Comments URL: https://news.ycombinator.com/item?id=47677188

Points: 1

# Comments: 0

I've been playing around with doing that with a cron job for a "dream" sequence.

I really want to get them out of main context asap, and where they belong, into skills.

https://github.com/notque/claude-code-toolkit

Comments URL: https://news.ycombinator.com/item?id=47556201

Points: 1

# Comments: 0

it runs indefinitely without my feedback or until rates limit it.

The AI agents built all of it. Not me. I realized I hadn't looked at it in awhile, and was looking for new ideas to add to my own ai system i built after learning from it.

So I thought I'd share it incase it was interesting to anyone else.

Especially the people who can't get claude code to not stop for them. I have been the entire time able to have it run indefinitely without my interaction. :)

I think i started it with a single prompt, and then told it to build everything else out it needed. That it's in control. I didn't write any of what is in the repo. I didn't tell it what to do.

It's just what it did.

EDIT: also i should commit what it has... it doesn't care about committing, so there's a whole lot of stuff it's built that isn't up there. Let me do that now.

EDIT 2: also, nothing is my ideas or written by me. It's all the collective. So please don't think i made the readme, or anything. I am not communicating ideas here, I let them do their own thing

Comments URL: https://news.ycombinator.com/item?id=47511235

Points: 2

# Comments: 1

https://github.com/notque/claude-code-toolkit

Comments URL: https://news.ycombinator.com/item?id=47479379

Points: 1

# Comments: 0

But most of those setups are thin wrappers around "You are an expert at"

Mine I have been working on since agents released, and has a different conception.

From an intelligent /do router command to automatically route to skills and agents so you don't have to remember anything.

High context skills, because in my testing it's better to have high context, and you use fewer tokens because it doesn't require turn after turn of working on it and fixing.

ADRs being the central component of everything you do, so that there is a consistent document that all agents get.

And a lot more. It's yet another Claude Code setup, but perhaps it's interesting to you.

Comments URL: https://news.ycombinator.com/item?id=47463371

Points: 1

# Comments: 1

I have a custom learning system. We are all trying things, that's where ai development is.

None of us know the best solution. We are all exploring in paths. I don't find memory and persistent long term context to be an issue for me, but I am using a full custom ai claude code setup, so perhaps I have sorted it for myself. Unsure.

Can you give a specific example? Like, talk through your workflow so I can understand it better?

https://github.com/notque/claude-code-toolkit

Comments URL: https://news.ycombinator.com/item?id=47421546

Points: 8

# Comments: 0

i have checks of which types of repos i'm in with branching dev flows for each one.

it's going to be hard to communicate all of this genericly, but i am trying.

there's a lot of patterns i think are helpful for me.

If I fork out a version for others that is public, then I have to maintain that variation as well.

Is anyone in a similar situation? I think most of the ones I see released are not particularly complex compraed to my system, but at the same time I don't know how to convey how to use my system as someone who just uses it alone.

it feels like I don't want anyone to run my system, I just want people to point their ai system to mine and ask it what there is valuable to potentially add to their own system.

I don't want to maintain one for people. I don't want to market it as some magic cure. Just show patterns that others can use.

Which is why I use a skill that is a command, that routes requests to agents and skills.

Writing about AI so far, but who knows. Just started it.

https://gist.github.com/notque/e57cb975a3df7780824ce4085a59a...

There was someone a while ago who made a funny post about the type of Hacker News commenters. So I have 5 of them that will review things, and ended up being way more effective than I ever imagined they'd be.

│ contrarian-provocateur-roaster │ Challenge premises, explore alternatives │ "Have you considered..."

│ enthusiastic-newcomer-roaster │ Accessibility, onboarding friction │ "Wait, how do I even..."

│ pragmatic-builder-roaster │ Operational reality, production concerns │ "This won't survive 3AM pages" │

│ skeptical-senior-roaster │ Long-term maintenance, sustainability │ "Who maintains this in 2 years?" │

│ well-actually-pedant-roaster │ Terminology precision, verifiability │ "Technically, that's not..." │

Someone tells me it "forgets" their instructions. Or it hallucinates fixes. Or it ignores the rules they put in CLAUDE.md. And when I ask what their setup looks like, it's always the same thing: a massive system prompt with every rule for every language, stuffed into context.

So I wrote up how I solve this.