Is that still needed now that Agent SDK usage is included in subscriptions?

https://support.claude.com/en/articles/15036540-use-the-clau...

  Update October 7, 2026: Claude Max, Ultra, and Team plans now include monthly API credits. They cover the Claude API, Claude Managed Agents, and the Claude Agent SDK and claude -p when you run them with an API key from your linked Claude Console organization. Nothing changes for your plan: when you’re signed in with your Claude plan, the Claude Agent SDK and claude -p still draw from your subscription limits.

Anthropic's subscription is the one that has historically been tough to use with other harnesses, where they have (had?) technical safeguards to ensure your subscription usage was limited to Claude Code CLI, with third party harnesses often implementing workarounds or faking it to use your Claude.ai subscription. Nowadays Jetbrains Air does officially allow using your Claude.ai subscription.

But OpenAI's subscription has seemingly always been available to use in other harnesses without trouble.

Yes, you can use your Codex subscription with Pi without any limitations. It supports Codex out of the box. You may need to install extensions for things like tracking usage and limit resets though. Pi only provides basic Codex integration.

Yes. You can and it's easy to test. I'd also encourage you to try local models with it as well.

Pi/opencode apparently make 10% already of all traffic already:

https://manifest.build/blog/chatgpt-plus-tokens-third-party-...

This, IMO, is one big selling point of Codex for me. The are much more accepting of usage outside of the Codex harness, and make it trivial to set up.

Yes and no. Any harness can use the subscription but must go through `claude -p` mode, which is more limited.

Yes, it is allowed and supported normally by pi and others.

Claude now supports AGENTS.md fully but the rest of what you said holds

Alas Opencode's source is hideous to read.

When you say "kinda dumb" it's worth noting that the smaller coding models tend not to actually need system prompts to be helpful coding assistants, etc. Qwen maybe more than Muse Glimmer? I've not tested Qwen 3.8 27B enough yet. Even Gemma 4 didn't seem to need much.

Muse Glimmer is so absolutely tuned for one particular pattern (turn-by-turn agentic coding and assistance) that it will do it more or less without a prompt at all (except to set the reasoning level maybe). Beyond the tools announcement, it feels to me like it almost only needs a prompt to do plan mode stuff. If LM Studio (in either of its forms) or Unsloth Desktop had proper support for running inside a linux container rather than just a filesystem sandbox, you'd barely need a dedicated coding agent at all. Osaurus gets even closer.

I wanted to like Opencode but I can't, really. I am enjoying Pi slightly more because it's just way less convoluted and obscure.

FWIW I use Paseo for the GUI, which to some extent eliminates that aspect of decision fatigue; if you like Paseo's UI well enough, you can have it with almost any harness. And since it can connect to its daemon via ssh you can still have the desktop GUI with a container. (Not clear to me if Opencode v2 Desktop makes remote connections to the daemon or just wraps the web interface like v1 did)

Opencode's system prompt is much smaller than omp. Smaller models may not work well just because of this. Also omp is not pi.

ohmypi is not pi, it's based on pi, but it's not pi.

Man, my M1 Pro unfortunately only has 16GB of RAM; it has been such a limiter to using local models. I'll give kapitsa a try, I see I should be able to squeeze some smaller models on

Alternatively, what you’re seeing is continuous hill climbing and optimisations based on large scale experiments and simulated rollouts.

For me personally, I don’t use Claude Code because I can’t read the source.

At least with Codex, I know there’s a bunch of telemetry and all that, but I can have my agent inspect the source and have relatively greater confidence it’s not implanting spyware onto my machine, because a classifier thinks I’m working for Deepseek or something.

'Tis a joke. His landing page says he's a dev at Salesforce, so I presume not famous.

I’m definitely not famous :^) thanks for reading!

>> Someone at Anthropic must’ve caught wind… just a day after making my decision, they announced Claude Code would finally start supporting AGENTS.md files in an effort to get me to stay.

> Forgive me for asking if I should know, but who is the author? Is he famous?

I think that was tongue in cheek. And by that I don't mean the author's tongue was actually in his cheek.

I also think it went over your head. And by that I don't mean I think it literally went over your head.

> At this point, you probably don't need either.

There's only so much stuff I have the patience to tell it in a session before I write it down somewhere.

Made me click, but I have no idea what this is supposed to be.