Claude Code Routines • Hacker News Board

Re: Claude Code Routines

#21

Post by dmix » Tue, Apr 14, 2026, 5:45 PM UTC

netdur wrote: post #17

didn’t we have several antitrust cases where a vendor used its monopoly to disadvantage rivals? did not anthropic block openclaw?

How is Anthropic a monopoly? The market is barely even fully developed and has multiple large and small competitors

Re: Claude Code Routines

#22

Post by nico » Tue, Apr 14, 2026, 5:45 PM UTC

Nice, could this enable n8n-style workflows that run fully automatically then?

Re: Claude Code Routines

#23

Post by mkw5053 » Tue, Apr 14, 2026, 5:46 PM UTC

vessenes wrote: post #12

This is one of the best features of OpenClaw - makes sense to swipe it into Claude Code directly. I wonder if Anthropic wants to just make claude a full stand-in replacement for openclaw, or just chip away at what they think the best features are, now that oAI has acquired.

What are some of the best use cases you've found? I have some gh actions set up to call claude code, but those have already been possible.

Re: Claude Code Routines

#24

Post by iBelieve » Tue, Apr 14, 2026, 5:47 PM UTC

ctoth wrote: post #6

You'd think that if they were compute-limited ... Trying to get people to use it less ... The rational thing to do would be to not ship features that will use more compute automatedly? Or does this use extra usage?

Max accounts get 15 daily runs included, any runs above that will get billed as extra usage.

Re: Claude Code Routines

#25

Post by andai » Tue, Apr 14, 2026, 5:47 PM UTC

I'm a little confused on the ToS here. From what I gathered, running `claude -p ` on cron is fine, but putting it in my Telegram bot is a ToS violation (unless I use per-token billing) because it's a 3rd party harness, right? (`claude -p` being a trivial workaround for the "no 3rd party stuff on the subscription" rule)

This Routines feature notably works with the subscription, and it also has API callbacks. So if my Telegram bot calls that API... do I get my Anthropic account nuked or not?

Re: Claude Code Routines

#26

Post by mellosouls » Tue, Apr 14, 2026, 5:49 PM UTC

Put Claude Code on autopilot. Define routines that run on a schedule, trigger on API calls, or react to GitHub events...

We ought to come up with a term for this new discipline, eg "software engineering" or "programming"

Re: Claude Code Routines

#27

Post by watermelon0 » Tue, Apr 14, 2026, 5:50 PM UTC

Seems like it only supports x86_64. It would be nice if they offered a way to bring your own compute, to be able to work on projects targeting arm64.

Re: Claude Code Routines

#28

Post by crooked-v » Tue, Apr 14, 2026, 5:50 PM UTC

The obvious functionality that seems to be missing here is any way to organize and control these at an organization rather than individual level.

Re: Claude Code Routines

#29

Post by varispeed » Tue, Apr 14, 2026, 5:51 PM UTC

Why would you use it if you don't know whether the model will be nerfed at that run?

Re: Claude Code Routines

#30

Post by outofpaper » Tue, Apr 14, 2026, 5:52 PM UTC

nico wrote: post #22

Nice, could this enable n8n-style workflows that run fully automatically then?

Yes but much less efficiently. Having LLMs handle automation is like using a steam engine to heat your bath water. It will work most of the time but it's super inefficient and not really designed for that use and it can go horribly wrong from time to time.