How to use Claude Code subagents to parallelize development
1–10 of 131 posts
Re: How to use Claude Code subagents to parallelize development
#2Follow up from my last post; lots were asking for more examples. I will be around if anybody has questions this morning.
Re: How to use Claude Code subagents to parallelize development
#3Follow up from my last post; lots were asking for more examples. I will be around if anybody has questions this morning.
Can it work without Linear, using md files?
Re: How to use Claude Code subagents to parallelize development
#4Is 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, and self-correction is super fast. Plus, you don't get lost in the implementation noise.
Re: How to use Claude Code subagents to parallelize development
#5As 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 for stuff that is very compartmentalized because they're hard to monitor and prone to failure with complex codebases where agents live and die by project knowledge curated in files like CLAUDE.md. If your main Claude instance doesn't give a good handoff to a subagent, or a subagent doesn't give a good handback to the main Claude, shit will go sideways fast.
Also, don't lean on agents for refactoring. Their ability to refactor a codebase goes in the toilet pretty quickly.
Re: How to use Claude Code subagents to parallelize development
#6Was going to ask how much all this cost, but this sort of answers it:
> "Managing Cost and Usage Limits: Chaining agents, especially in a loop, will increase your token usage significantly. This means you’ll hit the usage caps on plans like Claude Pro/Max much faster. You need to be cognizant of this and decide if the trade-off—dramatically increased output and velocity at the cost of higher usage—is worth it."
Re: How to use Claude Code subagents to parallelize development
#7As 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…
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.
Re: How to use Claude Code subagents to parallelize development
#8Is 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.
Re: How to use Claude Code subagents to parallelize development
#9As 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…
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.
Re: How to use Claude Code subagents to parallelize development
#10Earlier 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.
Everyone complains that when you compact the context, Claude tends to get stupid
Which as far as I understand it is summarizing the context with a smaller model.
Am I misunderstanding you, as the practical experience of most people seem to contradict your results.