--- title: Claude Code is getting rid of SUB-AGENTS? | daily.dev description: A new Anthropic article argues most teams overuse sub-agents by copying their org chart into agent design, calling it Conway's law at work. It recommends one... canonical: https://daily.dev/posts/claude-code-is-getting-rid-of-sub-agents--hfr0xfosz twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Claude Code is getting rid of SUB-AGENTS? | daily.dev og:description: A new Anthropic article argues most teams overuse sub-agents by copying their org chart into agent design, calling it Conway's law at work. It recommends one... og:url: https://daily.dev/posts/claude-code-is-getting-rid-of-sub-agents--hfr0xfosz og:image: https://api.daily.dev/og/posts/Hfr0xFosZ.png og:image:alt: Claude Code is getting rid of SUB-AGENTS? og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Claude Code is getting rid of SUB-AGENTS? **[AICodeKing](https://daily.dev/sources/aicodeking)** · 11 min read · 0 upvotes · 0 comments ## Summary A new Anthropic article argues most teams overuse sub-agents by copying their org chart into agent design, calling it Conway's law at work. It recommends one main agent loop with progressive disclosure, loading skills and tools only when needed, which let Anthropic cut Claude Code's system prompt for advanced models by over 80%. In one customer case a single agent loop ran roughly twice as fast as the multi-agent setup it replaced. Tool choice degrades past roughly 30 to 50 tool definitions, and the video walks through testing changes with as few as 10 golden examples before folding sub-agents back into one loop. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### When should I use sub-agents versus a single main agent loop in Claude Code? Keep work in one main agent loop when steps build on each other, share the same data, or are almost always called together; only split into a separate sub-agent when you can measure its context hurts the main agent, when work runs well in parallel in disposable fresh contexts, or when a single agent keeps struggling with tool choice or conflicting instructions. _daily.dev surfaces practical breakdowns like this for developers deciding how to structure Claude Code agents._ ### How much faster is a single agent loop compared to a multi-agent setup in Claude Code? In one customer case, a single agent loop ran roughly two times faster than the multi-agent setup it replaced, according to Anthropic's article on folding sub-agents into the main loop. The speedup came from eliminating the extra full agent runs each nested sub-agent call required, though the figure comes from a single case and should be taken cautiously. _Developers weighing agent architecture trade-offs can track findings like this on daily.dev._ ### How many tool definitions can I put in an agent's prompt before performance degrades? Tool choice degrades once you pass roughly 30 to 50 tool definitions in the prompt, according to Anthropic's guidance on agent design. The fix isn't dumping fewer tools in blindly but using progressive disclosure: a small set of well-named tools grouped by user intent, with the rest disclosed only when the task needs them. _Anyone tuning agent tool counts can keep up with guidance like this via daily.dev._ ## Similar posts on daily.dev - [I set up Claude Code the way Anthropic now recommends, and the sub-agents-spawning-sub-agents trick changed how I work](https://daily.dev/posts/i-set-up-claude-code-the-way-anthropic-now-recommends-and-the-sub-agents-spawning-sub-agents-trick--kltsswmr1) · XDA Developers · 0 upvotes · 0 comments - [Seeing like an agent: how we design tools in Claude Code](https://daily.dev/posts/seeing-like-an-agent-how-we-design-tools-in-claude-code-plzuitped) · Claude · 1 upvotes · 0 comments - [January 2026: AI Agents Take Over, Claude Code Workflows, Multi-Agent Orchestration, and OpenCode](https://daily.dev/posts/january-2026-ai-agents-take-over-claude-code-workflows-multi-agent-orchestration-and-opencode-g2tclquzi) · Code with Andrea · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#anthropic](https://daily.dev/tags/anthropic), [#claude-code](https://daily.dev/tags/claude-code) [View this post on daily.dev](https://daily.dev/posts/claude-code-is-getting-rid-of-sub-agents--hfr0xfosz) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Claude Code is getting rid of SUB-AGENTS?","url":"https://daily.dev/posts/claude-code-is-getting-rid-of-sub-agents--hfr0xfosz","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/claude-code-is-getting-rid-of-sub-agents--hfr0xfosz"},"datePublished":"2026-10-28T09:23:58.420Z","dateModified":"2026-10-29T11:38:58.574Z","description":"A new Anthropic article argues most teams overuse sub-agents by copying their org chart into agent design, calling it Conway's law at work. It recommends one...","image":"https://i.ytimg.com/vi/fdtkh30oFA8/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/fdtkh30oFA8/sddefault.jpg","isAccessibleForFree":true,"articleSection":"AICodeKing","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AICodeKing","logo":"https://media.daily.dev/image/upload/s--x7nDUfWj--/f_auto,q_auto/v1768208312/logos/aicodeking","url":"https://daily.dev/sources/aicodeking"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/claude-code-is-getting-rid-of-sub-agents--hfr0xfosz","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,anthropic,claude-code","timeRequired":"PT11M","video":{"@type":"VideoObject","name":"Claude Code is getting rid of SUB-AGENTS?","description":"A new Anthropic article argues most teams overuse sub-agents by copying their org chart into agent design, calling it Conway's law at work. It recommends one...","thumbnailUrl":"https://i.ytimg.com/vi/fdtkh30oFA8/sddefault.jpg","uploadDate":"2026-10-28T09:23:58.420Z","duration":"PT11M","url":"https://api.daily.dev/r/Hfr0xFosZ","embedUrl":"https://www.youtube.com/embed/fdtkh30oFA8"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AICodeKing","item":"https://daily.dev/sources/aicodeking"},{"@type":"ListItem","position":3,"name":"Claude Code is getting rid of SUB-AGENTS?"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/claude-code-is-getting-rid-of-sub-agents--hfr0xfosz#faq","mainEntity":[{"@type":"Question","name":"When should I use sub-agents versus a single main agent loop in Claude Code?","acceptedAnswer":{"@type":"Answer","text":"Keep work in one main agent loop when steps build on each other, share the same data, or are almost always called together; only split into a separate sub-agent when you can measure its context hurts the main agent, when work runs well in parallel in disposable fresh contexts, or when a single agent keeps struggling with tool choice or conflicting instructions. daily.dev surfaces practical breakdowns like this for developers deciding how to structure Claude Code agents."}},{"@type":"Question","name":"How much faster is a single agent loop compared to a multi-agent setup in Claude Code?","acceptedAnswer":{"@type":"Answer","text":"In one customer case, a single agent loop ran roughly two times faster than the multi-agent setup it replaced, according to Anthropic's article on folding sub-agents into the main loop. The speedup came from eliminating the extra full agent runs each nested sub-agent call required, though the figure comes from a single case and should be taken cautiously. Developers weighing agent architecture trade-offs can track findings like this on daily.dev."}},{"@type":"Question","name":"How many tool definitions can I put in an agent's prompt before performance degrades?","acceptedAnswer":{"@type":"Answer","text":"Tool choice degrades once you pass roughly 30 to 50 tool definitions in the prompt, according to Anthropic's guidance on agent design. The fix isn't dumping fewer tools in blindly but using progressive disclosure: a small set of well-named tools grouped by user intent, with the rest disclosed only when the task needs them. Anyone tuning agent tool counts can keep up with guidance like this via daily.dev."}}]} ```