mikebannister
mikebannister on Hacker News
My uncle had a south-up map of the US on his wall when I was growing up. I always thought it was funny and slightly profound.
I removed all "ruleset" capabilities so "fine grained controls" are no longer a feature.
Not at all resilient. It caches a copy of the whatever the current claude is in case of emergency but yeah, get ready to go live without a net if you use this :)
I updated it a lot. First I had claude put it on a diet (get rid of 50% of the text) and then some manual editing. I'm a convert in hating LLM readme output. DIE DIE DIE :)
Today I added --mode plan (along with config option). Nice thing about "owning" my own wrapper is I can invent my own features.
https://github.com/possibilities/claude-composer?tab=readme-...
Note: in case you missed it Anthropic added plan mode that you toggle interactively. One of the best additions to CC. So I've only added the ability to start CC in plan mode.
Just dropped another 300 lines by manually editing. Glad you called out this slop. Thanks!
That's something I'd like to explore more. It's one of the reason I created "trusted roots". So I can open new worktrees and open claude in them all in one step without any confirmation.
If you want to suggest anything specific feel free to open an issue and we explore it more.
> auto-accept
That's pretty much it and the concept of "toolsets"
> You would also expect some eat-your-own-dog-food
Maybe, but personally I don't see a reason to use an LLM to release an npm module
No, the "automatic dismissal" effectively scrapes the terminal and parses out info from the dialog.
I think if I end up not finding a real person (or myself) using them I'll ax it. It would take some heft off the project. Maybe just yolo OR cautious and call it day.
Personally yes I do run it in yolo mode. And I think, to the extent anyone will use this project, people mostly won't be using the fine grained control. For me toolsets and full yolo are what is useful in this project.
I think the real use cases are something like:
1. Try cautious mode, gain confidence, switch to yolo
2. Use yolo mode and find that it keeps doing something that annoys or scares you so you configure an exception for it
On number 2 I thought I would use it this way to prevent some unwanted behavior but I ended up learning how to avoid those behaviors in other ways.
prompt>
The docs are way to verbose and there's just too much content. The @readme.md and every doc in @docs/ needs to be trimmed down by ~50%. Please work hard, think hard, and work step by step, and file by file to make sure we have the best possible docs at about half the total size. Peace and love <3
Yeah I tried to keep it chill but it went pretty wild w/ docs. I think I'll just ask it to go on a 50% diet and see what happens! Stay tuned. :)
That's a good idea. Personally I don't use CLAUDE.md (everything goes in the prompt, thanks to context-composer, which I'll share another day) so I'm not motivated to have it but I'd be happy to collaborate on it and get that kind of feature merged in.
They give you Claude Code usage on all the paid plans now. A certain amount of usage is shared between Chat and Code.
We'll see. Happy to change it up if need be. I'd rather beg for forgiveness than permission. <3
I hate to be pessimistic but this is something that CC doesn't seem good at: forgetting the tools that it loves and using the ones you want it to. You might want to try "disallowing" that command(?) explicitly (in addition to adding to CLAUDE.md and/or prompt).
I'm not sure what command is being called to set PYTHONPATH. If my assumption that it relates to a specific command is incorrect the above probably isn't helpful.
Good luck!
Also, good call, I wiggled the readme around a bit. Thanks!
If you like the idea but they aren't working the way you'd like let me know. They aren't very "well baked" but I'll dump some time into improving at some point. If you have pain points or feedback I'll be happy to consider it.
BTW, I also intend to add some way to send push notifications of some sort. I need to be reminded when Claude is done hustling and and it's time to leave the comfort of my iced coffee on the patio for a keyboard and glowing terminal screen.
Good chance this will ultimately end up being part of a set of training wheels that I'll take off gradually as I am able to move work over to using non-interactive instances of CC.
> Why?
I have a lot of different projects, scenarios, and edge cases where it's helpful to me.
I think you will find that if you're interactive mode there will always be some dialogs to dismiss, especially if you're jumping around a lot of different projects, etc. So for me the goals are somewhere at the intersection of the interactive mode and unattended operation.
It depends what your goals are for sure. TBH I use it mostly in full yolo mode. But toolsets are much more useful for me. I can create groups of mcps and pre-allowed permissions and reuse that "preset". I have different types of projects that I use different toolsets for each.
But yeah, I hear you. This is pretty niche and might solve problems that only I care about.
All of it, in close collaboration :)
Posted by
mikebannister on Thursday June 05, 2025 @06:53PM
from the show-hn dept.
https://github.com/possibilities/claude-composer
Central feature is a something like "yolo mode" but with fine grained controls over how yolo you're feeling. Also makes it easy to use "presets" of tools and permissions.Let me know if you have any questions and feel free to contact me on X at https://x.com/possibilities