Claude Code Routines
Ranked 3 of 10 coding agent features by recommenders
People recommend it for running Claude Code on a timer in Anthropic's cloud, replacing self-hosted cron jobs; the common caveat is unreliability and vendor lock-in.
People recommend it for running Claude Code on a timer in Anthropic's cloud, replacing self-hosted cron jobs; the common caveat is unreliability and vendor lock-in.
43 people gave an opinion
- recommend it
- 16
- criticize it
- 27
- approval share
- 37%
Recommended in 2 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 16 people recommend itNeeds 10 or more, met.
- 0.5 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 2 of 13 monthsNeeds 4 or more, not met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Replaces self-built scheduled agent setups
“This is a smarter, faster, easier, and likely far more secure way of implementing the same thing”
Comment from 15 Apr 2026 in “Claude Code Routines” “I have no qualms using a convenient feature I could reimplement myself, it saves me time.”
Comment from 15 Apr 2026 in “Claude Code Routines” “Claude Routines/Scheduled agents can replace all the tasks I use OpenClaw for”
Comment from 9 Jun 2026 in “Claude Fable 5” - Comment from 24 Apr 2026 on Hacker News
Quick and easy to start
“This is a smarter, faster, easier, and likely far more secure way of implementing the same thing”
Comment from 15 Apr 2026 in “Claude Code Routines” “A Claude Routine would've been significantly easier”
Comment from 24 Apr 2026 on Hacker News “It's almost too easy to spin a new one up.”
Comment from 24 Apr 2026 on Hacker News Many automation use cases
“Once setting the cron job itself is free, you could think of a lot of use cases.”
Comment from 15 Apr 2026 in “Claude Code Routines” “This wild, one of the pieces I was lacking for a very openclaw-esque future.”
Comment from 14 Apr 2026 in “Claude Code Routines”
What people warn about
Each mark is one comment
Requires routing data through Anthropic's cloud
“I wish they'd release more stuff that didn't rely on me routing all my data through their cloud to work.”
Comment from 14 Apr 2026 in “Claude Code Routines” “That's all this "routines" thing is, it's just an agentic loop they launch in their cloud on a timer.”
Comment from 15 Apr 2026 in “Claude Code Routines” “I never want to outsource something so simple to a live service.”
Comment from 15 Apr 2026 in “Claude Code Routines” - Comment from 14 Apr 2026 in “Claude Code Routines”
Vendor lock-in concerns
“vendor specific, "bonuses" sounds like a way to try to lock people in”
Comment from 14 Apr 2026 in “Claude Code Routines” “it's something that keeps you from ever switching off Claude”
Comment from 14 Apr 2026 in “Claude Code Routines”
Other coding agent features people recommend
The four most recommended other coding agent features, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Claude Code plan mode | 41 | 22 | 65% | 11 | — | — |
| Claude Code auto mode | 20 | 29 | 41% | 6 | — | — |
| Claude Code RoutinesThis page | 16 | 27 | 37% | 2 | — | — |
| Claude Code Dynamic Workflows | 13 | 10 | 57% | 4 | — | — |
| Claude Code Ultracode | 12 | 13 | 48% | 4 | — | — |
What people said
40 of the 47 comments that mention it, newest first. Each links to the original comment.
“Claude Routines/Scheduled agents can replace all the tasks I use OpenClaw for”
“I couldn't think of anything useful to do with the routines”
“It's almost too easy to spin a new one up.”
“A Claude Routine would've been significantly easier”
“major vendor lock-in + hazy perspective”
“Now use it less and use more Claude Code Remote Routines”
“The trigger matrix here is actually the most interesting part.”
“Once setting the cron job itself is free, you could think of a lot of use cases.”
“I tried routines and they didn’t actually work.”
“moving your tech debt into a proprietary format”
“That's all this "routines" thing is, it's just an agentic loop they launch in their cloud on a timer.”
“you only have one at a time per suscription”
“90% of the time the automation never even runs.”
“I never want to outsource something so simple to a live service.”
“there is a limited way to configure it with other models”
“throw sh*t at the wall and see what sticks”
“It was a bit buggy, but it seems to work better now.”
“I have no qualms using a convenient feature I could reimplement myself, it saves me time.”
“This is a smarter, faster, easier, and likely far more secure way of implementing the same thing”
“But when I try to create a routine, the only GitHub events available in the drop down related to pull requests and releases.”
“The cap of 15 automatic Claude Code Routines runs per day is a bit low.”
“Friction. That's all it takes to lock users in.”
“it's something that keeps you from ever switching off Claude”
“There is no reason to believe Co-work/Routines/Skills will survive 5 years from now.”
“I love this feature very much, when it works. And it mostly doesn't.”
“you shouldn't bother using /loop, code routines, etc.”
“Now they’re trying to back track that with a cloud solution.”
“This is useful functionality but also seems very straightforward.”
“Buying in to things like this would make that much harder.”
“I wish they'd release more stuff that didn't rely on me routing all my data through their cloud to work.”
“This wild, one of the pieces I was lacking for a very openclaw-esque future.”
“vendor specific, "bonuses" sounds like a way to try to lock people in”
“The Chilling Effect of this is real and it gets more and more frustrating that they can't or won't clarify.”
“7 days is long enough for work to leave the context window”
“Very useful, (when it works).”
“Why would you use it if you don't know whether the model will be nerfed at that run?”
“any way to organize and control these at an organization rather than individual level”
“Seems like it only supports x86_64. It would be nice if they offered a way to bring your own compute”
“the $200/mo subscription is markedly cheaper than per-token API billing”
“at the end of the day this is yet another way of injecting data into a prompt”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.