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"
It's "promptramming".
Claude Code Routines
121–130 of 451 posts
Re: Claude Code Routines
#122LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…
I believe it doesn't matter, other companies will copy or improve it. The same happend with clawdbot, the amount of clones in a month was insane.
Re: Claude Code Routines
#123Earlier quoted context omitted.
The restrictions are dumb not because they're lower than any of us want them to be, but because they're unclear. Every time Claude comes up on Hacker News, someone asks this question. And every time people chime in to agree that they also are unclear or someone weighs in saying, no, it's totally clear, while proceeding not to point at any official resource and/or to "explain" the rules in a that is incompatible with…
You are arguing something different. My point is that they must apply these restrictions. Do I think they could have calculated their growth a little better? Yes, of course, but hindsight is 20/20.
We might be talking past each other, I promise I'm not just trying to argue.
> My point is that they must apply these restrictions.
I fully understand and respect they need restrictions on how you can use your subscription (or any of their offerings). My issue is not there there _are_ restrictions but that the restrictions themselves are unclear which leads to people being unsure where the line is (that they are trying not to cross).
Put simply: At what point is `claude -p` usage not allowed on a subscription:
- Running `claude -p` from the CLI?
- Running `claude -p` on a Cron?
- Running `claude -p` as a response to some external event? (GH action, webhook, etc?)
- Running `claude -p` when I receive a Telegram/Discord/etc message (from myself)?
Different people will draw the line in different places and Anthropic is not forthcoming about what is or is not allowed. Essentially, there is a spectrum between "Running claude by hand on the command line" and "OpenClaw" [0] and we don't know where they draw the line. Because of that, and because the banning process is draconian and final with no appeals, it leads to a lot of frustration.
[0] I do not use OpenClaw nor am I arguing it should be allowed on the subscription. It would be nice if it was but I'm not saying it should be. I'm just saying that OpenClaw clearly is _not_ allowed but `claude -p` wouldn't be usable at all with a subscription if it was completely banned so what can it (safely) be used for?
Re: Claude Code Routines
#124Haven't Github-triggered LLMs already been the source of multiple prompt injection attacks? Seems bad.
Re: Claude Code Routines
#125If 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
+1 for that, having that said, because GH agentic workflows require a bit more handholding and testing to work, (and have way more guardrails, which is great, but limiting), and lack some basic connectors (for example - last time I tried it, it had no easy slack connector, I had to do it on my own). This is why I'm moving some of the less critical gh-aw (all the read only ones) to Claude Routines.
Re: Claude Code Routines
#126This is massive. Arguably will be the start of the move to openclaw-style AI. I bet anthropic wants to be there already but doesn't have the compute to support it yet.
What’s massive about cron jobs and webhooks? I feel like I’m missing something. This is useful functionality but also seems very straightforward.
Re: Claude Code Routines
#127One gripe I have with Claude Code is that the CLI, Desktop app, and apparently the Webapp have a Venn Diagram of features. Plugins (sets of skills and more) are supported in Code CLI, maybe in Cowork (custom fail to import) but not Code Desktop. Now this? The report that they are 90% Ai code generated seems more likely the more I attempt to use their products.
Their source code leak showed how badly vibe coded Claude Code is, despite it being one of the best AI assistants.
But yea there's some annoying overlap here with Cowork which also has scheduled tasks, in Cowork the tasks can use your desktop, browser and accounts which is pretty useful - a big difference from these Claude Code Routines.
Re: Claude Code Routines
#128I'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…
The ambiguity is intentional. Like Microsoft not banning volume licenses. They want to scare you, so you don't max out your subscription – which they sell at a loss. Another comparison would be "unlimited storage", where "unlimited" means some people will abuse it and the company will soon limit the "unlimited."
Literally yeah, the ambiguity is just so they can boycott anytime they want, people underestimate Anthropic too much, obviously they have insane amount of scrappers, bots... no comments online is made without their awareness and analyzed by a bunch of agents that then do prediction and for sure so much more. They know exactly what they are doing.
Re: Claude Code Routines
#129LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…
> I'm not going to build my business or my development flows on things I can't replicate myself.
but you can replicate these yourself! i'm happy that ant/oai are experimenting to find pmf for "llm for dev-tools". After they figure out the proper stickyness, (or if they go away or nerf or raise prices, etc) you can always take the off-ramp and implement your own llm/agent using the existing open-source models. The cost of building dev-tools is near zero. it is not like codegen where you need the frontier performance.
Re: Claude Code Routines
#130LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…
> I want to pick up and move to another harness and/or model with minimal fuss. Buying in to things like this would make that much harder. Yes, I expect that is very much the point here. A bunch of product guys got on a whiteboard and said, okay the thing is in wide use but the main moat is that our competitors are even more distrusted in the market than we are; other than that it's completely undifferentiated and ca…
I think they really knee capped themselves when they released Claude for Github integrations, which allows anyone to use their Claude subscription to run Claude Code in Github actions for code reviews and arbitrary prompts. Now they’re trying to back track that with a cloud solution.