# We need Luna back as a valid override in multi\_agent\_v2 **URL:** \ **Category:** Codex CLI\ **Tags:** codex-cli\ **Created:** [July 31, 2026, 11:37pm UTC](https://community.openai.com/t/we-need-luna-back-as-a-valid-override-in-multi-agent-v2/1388619 "2026-07-31T23:37:47Z")\ **Posts on this page:** 1\ **Showing post:** 5
**Author:** ![VeitB](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/veitb/32/712987_2.png) [@VeitB](https://community.openai.com/u/VeitB)\ **Post date:** [August 17, 2026, 8:14am UTC](https://community.openai.com/t/we-need-luna-back-as-a-valid-override-in-multi-agent-v2/1388619/5 "2026-08-17T08:14:04Z")
Yes, since last week Luna agents can be used in the v2 multi-agent setup in Codex. I created a post about this here: > [@GPT-5.6 Sol can now delegate to Luna, plus other tips to save credits](https://community.openai.com/t/gpt-5-6-sol-can-now-delegate-to-luna-plus-other-tips-to-save-credits/1390765): > > We can now delegate to cheap, fast, and efficient Luna subagents in Codex. Support for Multi-Agent V2 was added this week. In fact, it is now possible to delegate to any supported model, not just Luna. A few tips to get more out of this recent Codex change, plus a handy skill template: With Codex, the other models become readily available tools inside the harness. You need to prompt the orchestrator not to simply spawn a copy of itself, but to select subagent capabilities based on the re… The question I have, @johnbernardcosgrove, is how you used Luna agents as little peer collaborators. I’m asking because the guidance has always been that these models simply aren’t capable enough to do exactly that. --- _[View the full topic](https://community.openai.com/t/we-need-luna-back-as-a-valid-override-in-multi-agent-v2/1388619)._