Claude Code Routines

#1

Post by matthieu_bl » Tue, Apr 14, 2026, 4:54 PM UTC

Re: Claude Code Routines

#2

Post by minimaxir » Tue, Apr 14, 2026, 5:26 PM UTC

Given the alleged recent extreme reduction in Claude Code usage limits (https://news.ycombinator.com/item?id=47739260), how do these more autonomous tools work within that constraint? Are they effectively only usable with a 20x Max plan?

EDIT: This comment is apparently [dead] and idk why.

Re: Claude Code Routines

#3

Post by matthieu_bl » Tue, Apr 14, 2026, 5:29 PM UTC

Blog post https://claude.com/blog/introducing-routines-in-claude-code

Re: Claude Code Routines

#4

Post by bpodgursky » Tue, Apr 14, 2026, 5:30 PM UTC

OpenClawd had about a two week moat...

Feature delivery rate by Anthropic is basically a fast takeoff in miniature. Pushing out multiple features each week that used to take enterprises quarters to deliver.

Re: Claude Code Routines

#5

Post by summarity » Tue, Apr 14, 2026, 5:31 PM UTC

If you’re trying this for automating things on GitHub, also take a look at Agentic Workflows: https://github.github.com/gh-aw/

They support much of the same triggers and come with many additional security controls out of the box

Re: Claude Code Routines

#6

Post by ctoth » Tue, Apr 14, 2026, 5:31 PM UTC

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?

Re: Claude Code Routines

#7

Post by nightpool » Tue, Apr 14, 2026, 5:33 PM UTC

bpodgursky wrote: post #4

OpenClawd had about a two week moat... Feature delivery rate by Anthropic is basically a fast takeoff in miniature. Pushing out multiple features each week that used to take enterprises quarters to deliver.

Do you mean a 3 months moat? Moltbot started going viral in January. That seems to be about a quarter to deliver to me : )

Re: Claude Code Routines

#8

Post by whicks » Tue, Apr 14, 2026, 5:34 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?

I would imagine that this sort of scheduling allows them to have more predictable loads, and they may be hoping that people will schedule some of their tasks in “off hours” to reduce daytime load.

Re: Claude Code Routines

#9

Post by whalesalad » Tue, Apr 14, 2026, 5:34 PM UTC

bpodgursky wrote: post #4

OpenClawd had about a two week moat... Feature delivery rate by Anthropic is basically a fast takeoff in miniature. Pushing out multiple features each week that used to take enterprises quarters to deliver.

Hard to wanna go all-in on the Anthropic ecosystem with how inconsistent model output from their top-tier has been recently. I pay $$$ for api-level opus 4.6 to avoid any low-tier binning or throttling or subversive "its peak rn so we're gonna serve up sonnet in place of opus for the next few hours" but I still find that the quality has been really hit or miss lately.

The bell curve up and then back down has been so jarring that I am pivoting to fully diversifying my use of all models to ensure that no one org has me by the horns.

Re: Claude Code Routines

#10

Post by slopinthebag » Tue, Apr 14, 2026, 5:35 PM UTC

bpodgursky wrote: post #4

OpenClawd had about a two week moat... Feature delivery rate by Anthropic is basically a fast takeoff in miniature. Pushing out multiple features each week that used to take enterprises quarters to deliver.

You're delusional if you think these features would take competent programmers quarters to deliver.