Live data from Hacker News

Viewing profile — AffableSpatula

AffableSpatula

HN member
Joined
Mon, Jan 31, 2011, 3:32 PM UTC
HN karma
619
Public activity
152 items

About AffableSpatula

affable, but not actually a spatula.

Recent public activity

  1. story
  2. comment
    Comment #48622142

    Sync your Claude Design projects into your repos (list/pull/push) straight over the API; perfect for scripts and there's a skill for agents too. `npx claude-design` `npx skills add…

  3. story
  4. story
  5. comment
    Comment #46745818

    You're absolutely right! I apologise — hopefully you can forgive me.

  6. comment
    Comment #46745734

    yep this is exactly how I use the main agent too, I explicitly instruct to only ever use background async subagents. Not enough people understand that the claude code harness is ev…

  7. comment
    Comment #46745030

    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 syste…

  8. comment
    Comment #46744935

    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 tas…

  9. comment
    Comment #46744869

    I think you've misunderstood what this is.

  10. comment
    Comment #46744735

    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 …

  11. comment
    Comment #46744698

    a similar question was asked elsewhere in the thread; the difference is that this is tightly integrated into the harness

  12. comment
    Comment #46744614

    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 cont…

  13. comment
    Comment #46744529

    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 c…

  14. comment
    Comment #46744502

    yeah I tend to agree. They're must be reaching the point where they can automate the analysis of claude code prompts to extract techniques and build them directly into the harness.…

  15. comment
    Comment #46744478

    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…

  16. comment
    Comment #46744338

    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 hav…

  17. comment
    Comment #46744324

    ha! The default system prompt appears to give the main agent appropriate guidance about only using swarm mode when appropriate (same as entering itself into plan mode). You can fur…

  18. comment
    Comment #46744301

    The difference is that this is tightly integrated into the harness. There's a "delegation mode" (akin to plan mode) that appears to clear out the context for the team lead. The har…

  19. story
    Claude Code's new hidden feature: Swarms

    https://xcancel.com/NicerInPerson/status/2014989679796347375 https://github.com/mikekelly/claude-sneakpeek

  20. story
  21. story
  22. story
  23. story
  24. comment
    Comment #41515495

    "You can build your own thing using card emulation via apps, but you will take all the risks." right! This is exactly what I've developed. I've built a new NFC application, with it…

  25. comment
    Comment #41512513

    Hi there, author here! I think you've highlighted a couple of things worth clarifying in the doc: 1. Apple having just announced it is opening up NFC to developers means that both …