Anthropic is now recommending that companies REMOVE unnecessary subagents from their AI systems.
This is a pretty significant shift in agent architecture, with their team finding that a single agent equipped with skills can frequently outperform complex multi-agent systems, and one customer seeing roughly 2x faster execution.
The emerging rules of thumb:
→ Skills: Teach the agent HOW to do something, including procedures, expertise, and instructions.
→ Tools / MCP: Give the agent the ability to DO things through APIs, actions, and live data.
→ Subagents: Use for parallel work, isolated context, or tasks a single agent struggles with.
The interesting part is progressive disclosure. Instead of spawning specialized agents or stuffing everything into a giant prompt, one agent discovers and loads skills and tools as needed.
Their advice is to fold existing subagents into the main loop, turn their instructions into skills, expose their actions as tools, and run evals to see if performance holds up.
As models have gotten smarter, improving agent architecture is becoming less about what you can add and more about what you can delete.
https://t.co/DNq60Skkmc
I had this feature cooked since 3 weeks ago but it was too powerful to be released sooner, hope you enjoy it!
any feedback is useful, the team read everything (Windows is coming soon I promise)
script based editing is live in HyperFrames Studio
edit long-form and scripted videos from the script itself
auto speech cleanup takes out the pauses and ums for you
then click any word and ask for a motion graphic right at that moment
get started ↓
@Jera_Value Las skills vienen pre-instaladas en la desktop app, para templates tienes https://t.co/HyHVRHf46u con mas de 300 componentes tipo shadcn e hicimos open source los launch videos de HyperFrames aqui: https://t.co/YNWNsBSSaf