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

201–210 of 278 posts

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

#201

Post by paddy_m »

Has anything like this been built?

I want a system that enforces planning, tests, and adversarial review (preferably by a different company's model). This is more for features, less for overall planning, but a similar workflow could be built for planning.

1. Prompt 2. Research 3. Plan (including the tests that will be written to verify the feature) 4. adversarial review of plan 5. implementation of tests, CI must fail on the tests 6. adversarial review verifying that the tests match with the plan 7. implementation to make the tests pass. 8. adversarial PR review of implementation

I want to be able to check on the status of PRs based on how far along they are, read the plans, suggest changes, read the tests, suggest changes. I want a web UI for that, I don't want to be doing all of this in multiple terminal windows.

A key feature that I want is that if a step fails, especially because of adversarial review, the whole PR branch is force pushed back to the previous state. so say #6 fails, #5 is re-invoked with the review information. Or if I come to the system and a PR is at #8, and I don't like the plan, then I make some edits to the plan (#3), the PR is reset to the git commit after the original plan, and the LLM is reinvoked with either my new plan or more likely my edits to the plan, then everything flows through again.

I want to be able to sit down, tend to a bunch of issues, then come back in a couple of hours and see progress.

I have a design for this of course. I haven't implemented it yet.

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

#202

Post by whalesalad »

nfg wrote: post #151
whalesalad wrote: post #138

Earlier quoted context omitted.

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

As a matter of interest are you using the copilot cli?

yeah. copilot cli using opus 4.6 vs claude code using opus 4.6

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

#203

Post by dboreham »

paddy_m wrote: post #201

Has anything like this been built? I want a system that enforces planning, tests, and adversarial review (preferably by a different company's model). This is more for features, less for overall planning, but a similar workflow could be built for planning. 1. Prompt 2. Research 3. Plan (including the tests that will be written to verify the feature) 4. adversarial review of plan 5. implementation of tests, CI must fai…

Similar ideas have been kicked around over here. One problem is that this seems like a set of features for GitHub rather than a stand-alone product (so no way to make money from it).

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

#204

Post by dboreham »

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…

From my experience they are motivated by these two issues that you run into when using Claude Code (or similar tool):

1. The LLM is operating on more what you'd call "guidelines" than the rules -- it will mostly make a PR after fixing a bug, but sometimes not. It will mostly run tests after completing a fix, but sometimes not. So there's a sentiment "heck, let's write some prompt that tells it to always run tests after fixing code", etc.

2. You end up running the LLM tool against state that is in GitHub (or RCS du jour). E.g. I open a bug (issue) and type what I found that's wrong, or whatever new feature I want. Then I tell Claude to go look at issue #xx. It runs in the terminal, asks me a bunch of unnecessary permission questions, fixes the bug, then perhaps makes a PR, perhaps I have to ask for that, then I go watch CI status on the PR, come back to the terminal and tell it that CI passed so please merge (or I can ask it to watch CI and review status and merge when ready). After a while you realize that all that process could just be driven from the GitHub UI -- if there was a "have Claude work on this issue" button. No need for the terminal.

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

#205

Post by jghn »

denolfe wrote: post #100
huydotnet wrote: post #33

Earlier quoted context omitted.

I've tried both. Each has pros and cons. Two things I don't like about superpowers is it writes all the codes into the implementation plan, at the plan step, then the subagents basically just rewrite these codes back to the files. And I have to ask Claude to create a progress.md file to track the progress if I want to work in multiple sessions. GSD pretty much solved these problems for me, but the down side of GSD is…

There is a fork that uses Claude Code-native features and tracks progress and task dependencies natively: https://github.com/pcvelz/superpowers

If you use it I'm curious if you find it limited at all from lagging behind superpowers? For instance I opened up one skill at random and they haven't yet pulled in the latest commit from last week.

I doubt any hot off the press features are *that* important, but am curious if the customizations of the fork are a net positive considering this.

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

#206

Post by Atotalnoob »

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

Copilot feels like being a caveman, Claude code feels like modern times comparatively.

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

#207

Post by icedchai »

prakashrj wrote: post #105
icedchai wrote: post #69

Earlier quoted context omitted.

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.

You didn't look at the code, so you don't know what you're really working with. Maybe it's total slop. This is concerning since you're dealing with security and presumably API keys to third-party platforms.

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

#208

Post by mrhaugan »

odie5533 wrote: post #112
hatmanstack wrote: post #108

Earlier quoted context omitted.

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.

It's not a context issue so much as a focus issue. The agent will complete part of a task and then ask if I want it to continue. Even if I told it I want it to keep going until all tasks are complete. Using a wrapper deals with that behavior. Most projects I do take 20 minutes or less for an agent to complete and those don't need a wrapper. But for longer tasks, like hours or days, it gets distracted.

Damn, what kind of tasks are you making your agents work on that takes days???

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

#209

Post by giancarlostoro »

Nice, I like the UI more than mine, I built a similar tool out of minor frustrations with some design choices in Beads, mine uses SQLite exclusively instead of git or hard files, been using it for all my personal projects, but havent gone back to try and refine what I have a little more. One thing a lot of these don't do that I added to mine is synching to and from GitHub. I want people to see exactly what my local tasks are, and if they need to pull one down to work on.

I think the secret sauce is talk to the model about what you want first, make the plan, then when you feel good about the spec, regardless of tooling (you can even just use a simple markdown file!) you have it work on it. Since it always has a file to go back to, it can never 'forget' it just needs to remember to review the file. The more detail in the file, the more powerful the output.

Tell your coding model: how you want it, what you want, and why you want it. It also helps to ask it to poke holes and raise concerns (bypass the overly agreeable nature of it so you dont waste time on things that are too complex).

I love using Claude to prototype ideas that have been in my brain for years, and they wind up coming out better than I ever envisioned.

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

#210

Post by paddy_m »

dboreham wrote: post #203
paddy_m wrote: post #201

Has anything like this been built? I want a system that enforces planning, tests, and adversarial review (preferably by a different company's model). This is more for features, less for overall planning, but a similar workflow could be built for planning. 1. Prompt 2. Research 3. Plan (including the tests that will be written to verify the feature) 4. adversarial review of plan 5. implementation of tests, CI must fai…

Similar ideas have been kicked around over here. One problem is that this seems like a set of features for GitHub rather than a stand-alone product (so no way to make money from it).

I'm not concerned about making money from it, I just want to use it. I'd like to check to see if I'm re-inventing the wheel. I'm curious if others would like a similar experience.
Post reply on HN