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

101–110 of 278 posts

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

#101

Post by odie5533 »

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.

Wrappers are useful for some tasks. I use ralph loops for things that are extremely complicated and take days of work. Like reverse engineering projects or large scale migration efforts.

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

#102

Post by canadiantim »

AndyNemmity wrote: post #98

I have a ai system i use. I'd like to release it so others can benefit, but at the same time it's all custom to myself and what i do, and work on. 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…

you don't have to maintain it. Especially in the age of ai, just giving people inspiration and something to vibe from is more than sufficient and appreciated

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

#103

Post by prakashrj »

tkiolp4 wrote: post #54
prakashrj wrote: post #11

Earlier quoted context omitted.

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.

It's good advice. I will only open source, if it has utility.

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

#104

Post by sarchertech »

recroad wrote: post #97
sarchertech wrote: post #81

Earlier quoted context omitted.

> large sass app > hundreds of customers

Large codebase. Yeah man, I have a small business, trying to grow but not easy going up against Ticketmaster.

A ticketmaster competitor doesn’t sound like a huge technical challenge unless you’re operating at scale. So my first question would be why do you have a large codebase so with so few customers?

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

#105

Post by prakashrj »

icedchai wrote: post #69
prakashrj wrote: post #11

Earlier quoted context omitted.

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.

This does not feel like 250K lines of complexity. Have you looked at any of the code at all? You likely have mass duplication, copy-pasta everywhere.

I didn't look at code. In addition to code, I have CI and CD built in. I becomes hard add features after a while, if you cannot have built in CI/CD that will catch regression.

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

#106

Post by SayThatSh »

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 played around a bit with the plugins and as you've said, plan mode really handles things fine for the most part. I've got various workflows I run through in Claude and I've found having CC create custom skills/agents created for them gets me 80% of the way there. It's also nice that letting the Claude file refer to them rather than trying to define entire workflows within it goes a long way. It'll still forget things here and there, leading to wasted tokens as it realizes it's being dumb and corrects itself, but nothing too crazy. At least, it's more than enough to let me continue using it naturally rather than memorizing a million slash commands to manually evoke.

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

#107

Post by jtbetz22 »

Andrei_dev wrote: post #22

250K lines in a month — okay, but what does review actually look like at that volume? I've been poking at security issues in AI-generated repos and it's the same thing: more generation means less review. Not just logic — checking what's in your .env, whether API routes have auth middleware, whether debug endpoints made it to prod. You can move that fast. But "review" means something different now. Humans make human m…

I have been ~obsessed~ with exactly this problem lately.

We built AI code generation tools, and suddenly the bottleneck became code review. People built AI code reviewers, but none of the ones I've tried are all that useful - usually, by the time the code hits a PR, the issues are so large that an AI reviewer is too late.

I think the solution is to push review closer to the point of code generation, catch any issues early, and course-correct appropriately, rather than waiting until an entire change has been vibe-coded.

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

#108

Post by hatmanstack »

odie5533 wrote: post #101
hatmanstack wrote: post #41

Earlier quoted context omitted.

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.

Wrappers are useful for some tasks. I use ralph loops for things that are extremely complicated and take days of work. Like reverse engineering projects or large scale migration efforts.

Even with the 1 mil context windows? Can't you just keep the orchestrator going and run sub agents? Maybe the added space is too new? I also haven't tested out the context rot from 300K and up. Would love some color on it from first hand exp.

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

#109

Post by prakashrj »

chrisss395 wrote: post #70

I'm curious if anyone has used this (or similar) to build a production system? I'm facing increasing pressure from senior executives who think we can avoid the $$$ B2B SaaS by using AI to vibe code a custom solution. I love the idea of experimenting with this but am horrified by the first-ever-case being a production system that is critical to the annual strategic plan. :-/

I would love to take up that challenge. With what I have learnt so far, I am raring to get opportunities to make custom solutions.
Post reply on HN