Claude Code introduces specialized sub-agents

(docs.anthropic.com)

117 points | by tekkertje 19 hours ago

7 comments

  • pjm331 9 hours ago
    I've made a few attempts at manually doing this w/ mcp and took a brief look at "claude swarm" https://github.com/parruda/claude-swarm - but in the short time I spent on it I wasn't having much success - admittedly I probably went a little too far into the "build an entire org chart of agents" territory

    the main problem I have is that the agents just aren't used

    For example, I set up a code reviewer agent today and then asked claude to review code, and it went off and did it by itself without using the agent

    in one of anthropic's own examples they are specifically telling claude which agents to use which is exactly what I don't want to have to do:

    > First use the code-analyzer sub agent to find performance issues, then use the optimizer sub agent to fix them

    My working theory is that while Claude has been extensively trained on tool use and is often eager to use whatever tools are available, agents are just different enough that they don't quite fit - maybe asking another agent to do something "feels" very close to asking the user to do something, which is counter to their training

    but maybe I just haven't spent enough time trying it out and tweaking the descriptions

    • conception 8 hours ago
      Roo code does this really well with their orchestration mode, there’s probably a way to have a claude.md to do this as well. The only issue with roo is it’s “single threaded” but you do get the specific loaded context and rules for a specific task which is really nice.
    • oc1 5 hours ago
      the same problem with mcp. as well as claude md. most of the time they aren't used when it would be appropriate. what's the point of this agents and standards when you can't make them reliably being used by your model..
  • bomewish 14 hours ago
    Has CC become much stupider in recent weeks, or is it me? Any anecdata out there?
    • _--__--__ 12 hours ago
      People speculate somewhat seriously that Claude (especially given its French name) picked up at some point that you aren't supposed to work as hard in July and August.
      • sunaookami 5 hours ago
        That one guy on Twitter that posted this wrote it as a joke and everyone took it seriously. It's not true. It works the same for me.
        • oc1 5 hours ago
          How do you know? It acts much lazier in the recent summer months for me..
          • stavros 3 hours ago
            How have you disproved the hypothesis that it recently got dumber and it just happens to be summer?
            • AbstractH24 2 hours ago
              Clearly, it compared performance to last summer

              (Just to be clear, I have no idea what on this thread to take seriously and not and who is. I'm joking at least.)

              • stavros 2 hours ago
                That won't do it, though, you'd have to observe it being dumber on June 1 and smart again on September 1 for years.
      • madrox 11 hours ago
        How long before we hire psychiatrists instead of engineers to debug AI
        • OrsonSmelles 10 hours ago
          Well, we could start with some ELIZA instances.
          • lubujackson 8 hours ago
            I see that you feel we could start with some ELIZA instances. Can you tell me more about that?
        • taneq 2 hours ago
          Robopsychologists, you say?
        • nialse 6 hours ago
          To be frank psychiatrists, being MDs, would likely prescribe medication and I’m not sure how that would help. As a licensed psychologist I have ideas on how to debug AI though.
          • AbstractH24 2 hours ago
            Why, we'll just have specialized agents for ingesting Prozac and that'll magically solve everything.
    • nico 13 hours ago
      I don’t know about stupider, but definitely less reliable/available

      A couple days ago I was getting so many api errors/timeouts I decided to upgrade from the $20 to the $100 plan (as I was also regularly hitting rate limits as well)

      It seemed to fix the issue immediately. But today, the errors came back for about half an hour

      • SOLAR_FIELDS 12 hours ago
        It goes down usually around 1400-1500 UTC. Europeans are still awake and once the west coast joins in the fray Anthropic falls over.

        Pretty rare to get a 529 outside of that time window in my personal experience, at least during the USA day.

      • data-ottawa 8 hours ago
        Their status page for the week is rough. They’re down to 98% uptime.

        Hopefully they work out whatever issue is going on.

        https://status.anthropic.com/

    • audinobs 1 hour ago
      I think it is like with a gambling game that you get on hot and cold streaks, runs based on chance.

      The model feels like it has got stupid when you get on a cold streak after a hot hand.

    • illusive4080 14 hours ago
      Not for me. It gets worse when context is nearly full. I like to compact or clear context more often than it does automatically.
      • nico 13 hours ago
        Do you do this via settings or just keep track of it and manually ask it to do it more often?
    • laborcontract 10 hours ago
      Insert something to the tune of: “never read files in slices. Instead, whenever accessing a file, you must read a file in entirety[..]” at the beginning of every conversation or whenever you’re down to burn more credits/get better results.

      A great deal of claude stupidity is due to context engineering, specifically due to the fact that it tries its hardest to pick out just the slice of code it needs to fulfill the task.

      A lot of the annoying “you’re absolute right!” come from CC incrementally discovering that you have more than 10 lines of code in that file that pertains to your task.

      I don’t believe conspiracies about dumbed down models. Its all context pruning.

      • oc1 5 hours ago
        so claude code does the same shit like cursor?
    • slantaclaus 10 hours ago
      I feel like it’s gotten better recently
  • lvl155 3 hours ago
    Here my main problem with sub-agents WITHIN Claude Code. They don’t allow you to use other models. Let’s be honest it’s 99% Sonnet.
    • stillsut 16 minutes ago
      Great point, I've found Sonnet really can't be beat on many tasks, but increasingly finding Gemini-Pro and o3 handle the tough bugs and refactors best.

      That's why I've been using agro to launch agents from each of the main LLM vendors and checking their results when I'm stuck: https://github.com/sutt/agro/blob/master/docs/index.md

  • Garlef 7 hours ago
    One nice realization I had when using a similar feature in roo:

    You don't need a full agent library to write LLM workflows.

    Rather: A general purpose agent with a custom addition to the system prompt can be instructed to call other such agents.

    (Of course explicitly mamaging everything is the better choice depending on your business case. But i think it would be always cheaper to at least build a prototype using this method.)

  • Dlanv 10 hours ago
    I wonder if this is also a good way to create experts for specific tasks/features of a codebase.

    For example, a sub-agent for adding a new stat to an RPG. It could know how to integrate with various systems like items, character stats component, metrics, and so on without having to do as much research into the codebase patterns.

  • T0Bi 16 hours ago
    So everything claude-flow¹ already does but worse (I guess?).

    ¹ https://github.com/ruvnet/claude-flow

    • jampa 10 hours ago
      > IMPORTANT: Claude Code must be installed first:

      > [...]

      > # 2. Activate Claude Code with permissions

      > claude --dangerously-skip-permissions

      Bypassing all permissions and connecting with MCPs, can't wait for "Claude flow deleted all my files and leaked my CI credentials" blog post

      • T0Bi 5 hours ago
        There are already several of such blog posts.

        I use the .devcontainer¹ from the claude-code repository. It works great with VSC and let's you work in your docker container without any issues. And as long as you use some sort of version control (git) you cannot really lose anything.

        ¹ https://github.com/anthropics/claude-code/tree/main/.devcont...

      • data-ottawa 8 hours ago
        I would like a simple tool to run Claude in a container with only read/write access to provided folders.

        I’ve set it up bespoke but the auth flow gets broken.

        • T0Bi 5 hours ago
          I use the .devcontainer¹ from the claude-code repository. It works great with VSC and let's you work in your docker container without any issues. And as long as you use some sort of version control (git) you cannot really lose anything.

          ¹ https://github.com/anthropics/claude-code/tree/main/.devcont...

        • oarsinsync 7 hours ago
          Have you considered asking Claude code to write this for you?
    • SOLAR_FIELDS 12 hours ago
      That guy doesn't even understand how his own software works. Is anyone actually using this thing and putting their code into production?
      • AbstractH24 2 hours ago
        Not only are people using them, they are building startups based on them. And then selling said startups.
      • lubujackson 8 hours ago
        It's extreme dogfooding where he is making a mashed potato volcano where Claude agents are the potatoes and your sanity is the gravy.
    • dchuk 14 hours ago
      I’ll admit this looks comprehensive, but man oh man does this seem complicated and over doing it
    • nazgul17 14 hours ago
      Except it's not in alpha phase
    • dazzaji 8 hours ago
      Ruv (of Claude Flow) seems to like the new Claude Agents a lot, and already is leveraging them in Claude Flow. He waxes positively on the topic here: https://www.linkedin.com/posts/reuvencohen_spent-the-afterno...
    • himeexcelanta 12 hours ago
      This looks like a yarn ball (in not a good way)
    • lvl155 3 hours ago
      What did you make me read. Right off the bat, it says v2 alpha.

      Bro…

  • physarum_salad 16 hours ago
    [dead]