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

51–60 of 278 posts

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

#51

Post by gtirloni »

jghn wrote: post #27
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…

I've gone the other way recently, shifting from pure plan mode to superpowers. I was reminded of it due to the announcement of the latest version. It is perhaps confirmation bias on my part but I've been finding it's doing a better job with similar problems than I was getting with base plan mode. I've been attributing this to its multiple layers of cross checks and self-reviews. Yes, I could do that by hand of course…

Yes, it does help in that way. Maybe I'm still struggling to let go and let AI take the wheel from beginning to end but I enjoy the exploratory part of the whole process (investigating possible solutions, trying theories, doing little spikes, etc, all with CC's assistance). When it's time to actually code, I just let it do its own thing mostly unsupervised. I do spend quite a lot of time on spec writing.

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

#52

Post by tkiolp4 »

prakashrj wrote: post #2

With GSD, I was able to write 250K lines of code in less than a month, without prior knowledge of claude.

That sounds awful.

I got a promotion once for deleting 250K lines of code in less than a month. Now that sounds better

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

#53

Post by thr0waway001 »

jdthedisciple wrote: post #36
thr0waway001 wrote: post #30

At the risk of sounding stupid what does the author mean by: “I’m not a 50-person software company. I don’t want to play enterprise theatre.” ?

Seems fairly obvious: Some agent harnesses play enterprise theater by creating jira-type tickets for you and moving them around silly swim lanes, instead of, of course, just simply getting sh!t done.

Wasn’t obvious to me so I asked.

But I guess if I go by what you’re saying I suppose it makes sense for it not to do a bunch of things you didn’t ask it to do.

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

#54

Post by tkiolp4 »

prakashrj wrote: post #11
wslh wrote: post #4

Earlier quoted context omitted.

250K? Could you expand your experience with details about your project and the lessons and issues you found?

A self-hosted VPN server manager: a TypeScript/Hono backend that runs on your own VPS, paired with a SwiftUI iOS/macOS app. It lets you provision cloud servers across multiple providers (Hetzner, DigitalOcean, Vultr), manage them via a Tailscale-secured connection with TLS pinning, and control an OpenClaw gateway. I will open source it soon in few weeks, as I have still complete few more features.

Please don’t.

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

#55

Post by arjie »

hatmanstack wrote: post #37
arjie wrote: post #29

I could not produce useful output from this. It was useful as a rubber duck because it asks good motivating questions during the plan phase, but the actual implementation was lacklustre and not worth the effort. In the end, I just have Claude Opus create plans, and then I have it write them to memory and update it as it goes along and the output is better.

No brother, the Claude plans aren't the right path, they're for hobbyists.

Okay, I'll give these another shot. Perhaps I just haven't figured out how to use them right.

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

#56

Post by jankhg »

Apart from GSD and superpowers, there's another system, called PAUL [1]. It apparently requires fewer tokens compared to GSD, as it does not use subagents, but keeps all in one session. A detailed comparison with GSD is part of the repo [2].

[1] https://github.com/ChristopherKahler/paul

[2] https://github.com/ChristopherKahler/paul/blob/main/PAUL-VS-...

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

#57

Post by jghn »

gtirloni wrote: post #51
jghn wrote: post #27

Earlier quoted context omitted.

I've gone the other way recently, shifting from pure plan mode to superpowers. I was reminded of it due to the announcement of the latest version. It is perhaps confirmation bias on my part but I've been finding it's doing a better job with similar problems than I was getting with base plan mode. I've been attributing this to its multiple layers of cross checks and self-reviews. Yes, I could do that by hand of course…

Yes, it does help in that way. Maybe I'm still struggling to let go and let AI take the wheel from beginning to end but I enjoy the exploratory part of the whole process (investigating possible solutions, trying theories, doing little spikes, etc, all with CC's assistance). When it's time to actually code, I just let it do its own thing mostly unsupervised. I do spend quite a lot of time on spec writing.

That’s part of what I’ve liked about it over plan mode. Again not a scientific measurement but I feel it’s better at interactive brainstorming and researching the big picture with me. And it’s built in multiple checkpoints also give me more space to pivot or course correct.

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

#58

Post by gtirloni »

hatmanstack wrote: post #41
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…

Why are we using cli wrappers if you're using Claude Code? I get if you need something like Codex but they released sub agents today so maybe not even that, but it's an unnecessary wrapper for Claude Code.

GSD and superpowers aren't CLI wrappers?

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

#59

Post by hatmanstack »

arjie wrote: post #55
hatmanstack wrote: post #37

Earlier quoted context omitted.

No brother, the Claude plans aren't the right path, they're for hobbyists.

Okay, I'll give these another shot. Perhaps I just haven't figured out how to use them right.

I don't know brother, I don't use them, they may be great they may suck. What I've found is that adding peripherals always creates more problems. If you aren't using Claude for professional work then just sticking with the factory plan mode probably works. If not, look into creating your own Claude skills, try to understand how prompt pipelines work and it will unlock a ton of automation for you. Not just for coding.

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

#60

Post by alasano »

gbrindisi wrote: post #14

I like openspec, it lets you tune the workflow to your liking and doesn’t get in the way. I started with all the standard spec flow and as I got more confident and opinionated I simplified it to my liking. I think the point of any spec driven framework is that you want to eventually own the workflow yourself, so that you can constraint code generation on your own terms.

I also like openspec.

I think these type of systems (gsd/superpowers) are way too opinionated.

It's not that they can't or don't work. I just think that the best way to truly stay on top of the crazy pace of changes is to not attach yourself to super opinionated workflows like these.

I'm building an orchestrator library on top of openspec for that reason.

Post reply on HN