherever you stand. To cancel, signal the session the dispatch records in <pgid-file>. prompt.md § Steer, cancel, follow up has both.