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

How to use Claude Code subagents to parallelize development

zachwills.net

Post reply on HN
Print view View original

11–20 of 131 posts

Re: How to use Claude Code subagents to parallelize development

#11

Post by zarzavat »

CuriouslyC wrote: post #5

As someone who's built a project in this space, this is incredibly unreliable. Subagents don't get a full system prompt (including stuff like CLAUDE.md directions) so they are flying very blind in your projects, and as such will tend to get derailed by their lack of knowledge of a project and veer into mock solutions and "let me just make a simpler solution that demonstrates X." I advise people to only use subagents…

> Their ability to refactor a codebase goes in the toilet pretty quickly.

Very much this. I tried to get Claude to move some code from one file to another. Some of the code went missing. Some of it was modified along the way.

Humans have strategies for refactoring, e.g. "I'm going to start from the top of the file and Cut code that needs to be moved and Paste it in the new location". LLM don't have a clipboard (yet!) so they can't do this.

Claude can only reliably do this refactoring if it can keep the start and end files in context. This was a large file, so it got lost. Even then it needs direct supervision.

Re: How to use Claude Code subagents to parallelize development

#12

Post by simianwords »

Slightly off topic but I would really like agentic workflow that is embedded in my IDE as well as my code host provider like GitHub for pull requests.

Ideally I would like to spin off multiple agents to solve multiple bugs or features. The agents have to use the ci in GitHub to get feedback on tests. And I would like to view it on IDE because I like the ability to understand code by jumping through definitions.

Support for multiple branches at once - I should be able to spin off multiple agents that work on multiple branches simultaneously.

Re: How to use Claude Code subagents to parallelize development

#13

Post by CuriouslyC »

olivermuty wrote: post #9
theshrike79 wrote: post #7

Earlier quoted context omitted.

I don't use subagents to do things, they're best for analysing things. Like "evaluate the test coverage" or "check if the project follows the style guide". This way the "main" context only gets the report and doesn't waste space on massive test outputs or reading multiple files.

This is only a problem if an agent is made in a lazy way (all of them). Chat completion sends the full prompt history on every call. I am working on my own coding agent and seeing massive improvements by rewriting history using either a smaller model or a freestanding call to the main one. It really mitigates context poisoning.

There's a large body of research on context pruning/rewriting (I know because I'm knee deep in benchmarks in release prep for my context compiler), definitely don't ad hoc this.

Re: How to use Claude Code subagents to parallelize development

#14

Post by zarzavat »

ehnto wrote: post #8
Frannky wrote: post #4

Is it a good idea to generate more code faster to solve problems? Can I solve problems without generating code? If code is a liability and the best part is no part, what about leveraging Markdown files only? The last programs I created were just CLI agents with Markdown files and MCP servers(some code here but very little). The feedback loop is much faster, allowing me to understand what I want after experiencing it,…

Code you didn't write is an even bigger liability, because if the AI gets off track and you can't guide it back, you may have to spend the time to learn it's code and fix the bugs. It's no different to inheriting a legacy application though. As well, from the perspective of a product owner, it's not a new risk.

Claude is a junior. The more you work with it, the more you get a feel for which tasks it will ace unsupervised (some subset of grunt work) and which tasks to not even bother using it for.

I don't trust Claude to write reams of code that I can't maintain except when that code is embarrassingly testable, i.e it has an external source of truth.

Re: How to use Claude Code subagents to parallelize development

#16

Post by dutchCourage »

That sounds crazy to me, Claude Code has so many limitations.

Last week I asked Claude Code to set up a Next.js project with internationalization. It tried to install a third party library instead of using the internationalization method recommended for the latest version of Next.js (using Next's middleware) and could not produce of functional version of the boilerplate site.

There are some specific cases where agentic AI does help me but I can't picture an agent running unchecked effectively in its current state.

Re: How to use Claude Code subagents to parallelize development

#17

Post by Joel_Mckay »

Frannky wrote: post #4

Is it a good idea to generate more code faster to solve problems? Can I solve problems without generating code? If code is a liability and the best part is no part, what about leveraging Markdown files only? The last programs I created were just CLI agents with Markdown files and MCP servers(some code here but very little). The feedback loop is much faster, allowing me to understand what I want after experiencing it,…

Using LLMs to code poses a liability most people can't appreciate, and won't admit:

https://www.youtube.com/watch?v=wL22URoMZjo

Have a great day =3

Re: How to use Claude Code subagents to parallelize development

#18

Post by Frannky »

ehnto wrote: post #8
Frannky wrote: post #4

Is it a good idea to generate more code faster to solve problems? Can I solve problems without generating code? If code is a liability and the best part is no part, what about leveraging Markdown files only? The last programs I created were just CLI agents with Markdown files and MCP servers(some code here but very little). The feedback loop is much faster, allowing me to understand what I want after experiencing it,…

Code you didn't write is an even bigger liability, because if the AI gets off track and you can't guide it back, you may have to spend the time to learn it's code and fix the bugs. It's no different to inheriting a legacy application though. As well, from the perspective of a product owner, it's not a new risk.

There is no generated code. It is just a user interacting with a CLI terminal(via librechat frontend), guided by Markdown files, with access to MCPs

Re: How to use Claude Code subagents to parallelize development

#19

Post by Jare »

simianwords wrote: post #12

Slightly off topic but I would really like agentic workflow that is embedded in my IDE as well as my code host provider like GitHub for pull requests. Ideally I would like to spin off multiple agents to solve multiple bugs or features. The agents have to use the ci in GitHub to get feedback on tests. And I would like to view it on IDE because I like the ability to understand code by jumping through definitions. Suppo…

Would that be solved by having several clones of your repo, each with a IDE and a Claude working on each problem? Much like how multiple people work in parallel.

Re: How to use Claude Code subagents to parallelize development

#20

Post by simianwords »

Jare wrote: post #19
simianwords wrote: post #12

Slightly off topic but I would really like agentic workflow that is embedded in my IDE as well as my code host provider like GitHub for pull requests. Ideally I would like to spin off multiple agents to solve multiple bugs or features. The agents have to use the ci in GitHub to get feedback on tests. And I would like to view it on IDE because I like the ability to understand code by jumping through definitions. Suppo…

Would that be solved by having several clones of your repo, each with a IDE and a Claude working on each problem? Much like how multiple people work in parallel.

Yeah but it’s not ideal. I thought of this too.
Post reply on HN