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

How I use Claude Code to implement new features in an existing complex codebase

sabrina.dev

Post reply on HN
Print view View original

41–50 of 71 posts

Re: How I use Claude Code to implement new features in an existing complex codebase

#41

Post by AndyNemmity »

_andrei_ wrote: post #40
AndyNemmity wrote: post #3

[flagged]

> If you don't discuss hooks and subagents, i'm not sure what you're doing right now. Agents have their own context and can be useful for tasks that can be parallelized, which is a minority of tasks. How are they critical to better performance for you?

This is the best question anyone has asked.

Let's consider context. At some level the more context you have is good. At some level, the more irrelevant context you have is bad.

Okay. We have at top level of context, a hook that forces a system prompt on every action.

Next level we have a ./claude/CLAUDE.md then we have the project level CLAUDE.md then we have a possible not required agent setup then we have the instructions you give it

We know that CLAUDE.md gets lost in the context, at any level. The system prompt level hooks don't.

Why does the CLAUDE.md get lost? Why are we losing ability with a longer context.

The problem is irrelevant context to the action. The Documentation agent doesn't require the Golang modernization rules. The Golang agent, doesn't require the planing coordinator rules.

So the question I asked myself last weekend was, what is the experience if you split the contexts to only the required information for the task.

I did head to head battles with agents, reading in the information, versus contextual specific information. The agents with context specific destroyed the competition. Like it was another world.

So then I ran head to head tests on the type of information. Etc etc. My current setup is the best level achieved in those tests.

So my argument is that removing the context that is entirely irrelevant for the agent improves performance dramatically.

But I'm one person doing tests... it's true for me. Maybe it's not true for others. People have to explore the conception and determine that.

I can only tell you what has worked best for me, and for me, it's like a model jump in performance improvements.

Re: How I use Claude Code to implement new features in an existing complex codebase

#42

Post by AndyNemmity »

weitendorf wrote: post #35
AndyNemmity wrote: post #26

Earlier quoted context omitted.

.

It’s not the specific agent config or anything like that I’m after, just the genuine interest+enthusiasm in an area we’re actively working on. The central premise to what we’re building is our system for reusable and composable AI workflows. Shit’s moving fast and the math works out such that it’s probably better to just find someone at the bleeding edge and offer to pay them really generously to work with us than to…

.

Re: How I use Claude Code to implement new features in an existing complex codebase

#43

Post by CyberMacGyver »

AndyNemmity wrote: post #3

[flagged]

Genuinely, how do you keep up to date with these features while still being focused at the task?

The more I focus the less I have time to read and experiment O want to finish it. What are your sources and how are you balancing it ?

Re: How I use Claude Code to implement new features in an existing complex codebase

#44

Post by literalAardvark »

WD-42 wrote: post #27
ofrzeta wrote: post #20

That many sites about AI look a lot like scam sites ("make money fast") is a real turn-off -> https://www.sabrina.dev Maybe it does have some valuable content but I will just close it.

The grifters have entered the arena.

Hype is like catnip for them. They've been around for a while, many of the OG AI YouTubers didn't know anything about it when they started to pretend to educate.

Re: How I use Claude Code to implement new features in an existing complex codebase

#45

Post by bathtub365 »

gexla wrote: post #37
XenophileJKO wrote: post #8

Earlier quoted context omitted.

Actually please write an article about how you are currently using it then. I've been actively using it and working with sub-agents. I feel like there are very little resources out there on more complex Claude Code setups. I would love to see other setups, like what MCP, hooks, sub-agents, commands, etc.

I think the basic issue for me is that people put this stuff out as if it's some big discovery, and yet my own usage is way different and serves me just fine thank you. These have the feel of a developer who has just discovered development and then want to tell you about all the best tools. But it's not really about showing you the best tools, is it? Rather, it's about riding the hype train and creating slop for more…

When someone has a YouTube channel about programming with a certain level of polish they are not trying to be a professional programmer, they are trying to be a professional YouTuber.

Re: How I use Claude Code to implement new features in an existing complex codebase

#46

Post by poisonborz »

ToJans wrote: post #32
AndyNemmity wrote: post #12

Earlier quoted context omitted.

.

Wow, that is a huge instruction set. I've created a (way smaller) "/hire" command that does something similar, but I should probably turn it into an agent as well, as the commao is only creating agents, and I still need to do further adaptation with individual promoting and edits It's these little, but crucial insights that make all the difference, so thank you! I have the exact same feeling about losing time, for me…

The situation is of your own making. You can change/get out any time.

Re: How I use Claude Code to implement new features in an existing complex codebase

#47

Post by AndyNemmity »

CyberMacGyver wrote: post #43
AndyNemmity wrote: post #3

[flagged]

Genuinely, how do you keep up to date with these features while still being focused at the task? The more I focus the less I have time to read and experiment O want to finish it. What are your sources and how are you balancing it ?

Honestly, the release of sub-agents was the first time it felt actually meaningful.

MCP servers and the rest have not provided the type of gains sub-agents have. Hooks and subagents actually provide tangible value. Enough that it's changed my structure entirely to be tool focused, and not output focused.

Re: How I use Claude Code to implement new features in an existing complex codebase

#48

Post by dSebastien »

AndyNemmity wrote: post #41
_andrei_ wrote: post #40

Earlier quoted context omitted.

> If you don't discuss hooks and subagents, i'm not sure what you're doing right now. Agents have their own context and can be useful for tasks that can be parallelized, which is a minority of tasks. How are they critical to better performance for you?

This is the best question anyone has asked. Let's consider context. At some level the more context you have is good. At some level, the more irrelevant context you have is bad. Okay. We have at top level of context, a hook that forces a system prompt on every action. Next level we have a ./claude/CLAUDE.md then we have the project level CLAUDE.md then we have a possible not required agent setup then we have the instr…

It's been my experience too, already prior to support for sub-tasks/agents.

I've been exploring the ways in which I could "lazy load" context depending on the task at hand. I've approached this by defining an AI "receptionist", a set of roles and a set of tasks.

The receptionist is the entrypoint of the system. It knows where to find roles/tasks but only loads very basic information about the roles.

Depending on the role I ask for, it then loads the right role file, which in turn loads additional context. Then I ask for whatever i want to do, and it loads specific task files based on what I asked. And the task files load additional context etc.

This works quite well because I end up with just the right context for the task at hand. And each role/task can actually be executed as a sub-task/agent

Re: How I use Claude Code to implement new features in an existing complex codebase

#49

Post by AndyNemmity »

dSebastien wrote: post #48
AndyNemmity wrote: post #41

Earlier quoted context omitted.

This is the best question anyone has asked. Let's consider context. At some level the more context you have is good. At some level, the more irrelevant context you have is bad. Okay. We have at top level of context, a hook that forces a system prompt on every action. Next level we have a ./claude/CLAUDE.md then we have the project level CLAUDE.md then we have a possible not required agent setup then we have the instr…

It's been my experience too, already prior to support for sub-tasks/agents. I've been exploring the ways in which I could "lazy load" context depending on the task at hand. I've approached this by defining an AI "receptionist", a set of roles and a set of tasks. The receptionist is the entrypoint of the system. It knows where to find roles/tasks but only loads very basic information about the roles. Depending on the…

You stumbled on to the solution before the tools caught up to you. really cool.

Re: How I use Claude Code to implement new features in an existing complex codebase

#50

Post by XenophileJKO »

AndyNemmity wrote: post #42
weitendorf wrote: post #35

Earlier quoted context omitted.

It’s not the specific agent config or anything like that I’m after, just the genuine interest+enthusiasm in an area we’re actively working on. The central premise to what we’re building is our system for reusable and composable AI workflows. Shit’s moving fast and the math works out such that it’s probably better to just find someone at the bleeding edge and offer to pay them really generously to work with us than to…

.

Hmm.. I work at LinkedIn.. and I didn't get the magic invite. :(
Post reply on HN