Comment by firloop
3 days ago
This is slightly different from what OpenCode was banned from doing; they were a separate harness grabbing a user’s Claude Code session and pretending to be Claude Code.
OpenClaw was still using Claude Code as the harness (via claude -p)[0]. I understand why Anthropic is doing this (and they’ve made it clear that building products around claude -p is disallowed) but I fear Conductor will be next.
[0]: See “Option B: Claude CLI as the message provider” here https://docs.openclaw.ai/providers/anthropic#option-b-claude...
and they’ve made it clear that building products around claude -p is disallowed
Imagine not being able to connect services together or compose building-blocks to do what you want. This is absolute insanity that runs counter to decades of computing progress and interoperability (including Unix philosophy); and I'm saying this as someone who doesn't even care for using AI.
But you can still integrate this (claude -p) into your local workflows when you basically want to pipe pipe stuff to Claude for inference
it's trivial to use tmux. But it does feels like openclaw is used (and increasingly developed) by people who never heard of it.
openclaw even ships with a built in tmux skill
Even better, running something like 'claude -p' at the command line is exactly the kind of thing a model would do. Mine loves to run python, node, and a dozen other applications.
They aren’t stopping anyone from using claude -p, they are just charging for that usage.
Except it's not counter to history for SaaS services. Many will ban unauthentic usage from non-human clients. Getting banned from a SaaS service for boting is nothing new
You absolutely can, just pay for their API usage. The subscriptions are deeply discounted if you use your full quota compared to the API.
It is confusing for a company to sell you the subscription service, say "Claude Code is covered", ship Claude Code with `claude -p`, and then say "oh right, actually, not _all of Claude Code_, don't try and use it as a executable ... sorry, right, the subscription only works as long as you're looking at that juicy little Claude Code logo in the TUI"
The disrespect Anthropic has for their user base is constant and palpable.
10 replies →
> building products around claude -p
But OpenClaw is not a product. It's just a pile of open source code that the user happens to choose to run. It's the user electing to use the functionality provided to them in the manner they want to. There's nothing fundamental to distinguish the user from running claude -p inside OpenClaw from them running it inside their own script.
I've mostly defended Anthropic's position on people using the session ids or hidden OAuth tokens etc. But this is directly externally exposed functionality and they are telling the user certain types of uses are banned arbitrarily because they interfere with Anthropic's business.
This really harms the concept of it as a platform - how can I build anything on Claude if Anthropic can turn around and say they don't like it and ban me arbitrarily.
Claude Code is not a platform and you’re not meant to be building on it. Netflix is also not a platform and you shouldn’t be running code (open source or not) to mass download Netflix movies either.
It's a reasonable comment, and I should be clear, I don't expect it to be a platform. But I do expect to be able to use its advertised features for any reasonable purpose they can support.
Where it leaves me is is sort of like the DoD - nobody should use Claude for anything. Because Anthropic has set as principle here that if they don't like what you do, they will interfere with your usage. There is no principle to guide you on what they might not like and therefore ban next. So you can't do anything you want to be able to rely on. If you need to rely on it, don't use Claude Code.
And to be clear, I'm not arguing at all against using their API per-token billed services.
1 reply →
https://code.claude.com/docs/en/overview#what-you-can-do
Try this one: https://code.claude.com/docs/en/overview#run-agent-teams-and...
Or perhaps: https://code.claude.com/docs/en/overview#pipe-script-and-aut...
You know what they say about looking and quacking.
Is using claude -p supposed to be dangerous? Could someone be confused as openclaw or other things?
If yes, why do Anthropic provide this cli flag?
Ah thank you, this is very helpful distinction to know.
When they shut down open code, I thought it was a lame move and was critical of them, but I could understand at least where they're coming from. With this though, it's ridiculous. Claude core tools are still being used in this case. Shelling out to it to use it there's no different than a normal user would do themselves.
If this continues, I'll be taking my $200 subscription over to open AI.
Im still using opencode with claude pro so im confused.
You're using it with a PAYG API key, not a subscription.
No a normal user is not shelling out to Claude Code 24/7, but OpenClaw certainly is.
OpenAI will soon do the same thing, don't be delusional.
If OpenAI does it too, well then I guess my principles will be challenged. Gemini CLI is unfortunately too eager to use Flash despite my setting it to use Pro, and it generates ass code that doesn't work, so that's out. I might have to invest in some GPUs then and run local. We'll cross that bridge when we get there though.
I’m also terrified of this.
When this happens I will have to look at other providers and downgrade my subscription. Conductor is just too powerful to give up. It’s the whole reason why I’m on a max plan.
I assume this means we can no longer use Claude code sessions in editors like zed because it also wraps claude cli via ACP?
ACP was a good idea but I feel it has not lived up to its potential.
Has there been an actual change to their ToS? As of the last change which I saw reach HN, a week or so ago, `claude -p` was still in compliance with the Claude Code ToS. Has that language changed?
Came here to say the same. I remember the discussion on HN back then where we discovered that an official from Anthropic made clear that claude -p was still okay.
I keep hearing OpenClaw runs on pi?
EDIT: confused by downvotes. In this thread people are saying it runs on top of `claude -p` and others saying it's on pi.
The `claude -p` option is allowed per https://x.com/i/status/2040207998807908432 so I really don't understand how they're enforcing this.
It runs on pi, not claude -p
That's my understanding too, though i haven't checked it. running claude -p would be horribly inefficient. I would not be surprised if openclaw added some compatibility layer to brute force prompts through claude -p as a workaround. This isn't the first time that openclaw was "banned" from claude subscriptions.
Why are they doing that? Opus is the only good way to run Claw. Do they regret making it cheaper or what?
Also what's the point of Claude -p if not integration with 3rd party code? (They have a whole agents SDK which does the same thing.. but I think that one requires per token pricing.) I guess they regret supporting subscription auth on the -p flag
> Opus is the only good way to run Claw
that's a ridiculous position to take - gemini and others work just great with claw...
Well, it might have been cargo culting but that was the consensus in the OC community a while ago.
5.4 and minimax 2.7 work nicely as well.
exactly. They probably have unsustainable margins on accident.