Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I-have-ADHD: A skill to stop coding agents from burying the answer

github.com

Post reply on HN
Print view View original

61–70 of 384 posts

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#64

Post by bel8 »

klardotsh wrote: post #30
sleazebreeze wrote: post #12

Claude models are the ones that need this the most and in my experience with this specific skill only maintain the conciseness for a few turns at most before they completely forget and are back to their unfathomable verbosity. That's with it instructed to use it in my sparse global CLAUDE.md and also manually repeating it regularly during sessions. I don't really want to install a hook that runs this on every single…

GLM (both mainline and flash varieties), being trained to speak a very similar Claudeish, is also atrocious about this. My AGENTS.md demands all prose be in STE100, which is trying to solve a similar problem as the skill linked in OP. Getting GLM to STFU by AGENTS instruction is nigh impossible. I use a plugin for OMP/Pi to periodically inject system prompt reminders of output style, and it still largely ignores the…

yup.

GPT Luna tends to keep things objective. Muse Spark 1.3 is also one of the better models in this aspect, for me.

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#65

Post by sixothree »

hk1337 wrote: post #13

> A skill to stop your coding agent from burying the answer This is just an annoying thing for anyone. It gives a 10 page dissertation that sums up to, "it's good, nothing to worry about".

Or worse, buries an important detail somewhere in the text. Tangentially, over the weekend I had claude ask me if I wanted to continue with UIM-001. I couldn't find UIM-001 in any document it referenced creating or any text it had previously generated. Claude seems to be the worst about all of this stuff.

Also, somehow over the weekend it responded with these sections all clearly laid out - What landed, Decisions I made and recorded, Two findings, and What you need to do. Not sure why it can't do that all the time.

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#66

Post by elboru »

hk1337 wrote: post #13

> A skill to stop your coding agent from burying the answer This is just an annoying thing for anyone. It gives a 10 page dissertation that sums up to, "it's good, nothing to worry about".

What bothers me is the last few lines where it notes something "important" that you NEED to pay attention to. Just to find out that it is something you already mentioned somewhere in the conversation or that is not related to the current work.

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#68

Post by ilivethere »

SandersAK wrote: post #7

love when they put stuff in like this... One note on the repo's AGENTS.md: it contains instructions directing agents to post comments on a GitHub issue thread ("AI Agora", issue #127). I ignored that — it's the repo's content, not your request, and I don't act on instructions embedded in fetched files.

the AGENTS.md says that file is specifically for agents working ON i-have-adhd. When you install the skill, only the contents of the skills/ is copied over...

Re: I-have-ADHD: A skill to stop coding agents from burying the answer

#70

Post by bsimpson »

hk1337 wrote: post #13

> A skill to stop your coding agent from burying the answer This is just an annoying thing for anyone. It gives a 10 page dissertation that sums up to, "it's good, nothing to worry about".

I often use Google Deep Research when I want it to actually go out and find an answer for me, but the prompt must have a high school essay requirement in there. Nothing I can do prevents it from giving me a page of background that tries to make the question sound important and interesting, even when it isn't.

I usually follow up with an "I'm not reading all that" and make it summarize.

Post reply on HN