Show HN: Project management system for Claude Code

Here's a summary of the themes expressed in the Hacker News discussion:

Need for Demonstrations and Clarity

A significant portion of the discussion revolves around the desire for better understanding of how the system works in practice. Users are looking for demonstrations to grasp the workflows and the tangible benefits.

"Lots of thought went into this. It would be very helpful to see examples of the various workflows and documents. Perhaps a short video of the system in use?" - yodon
"Great idea! I'll whip something up over the weekend and post the video here and on the repo" - arousdi
"I was also looking for a video. The concept sounds good, but feels like I need to learn a lot of new commands, or have a cheat sheet next to me to be able to be able to use the framework." - cahaya
"Agree! I see a lot of pontential here, just hard to get a grasp." - raimille1
"Would love to see a video/graphic of this in action." - thomask1995
"Good idea. I'd love a video." - greggh

The Role of Task Decomposition and Structure

There's a strong consensus on the importance of breaking down large tasks into smaller, manageable units for AI agents. This structured approach is seen as crucial for effective AI-assisted development, contrasting with "vibe coding."

"Task decomposition is the most important aspect of software design and SDLC." - nivertech
"Hopefully, your GitHub tickets are large enough, such as covering one vertical scope, one cross-cutting function, or some reactive work such as bug fixing or troubleshooting. The reason is that coding agents are good at decomposing work into small tasks/TODO lists. IMO, too many tickets on GitHub will interfere with this." - nivertech
"When we break down an epics into tasks, we get CC to analyze what can be run in parallel and use each issue as a conceptual grouping of smaller tasks, so multiple agents can work on the same issue in parallel." - arousdi
"My workflow is a mix of Claude Code, Gemini CLI, Qwen Code or other coding CLI tools with GitHub (issues, documentation, branches, worktrees, PRs, CI, CodeRabbit and other checks)." - brainless
"The system is trying to solve: breaking down large projects into small tasks and assigning sub-agents to work on each task, so the code, research, test logs, etc. stay inside the agent, with only a summary being surfaced back up to the main thread." - arousdi
"tl;dr break shit down into small chunks" - apwell23

The Need for Human Oversight and Validation

A recurring theme is the necessity of human intervention and review to guide and correct AI-generated code. Users are cautious about fully autonomous AI development, emphasizing that AI is a tool requiring skilled human direction.

"I'm a huge fan of Claude Code. That being said it blows my mind people can use this at a higher level than I do. I really need to approve every single edit and keep an eye on it at ALL TIMES, otherwise it goes haywire very very fast! How are people using auto-edits and these kind of higher-level abstraction?" - jdmoreira
"Of course, you still need to use your human brain to verify before hand that there aren't special edge cases that need to be considered." - semitones
"When using agents like this, you only see a speedup because you’re offloading the time you’d spend thinking / understanding the code. If you can review code faster than you can write it, you’re cutting corners on your code reviews. Which is normally fine with humans (this is why we pay them), but not AI." - aosidjbd
"I have to handhold agents to get anywhere near stuff I actually want to commit with my name on." - royletron
"My view, after having gone all-in with Claude Code (almost only Opus) for the last four weeks, is ”no”. You really can’t. The review process needs to be diligent and all-encompassing and is, quite frankly, exhausting." - adriand
"For me, that's 'just one', and that's why LLM coding doesn't scale very far for me with these tools." - stavros
"The secret? The secret is that just as before you had a large amount of "bad coders", now you also have a large amount of "bad vibe coders". I don't think it's news to anyone that most people tend to be bad or mediocre at their job. And there's this mistaken thinking that the AI is the one doing the work, so the user cannot be blamed… but yes they absolutely can. The prompting & the tooling set up around the use of that tool, knowing when to use it, the active review cycle, etc - all of it is also part of the work, and if you don't know how to do it, tough." - scrollaway
"I think one of the best skills you can have today is to be really good at "glance-reviews" in order to be able to actively review code as it's being written by AI, and be able to interrupt it when it goes sideways." - scrollaway
"You can't, at least for production code. I have used Claude Code for vibe coding several side projects now, some just for fun, others more serious and need to be well written and maintainable. For the former, as long as it works, I don't care, but I could easily see issues like dependency management. Then for the latter, because I actually need to personally verify every detail of the final product and review (which means "scan" at the least) the code, I always see a lot of issues -- tightly coupled code that makes testing difficult, missing test cases, using regex when it shouldn't, having giant classes that are impossible to read/maintain. Well, many of the issues you see humans do. I needed to constantly interrupt and ask it to do something different." - rs186
"Else the LLM will keep going down rabbit holes and failing to produce useful results without supervision." - vemrv
"Nizoss: Same, I manually approve and steer each operation. I don't see how cleaning up and simplifying after the fact is easier or faster." - Nizoss

AI as a Fast Junior Developer vs. Autonomous Agent

There's a division in how users perceive the capabilities of AI coding tools. Some view them as powerful assistants that can accelerate development when closely managed, akin to a junior developer, while others are skeptical about their ability to function truly autonomously, especially for complex or novel tasks.

"Essentially, I'm treating Claude Code as a very fast junior developer who needs to be spoon-fed with the architecture." - arousdi
"I don't think anyone is doing this. I don't believe I've seen any real stories of people doing this successfully." - noodletheworld (referring to unsupervised agents)
"Can you use unsupervised agents, where you don't interact at a 'code' level, only at a high level abstraction level? ...and, I don't think you can." - noodletheworld
"You can. People do. It's not perfect at it yet, but there are success stories of this." - the_mitsuhiko (responding to a user's skepticism about autonomous AI)
"I definitely don't think that's remotely reasonable for someone who can't program. For small things yes, but large things? They're going to get into a spin cycle with the LLM on some edge case it's confused about where they consistently say 'the button is blue!' and the bot confirms it is indeed not blue." - unshavedyak
"I think for me personally, such a linear breakdown of the design process doesn't work." - tmvphil (highlights the iterative nature of human problem-solving that might conflict with rigid AI workflows)

AI's Utility in Repetitive Tasks and Template-Based Development

A common observation is that LLMs excel in scenarios that can be mapped to existing patterns or templates, such as CRUD operations or minor updates to well-defined architectures. Their effectiveness diminishes for novel or highly intricate low-level systems.

"LLMs are a godsend when it comes to developing things that fit into one of the tens of thousands (or however many) of templates they have memorized. For instance, a lot of modern B2B software development involves updating CRUD interfaces and APIs to data." - semitones
"Of course, there are many many other kinds of development - when developing novel low-level systems for complicated requirements, you're going to get much poorer results from an LLM, because the project won't as neatly fit in to one of the 'templates' that it has memorized, and the LLM's reasoning capabilities are not yet sophisticated enough to handle arbitrary novelty." - semitones
"I don't go gushy about code generation when I use yasnippet or a vim macro, why should super autocomplete be different?" - dingnuts

Concerns About Code Quality and the "Vibe Coding" Phenomenon

There's a debate regarding the perceived quality of AI-generated code. Some users express skepticism, associating AI output with "garbage" or "bullshit-coding," while others argue that the quality reflects the user's proficiency in guiding the AI and that a negative attitude is detrimental. The term "vibe coding" is used to describe a less rigorous approach to AI-assisted development.

"The secret to being an elite 10x dev - push 1000's of lines of code, soak up the ooo's and ahhh's at the standup when management highlight your amazingly large line count, post to linkedin about how great and humble you are, then move to the next role before anyone notices you contribute nothing but garbage and some loser 0.1x dev has to spend months fixing something they could have writting in a week or two from scratch." - blitzar
"I’m always amazed on how LLMs are praised for being able to churn out the large amount of code we apparently all need. I keep wondering why. All projects I ever saw need lines of code, nuts and bolts removed instead of added." - fzeindl
"Great engineers who pick up vibe coding without adopting the ridiculous 'it's AI so it can't be better than me' attitude are the ones who are able to turn into incredibly proficient people able to move mountains in very little time. People stuck in the 'AI can only produce garbage' mindset are unknowingly saying something about themselves. AI is mainly a reflection of how you use it. It's a tool, and learning how to use that tool proficiently is part of your job." - scrollaway
"The secret? The secret is that just as before you had a large amount of 'bad coders', now you also have a large amount of 'bad vibe coders'." - scrollaway
"if you have to understand the code, it's not vibe coding. Karpathy's whole tweet was about ignoring the code. if you have to understand the code to progress, it's regular fucking programming." - dingnuts
"This is a more advanced version of what I'm doing. I was impressed that someone took it up to this level till I saw the tell tale signs of the AI generated content in the README. Now I have no faith that this is a system that was developed, iterated and tested to actually work and not just a prompt to an AI to dress up a more down to earth workflow like mine." - dcreater
"Maybe the ordering flow does work, but how much traction are you going to really get without the demo actually doing what it's supposed to? Not trying to be snarky - just trying to understand if people actually pay for mediocre or low-quality products like these" - tantanu (critiquing a user's LLM-generated project)
"The rest of the README is llm-generated so I kinda suspect these numbers are hallucinated, aka lies." - moconnor
"It will increasingly become common knowledge that the best practice for AI coding is small edits quite carefully planned by a human. Else the LLM will keep going down rabbit holes and failing to produce useful results without supervision." - vemrv

Workflow Evolution and Adaptation

There's a discussion about whether the structured, phased approach described resembles waterfall development and the implications of this for adapting to changing requirements. Some users argue that the AI era necessitates a re-evaluation of traditional agile principles, particularly regarding documentation.

"We follow a strict 5-phase discipline" - "So we're doing waterfall again? Does this seem appealing to anyone? The problem is you always get the requirements and spec wrong, and then AI slavishly delivers something that meets spec but doesn't meet the need." - tmvphil
"Waterfall might be what you need when dealing with external human clients, but why would you voluntarily impose it on yourself in miniature?" - tmvphil
"I think for me personally, such a linear breakdown of the design process doesn't work. I might write down 'I want to do X, which I think can be accomplished with design Y, which can be broken down into tasks A, B, and C' but after implementing A I realize I actually want X' or need to evolve the design to Y' or that a better next task is actually D which I didn't think of before." - tmvphil
"I think the big difference between this and waterfall is that waterfall talked about the execution phase before the testing phase, and we have moved past defining the entire system as a completed project before breaking ground. Nothing in defining a feature in documentation up front stops continuous learning and adaptation. However, LLMs and code breaks the "Working software over comprehensive documentation" component of agile. It breaks because documentation now matters in a way it didn't when working with small teams. However, it also breaks because writing comprehensive documentation is now cheaper in time than it was three years ago. The big problem now is maintaining that documentation. Nobody is doing a good job of that yet - at least that I've seen." - ebiester
"A project management layer is a huge missing piece in AI coding right now. Proper scoping, documentation, management, etc is essential to getting good results." - tummler
"The main idea was to remove the vibe from vibe coding and use the AI as a tool rather than as the developer itself." - arousdi

The Use of Multiple Agents and Context Management

The concept of using multiple specialized agents to handle different aspects of a task is explored. The advantage seen is primarily in context management, preventing the main agent from being overwhelmed with specific details for each sub-task.

"The advantage with using multiple agents is in context management, not parallelization. A main agent can orchestrate sub agents. The goal is to not overwhelm the main agent with specialized context for each step that can be delegated to separate task focused agents along the way." - swader999
"100%! Use agents as 'context firewalls'. Let them read files, run tests, research bugs, etc, and pass essential data back to the main thread." - arousdi
"Are ppl really doing this? My brain gets overwhelmed if i have more than 2 or 3." - apwell23
"It really depends on how you use parallel agents. Personally, I don't run multiple instances of Cloud Code nor do I use multiple screens. I find it hard to focus :) That being said, if a task requires editing three different files, I would launch three different sub-agents, each editing one file, cutting down implementation time by two-thirds." - arousdi
"The real idea is to make sure that each agent works in its own little world and documents everything. So the main thread context is occupied with the understanding of the project instead of code snippets." - arousdi
"That's exactly why we use separate agents as 'context firewalls'. Instead of having the main thread do all the work and get its context polluted, with sub-agents, each agent works on one thing, then provides a summary to the main thread (much smaller context use) as well as a detailed summary in an empty file." - royletron
"Nizoss: I'm genuinely curious to see what the software quality looks like with this approach. Particularly how it handles complexity as systems grow. Feature development is one thing, going about it in a clean and maintainable way is another. I've come across several projects that try to replicate agile/scrum/SAFe for agents, and I'm trying to understand the rationale." - Nizoss