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

Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

github.com

Post reply on HN
Print view View original

221–230 of 278 posts

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#221

Post by gtirloni »

whalesalad wrote: post #138
Rapzid wrote: post #135

Earlier quoted context omitted.

I use GitHub Copilot and unfortunately there has been a weird regression in the bundled Plan mode. It suddenly, when they added the new plan memory, started getting both VERY verbose in the plan output and also vague in the details. It's adding a lot of step that are like "design" and "figure out" and railroads you into implementation without asking follow-up questions.

I find that even with opus 4.6, copilot feels like it’s handicapped. I’m not sure if it’s related to memory or what but if I give two tasks to opus4.6 one in CC and one in Copilot, CC is substantially better. I’ve been really enjoying Codex CLI recently though. It seems to do just as well as Opus 4.6, but using the standard GPT 5.4

I think this shows that the model alone isn't the complete story and that these "harnesses" (as people seem to be calling them) shape a lot of the experienced behavior of these tools.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#222

Post by gtirloni »

swingboy wrote: post #132
hermanzegerman wrote: post #88

Earlier quoted context omitted.

No it's not. It's using Skills and Agents and runs always inside of Claude Code, Gemini CLI etc...

GSD delegates a lot of the deterministic work to a JavaScript CLI. That might be what the poster is talking about.

That's definitely not a CLI wrapper. But people are calling Claude Code (clearly a TUI) a CLI so :shrug:

GSD is a collection of skills, commands, MCPs(?), helper scripts, etc that you use inside Claude Code (and others). If anything, Claude Code is the wrapper around those things and not the other way around.

Re: helper scripts. Anyone doing extensive work in any AI-assisted platform has experienced the situation where the agent wants to update 10k files individually and it takes ages. CC is often smart enought to code a quick Python script for those changes and the GSD helper scripts help in the same way. It's just trying to save tokens. Hardly a wrapper around Claude Code.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#223

Post by gtirloni »

whalesalad wrote: post #137
gtirloni wrote: post #21

I was using this and superpowers but eventually, Plan mode became enough and I prefer to steer Claude Code myself. These frameworks are great for fire-and-forget tasks, especially when there is some research involved but they burn 10x more tokens, in my experience. I was always hitting the Max plan limits for no discernable benefit in the outcomes I was getting. But this will vary a lot depending on how people prefer…

Same experience. Superpowers are a little too overzealous at times. For coding especially I don’t like seeing a comprehensive design spec written (good) and then turning that into effectively the same doc but macro expanded to become a complete implementation with the literal code for the entire thing in a second doc (bad). Even for trivial changes I’d end up with a good and succinct -design.md, then an -implementati…

Yes. I sometimes had to specifically ask it to NOT add any code to the specs because that would be done at a later stage.

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#224

Post by FromTheFirstIn »

sigbottle wrote: post #211
gtirloni wrote: post #21

I was using this and superpowers but eventually, Plan mode became enough and I prefer to steer Claude Code myself. These frameworks are great for fire-and-forget tasks, especially when there is some research involved but they burn 10x more tokens, in my experience. I was always hitting the Max plan limits for no discernable benefit in the outcomes I was getting. But this will vary a lot depending on how people prefer…

Yup yup yup. I burned literally a weeks worth of the 20$ claude subscription and then 20$ worth of API credits on gsdv2. To get like 500 LOC. And that was AFTER literally burning a weeks worth of codex and Claude 20$ plans and 50$ API credits and getting completely bumfucked - AI was faking out tests etc. I had better experiences just guiding the thing myself. It definitely was not a set and forget experience (6 hour…

You spent $25 on 500 LOC?

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#226

Post by reedlaw »

recroad wrote: post #74

I use openspec and love it. I’m doing 5-7x with close to 100% of code AI generated, and shipping to production multiple times a day. I work on a large sass app with hundreds of customers. Wrote something here: https://zarar.dev/spec-driven-development-from-vibe-coding-t...

This is the second endorsement I've seen today. I gave OpenSpec a shot and was dismayed by the Explore prompt. [1] Over 1,000 words with verbose, repetitive instructions which will lead to context drift. The examples refer to specific tools like SQLite and OAuth. That won't help if your project isn't related to those.

I do like the basic concept and directory structure, but those are easy enough to adopt without all the cruft.

1. https://github.com/Fission-AI/OpenSpec/blob/main/src/core/te...

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#228

Post by wffurr »

coopykins wrote: post #171

There are so many of these "meta" frameworks going around. I have yet to see one that proves in any meaningful way they improve anything. I have a hard time believing they accomplish anything other than burn tokens and poison the context window with too much information. What works best IME is keeping things simple, clear and only providing the essential information for the task at hand, and iterating in manageable s…

There was a post from Apenwarr[1] recently that gave it a name: "the AI Developer’s Descent Into Madness", ending with "I need an agent framework. I can have my agent write an agent framework!"

[1]: https://apenwarr.ca/log/20260316

Re: Get Shit Done: A meta-prompting, context engineering and spec-driven dev system

#230

Post by indigodaddy »

dominotw wrote: post #199
indigodaddy wrote: post #48

Earlier quoted context omitted.

Check out exe.dev/Shelley web agent it facilitates much of what you describe by default.

yea i am not going to checkout your shitty vibecoded project. Can we pls stop this.

Lol, not my project, and you shouldn't make assumptions, you have no clue what you are talking about
Post reply on HN