Skip navigation
I managed to unlock a crazy new hidden feature in Claude Code called Swarms.
0:00 / 3:35

I managed to unlock a crazy new hidden feature in Claude Code called Swarms.

Mike Kelly

@NicerInPerson6.4K followers

Visit on X
2,903 likesDownloadOriginal post

566,747 views

I managed to unlock a crazy new hidden feature in Claude Code called Swarms. You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes. When you approve a plan, it enters a new "delegation mode" and spawns a team of specialists who: - Share a task board with dependencies - Work in parallel as teammates - Message each other to coordinate work Workers do the heavy lifting, coordinate amongst themselves, then report back.

56 Comments

Comments from the original post on X (Twitter)

  • Mike Kelly's profile picture

    @NicerInPerson

    I packaged up an unlocked build of claude code so everyone can try it out

    265 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    Update: it made the front page of HN but got pulled down my mods

    54 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    Update: it’s back up on the main page 🤷‍♂️

    55 likes

  • am.will's profile picture

    @LLMJunky

    This is very similar to codex new orchestration mode actually. Very interesting to see them both coming out with us at the same exact time

    39 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    Are codex subagents async yet? Claude code is event driven. Most harnesses are lagging here atm

    24 likes

  • am.will's profile picture

    @LLMJunky

    Yes they are. Gotta enable it in /experimental I wrote about them here! Thanks for the video, great work!

    35 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    Awesome. I need to get back to playing with codex then. The lack of async subagents kept me from using it as main driver.

    2 likes

  • am.will's profile picture

    @LLMJunky

    Yeah I totally get it. They're not quite as polished as Claude yet but we're heading in the right direction and the model is extremely smart. Enjoy and I followed you I'm looking forward to hearing more from you.

    7 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    Yes likewise!

    3 likes

  • Riz's profile picture

    @rizzytoday

    great tool to burn all your tokens

    28 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    Takes up less tokens to break up work across subagents

    31 likes

  • BL3's profile picture

    @SellingStrikes

    @rizzytoday Wrong.

  • Mike Kelly's profile picture

    @NicerInPerson

    @rizzytoday nah

    2 likes

  • BL3's profile picture

    @SellingStrikes

    First off, you didn't "unlock/find" Swarm Mode.. it was never HIDDEN lol.. I was running parallel sub-agents, full swarm setups with delegation, coordination boards, the whole thing, way before they dropped the official sub-agent update in summer 2025. So spare me the "revolutionary" act. Second, the token burn is obvious to anyone who's actually pushed these systems hard. Every single sub-agent turn is a fresh reasoning chain.. new prompt, new generation, new tokens. Then you got the lead agent delegating tasks (tokens), sub-agents reporting back (tokens), merging results (tokens), resolving conflicts (tokens), and all the context you gotta duplicate or summarize across agents so they don't work blind (more tokens). That's not theory, that's straight math: one complex task in a single thread might take X tokens end-to-end, but split it across 4-8 sub-agents with coordination loops and you're easily at 3-5x the burn, minimum. I know this because I live it.. my weekly limits vanish in a day or two when I'm swarming heavy projects, versus stretching a week+ on single-threaded runs. Same tasks, dramatically different token spend. Yeah, the builds come out cleaner and faster because the work gets properly parallelized and specialized. Nobody's denying the engineering efficiency. But token efficiency? Night and day worse. So when you hit me with that weak "nah," it just shows you haven't actually stress-tested this stuff at scale. Come back when you've burned through a few limits yourself instead of theorizing from the sidelines. Basic stuff, man.

    8 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    @rizzytoday yeah nah

    1 like

  • BL3's profile picture

    @SellingStrikes

    Yea I’m right.. If you can’t explain it just say it.. making a thread like you discovered something that’s been baked into the CLI before u even started using it.. is tool behavior. The FACTS.. For non-trivial tasks, total token spend routinely hits 3–5x (or higher) vs. a well-prompted single agent that iterates in one long thread. This isn't just theory; it's the consistent complaint across similar frameworks where heavy users hit rate limits way faster despite cleaner outputs.

    5 likes

  • Mike Kelly's profile picture

    @NicerInPerson

    @rizzytoday nah

    2 likes

  • Marcin Dudek's profile picture

    @MythThrazz

    It’s funny, always the feature I’m missing the most and spend hours tinkering on my own with the existing tools, end up being part of the “core” CC within weeks. Wonder which of hundreds of persistient memory systems will emerge victorious.

    22 likes

  • No Secret Rulers's profile picture

    @NoSecretRulers

    Delivering slop faster than ever!

    18 likes

  • Rohit Ghumare's profile picture

    @ghumare64

    You can try dedicated skills for this in

    12 likes