I discovered the wildest feature of GitHub Copilot CLI by complete accident last night. You can have models call each other. So you can have Opus, Codex and Gemini all working together in the same chat.🤯

@github i use claude to run codex because i hate interacting with 5.2 on a personal level 😂

@github Does this count as one premium request? Or multiple?

@github GREAT question. I have no idea. @pierceboggan do you know how the billing works here?

@github That is really cool indeed, but isn’t this how agents are designed? For each agent definition you can specify the model explicitly. Or do you mean it spawned the agents ad-hoc with the requested models without being specified up front in your config?

@github Interesting... So the model has to be Auto? Or not necessarily?

@github No! It can be any model! That said some models are gonna suck at following your instructions *cough* gpt-5-mini *cough* and might not actually call the subagents correctly.

@github Do you know what I saw this a while back from the amazing @_Evan_Boyle but then completely forgot about it - so thanks again for the reminder! I need to definitely use this more!!!

@github I use it to analyze the content from a screenshot or photo from opus in a haiku sub agent, saves a lot of context, and a bit faster.

@github Nice flow - I'll have to try it

@github I have been using that workflow for a few weeks now (since it released). I no longer use VS Code chat and I'm using 100% Copilot CLI, it's just better. I just switched from VS Code Insiders to the blue logo, since all the updates come from Copilot CLI now :)

@github You can do this in @code now too!

@github It’s over , It’s over we are cooked. The beast is out of the cage and there’s no hitting pause now. 💀🔥

@github So cool! I think we have the great Steve Sanderson to thank for that, he demoed running a prompt on 3 models simultaneously last week. This is an even better use-case for that capability in Copilot CLI - now we need that in Copilot Chat in VSCode assuming we don't have that yet.

@github where is gemini pro? Seems missing for some but not others...@pierceboggan

@github Multi-model orchestration is a game changer. Each model has different strengths, being able to route tasks to the right one automatically is the future of AI tooling.

@github Can OpenCode do this, @thdxr ?

@github Each skill defined can be tied to a model and in your prompt you can also tell it to use a certain skill for a certain part, then it will sub agent the call - which doesn't cost extra tokens, only the first premium token is counted.

@github This is the way :)

@github I wish when you create custom agents, like " the model would automatically switch to the custom agent rather having to say "using csharp-expert agent do X and y".. It even ignores top level instructions like, "when writing c# use the csharp-expert agent"

@github Works in the cli 🤯 but not on vs code

@github I think it will work in @code though cc: @pierceboggan

@github Is it running subAgents with the specified models you told it to. Its kinda crazy,

@github Are you sure its not a hallucination?

@github The thought did cross my mind, but I doubled checked with the team and it is not.

@github Wow thats amazing! Did it call the other models through a tool call?

@github Yes - it appears like it's a tool call

@github It's a bug. Wait, it just became a feature

@github Good to know! I had assumed this would be a standard feature of AI assistants, if not already. I wouldn’t really want to use an AI assistant tool that forces everything to go through the same model, when different models have different strengths.

@github does each sub agent cost each their own usage?

@github …🦝

@github I do this manually today.

@github 🤯This is an incredible advantage for multi-model harnesses over single-model harnesses!

@github RIGHT?!?! Why on earth would you lock into one model?

@github What if I use the cheaper model to call the more expensive model to do the work? 🤔

@github Have you tried it with code-review or speckit? I could see multiple models double checking the review, plan or tasks phase. I have actually been swapping a bit to gemini for `/speckit.plan` as it has such a bigger context windown and web_searches easier

@github Make a skill in claude to call codex (or any other cli coding agent). Only one tool needed, leverages many models as you wish

@github Sometimes these accidental discoveries lead to the most innovative uses. I've stumbled upon similar unexpected features while building my app, it's amazing what you can find when you're not looking.

@github Bravo, thanks for sharing!

@github Super awesome to see this. I wasn't aware either!

@github WOOOCOOL!🔀

@github this is wild man, collaboration just got a whole new level fr

@github Interesting, must try

@github I can't believe this isn't a bigger deal. This seems like a massive unlock, but I'm not 100% sure what workflows it unlocks. Which is like, just another day with AI.

Wow. I am not a coder but have managed to build a site and am using copilot with Opus, Gemini, ChatGPT Codex, and a few others. I’ve been looking into extensions to use them as a team/swarm to fix bugs and build faster. If this can be done my adding the directions at the end of the prompt, that would be amazing. Is that all you are doing?

@hirletz @github That's all I did here. But you could create custom agents that do this. Agents that call agents that call agents, etc. Basically orchestration. Something like

@github Multi-model chats are fun until coordination debt hits: shared context, conflicting tool calls, unclear source-of-truth. Do you run a single orchestrator + specialist workers (with state), or let them free-for-all?