Claude Code's new hidden feature: Swarms • Hacker News Board

Re: Claude Code's new hidden feature: Swarms

#41

Post by AffableSpatula » Sat, Jan 24, 2026, 4:30 PM UTC

nulone wrote: post #38

AffableSpatula wrote: post #16

Earlier quoted context omitted.

Delegation patterns like swarm lead to less token usage because: 1. Subagents doing work have a fresh context (ie. focused and not working on the top of a larger monolithic context) 2. Subagents enjoying a more compact context leads to better reasoning, more effective problem solving, less tokens burned.

Merge cost kills this. Does the harness enforce file/ownership boundaries per worker, and run tests before folding changes back into the lead context?

I don't know what you're referring to but I can say with confidence that I see more efficient token usage from a delegated approach, for the reasons I stated, provided that the tasks are correctly sized. ymmv of course :)

Re: Claude Code's new hidden feature: Swarms

#42

Post by joshribakoff » Sat, Jan 24, 2026, 4:35 PM UTC

This is just sub agents, built into Claude. You don’t need 300,000 line tmux abstractions written in go. You just tell Claude to do work in parallel with background sub agents. It helps to have a file for handing off the prompt, tracking progress, and reporting back. I also recommend constraining agents to their own worktrees. I am writing down the pattern here https://workforest.space while nearly everyone is building orchestrators i also noticed claude is already the best orchestrator for claude.

Re: Claude Code's new hidden feature: Swarms

#43

Post by Androider » Sat, Jan 24, 2026, 4:36 PM UTC

Looks like agent orchestrators provided by the foundation model providers will become a big theme in 2026. By wrapping it in terms that are already used in software development today like team leads, team members, etc. rather than inventing a completely new taxonomy of Polecats and Badgers, will help make it more successful and understandable.

Re: Claude Code's new hidden feature: Swarms

#44

Post by AffableSpatula » Sat, Jan 24, 2026, 4:41 PM UTC

joshribakoff wrote: post #42

This is just sub agents, built into Claude. You don’t need 300,000 line tmux abstractions written in go. You just tell Claude to do work in parallel with background sub agents. It helps to have a file for handing off the prompt, tracking progress, and reporting back. I also recommend constraining agents to their own worktrees. I am writing down the pattern here https://workforest.space while nearly everyone is buildi…

Claude already had subagents. This is a new mode for the main agent to be in (bespoke context oriented to delegation), combined with a team-oriented task system and a mailbox system for subagents to communicate with each other. All integrated into the harness in a way that plugins can't achieve.

Re: Claude Code's new hidden feature: Swarms

#45

Post by svara » Sat, Jan 24, 2026, 4:42 PM UTC

I'm a fan of AI coding tools but the trend of adding ever more autonomy to agents confuses me.

The rate at which a person running these tools can review and comprehend the output properly is basically reached with just a single thread with a human in the loop.

Which implies that this is not intended to be used in a setting where people will be reading the code.

Does that... Actually work for anyone? My experience so far with AI tools would have me believe that it's a terrible idea.

Re: Claude Code's new hidden feature: Swarms

#46

Post by djfdat » Sat, Jan 24, 2026, 4:52 PM UTC

basedrum wrote: post #25

How is this different from GSD: https://github.com/glittercowboy/get-shit-done I've been using that and it's excellent

Really boils down to the benefits of first party software from a company that has billions of dollars of funding vs similar third party software from an individual with no funding.

GSD might be better right now, but will it continue to be better in the future, and are you willing to build your workflows around that bet?

Re: Claude Code's new hidden feature: Swarms

#47

Post by ecto » Sat, Jan 24, 2026, 4:57 PM UTC

mohsen1 wrote: post #37

MetaMonk wrote: post #20

A guy who worked at docker on docker swarm now works at Anthropic so makes sense

Swarm is actually OpenAI's terminology https://github.com/openai/swarm

Swarm is actually bee terminology

Re: Claude Code's new hidden feature: Swarms

#48

Post by dang » Sat, Jan 24, 2026, 5:30 PM UTC

codethief wrote: post #3

https://xcancel.com/NicerInPerson/status/2014989679796347375 In his second post he included a link to GitHub: https://github.com/mikekelly/claude-sneakpeek

Thanks! We'll put those links in the toptext.

Re: Claude Code's new hidden feature: Swarms

#49

Post by bloppe » Sat, Jan 24, 2026, 5:33 PM UTC

Androider wrote: post #43

Looks like agent orchestrators provided by the foundation model providers will become a big theme in 2026. By wrapping it in terms that are already used in software development today like team leads, team members, etc. rather than inventing a completely new taxonomy of Polecats and Badgers, will help make it more successful and understandable.

Respectfully disagree. I think polecats are a reasonable antidote to overanthropomorphization.

Re: Claude Code's new hidden feature: Swarms

#50

Post by stingraycharles » Sat, Jan 24, 2026, 5:40 PM UTC

joshribakoff wrote: post #42

This is just sub agents, built into Claude. You don’t need 300,000 line tmux abstractions written in go. You just tell Claude to do work in parallel with background sub agents. It helps to have a file for handing off the prompt, tracking progress, and reporting back. I also recommend constraining agents to their own worktrees. I am writing down the pattern here https://workforest.space while nearly everyone is buildi…

It’s even less of a feature, Claude Code already has subagents; this new feature just ensures Claude Code actually uses this for implementation.

imho the plans of Claude Code are not detailed enough to pull this off; they’re trying to do it to preserve context, but the level of detail in the plans is not nearly enough for it to be reliable.