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

Claude Code's new hidden feature: Swarms

twitter.com

Post reply on HN
Print view View original

21–30 of 351 posts

Re: Claude Code's new hidden feature: Swarms

#21

Post by AffableSpatula »

bonsai_spool wrote: post #18
AffableSpatula wrote: post #8

Earlier quoted context omitted.

The feature is shipped in the latest builds of claude code, but it's turned off by a feature flag check that phones home to the backend to see if the user's account is meant to have it on. You can just patch out the function in the minified cli.js that does this backend check and you gain access to the feature.

Do you know what patch to apply? The Github link from the OP seems to have a lot of other things included.

it's my repo - it's a fork of cc-mirror which is an established project for parallel claude installs. I wanted to take the least disruptive approach for the sake of using working code and not spelunking through bugs. Having said that - if you look through the latest commits you'll see how the patch works, it's pretty straightforward - you could do it by hand if you wanted.

Re: Claude Code's new hidden feature: Swarms

#22

Post by deaux »

neom wrote: post #12

Claude Code in the desktop app seems to do this? It's crazy to watch. It sets of these huge swarms of worker readers under master task headings, that go off and explore the code base and compile huge reports and todo lists, then another system behind the scenes seems to be compiling everything to large master schemas/plans. I create helper files and then have a devops chat, a front end chat, an architecture chat and…

Sounds very similar to oh-my-opencode.

Re: Claude Code's new hidden feature: Swarms

#23

Post by AffableSpatula »

lysace wrote: post #13

I'm already burning through enough tokens and producing more code than can be maintained - with just one claude worker. Feel like I need to move into the other direction, more personal hands-on "management".

I've seen more efficient use of tokens by using delegation. Unless you continually compact or summarise and clear a single main agent - you end up doing work on top of a large context; burning tokens. If the work is delegated to subagents they have a fresh context which avoids this whilst improving their reasoning, which both improve token efficiency.

Re: Claude Code's new hidden feature: Swarms

#24

Post by storystarling »

AffableSpatula wrote: post #23
lysace wrote: post #13

I'm already burning through enough tokens and producing more code than can be maintained - with just one claude worker. Feel like I need to move into the other direction, more personal hands-on "management".

I've seen more efficient use of tokens by using delegation. Unless you continually compact or summarise and clear a single main agent - you end up doing work on top of a large context; burning tokens. If the work is delegated to subagents they have a fresh context which avoids this whilst improving their reasoning, which both improve token efficiency.

I've found the opposite to be true when building this out with LangGraph. While the subagent contexts are cleaner, the orchestration overhead usually ends up costing more. You burn a surprising amount of tokens just summarizing state and passing it between the supervisor and workers. The coordination tax is real.

Re: Claude Code's new hidden feature: Swarms

#27

Post by AffableSpatula »

storystarling wrote: post #24
AffableSpatula wrote: post #23

Earlier quoted context omitted.

I've seen more efficient use of tokens by using delegation. Unless you continually compact or summarise and clear a single main agent - you end up doing work on top of a large context; burning tokens. If the work is delegated to subagents they have a fresh context which avoids this whilst improving their reasoning, which both improve token efficiency.

I've found the opposite to be true when building this out with LangGraph. While the subagent contexts are cleaner, the orchestration overhead usually ends up costing more. You burn a surprising amount of tokens just summarizing state and passing it between the supervisor and workers. The coordination tax is real.

Task sizing is important. You can address this by including guidance in the CLAUDE.md around that ie. give it heuristics to use to figure out how to size tasks. Mine includes some heuristics and T shirt sizing methodology. Works great!

Re: Claude Code's new hidden feature: Swarms

#28

Post by jswny »

neom wrote: post #12

Claude Code in the desktop app seems to do this? It's crazy to watch. It sets of these huge swarms of worker readers under master task headings, that go off and explore the code base and compile huge reports and todo lists, then another system behind the scenes seems to be compiling everything to large master schemas/plans. I create helper files and then have a devops chat, a front end chat, an architecture chat and…

That’s just spawning multiple parallel explore agents instructed to look at different things, and then compiling results

That’s a pretty basic functionality in Claude code

Re: Claude Code's new hidden feature: Swarms

#29

Post by neom »

jswny wrote: post #28
neom wrote: post #12

Claude Code in the desktop app seems to do this? It's crazy to watch. It sets of these huge swarms of worker readers under master task headings, that go off and explore the code base and compile huge reports and todo lists, then another system behind the scenes seems to be compiling everything to large master schemas/plans. I create helper files and then have a devops chat, a front end chat, an architecture chat and…

That’s just spawning multiple parallel explore agents instructed to look at different things, and then compiling results That’s a pretty basic functionality in Claude code

Sounds like I should probably switch to claude code cli. Thanks for the info. :)
Post reply on HN