[{"data":1,"prerenderedAt":78},["ShallowReactive",2],{"term-s\u002Fsubagent":3,"related-s\u002Fsubagent":60},{"id":4,"title":5,"acronym":6,"body":7,"category":40,"description":41,"difficulty":42,"extension":43,"letter":44,"meta":45,"navigation":46,"path":47,"related":48,"seo":54,"sitemap":55,"stem":58,"subcategory":6,"__hash__":59},"terms\u002Fterms\u002Fs\u002Fsubagent.md","Subagent",null,{"type":8,"value":9,"toc":33},"minimark",[10,15,19,23,26,30],[11,12,14],"h2",{"id":13},"eli5-the-vibe-check","ELI5 - The Vibe Check",[16,17,18],"p",{},"A subagent is a junior teammate you delegate a chunk of work to. Instead of doing the research yourself and cluttering your own head with every dead end, you hand it off, they go figure it out in their own space, and they come back with just the summary you actually need. Your main context stays clean, and theirs gets thrown away when they're done.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25],{},"A subagent is a separately invoked LLM agent instance, spawned by a parent agent or orchestrator to handle a bounded subtask, typically running in its own context window with its own tool access. It returns a condensed result to the parent rather than its full working trace, which keeps the parent's context from filling up with intermediate scratch work.",[11,27,29],{"id":28},"when-youll-hear-this","When You'll Hear This",[16,31,32],{},"\"Spin up a subagent to handle the migration, keep the main context clean.\" \u002F \"The subagent came back with a three-line summary instead of dumping its whole scratchpad.\"",{"title":34,"searchDepth":35,"depth":35,"links":36},"",2,[37,38,39],{"id":13,"depth":35,"text":14},{"id":21,"depth":35,"text":22},{"id":28,"depth":35,"text":29},"ai","A subagent is a junior teammate you delegate a chunk of work to.","intermediate","md","s",{},true,"\u002Fterms\u002Fs\u002Fsubagent",[49,50,51,52,53],"Multi-Agent","Agent Loop","Orchestrator-Worker Pattern","Context Window","Claude Code",{"title":5,"description":41},{"changefreq":56,"priority":57},"weekly",0.7,"terms\u002Fs\u002Fsubagent","5ESfvknI4B8hGkGsexnlvmG9N_OjOQLZzAsp21m2jfk",[61,64,68,72,75],{"title":50,"path":62,"acronym":6,"category":40,"difficulty":42,"description":63},"\u002Fterms\u002Fa\u002Fagent-loop","The agent loop is the heartbeat of any AI coding agent: think, act, look, repeat.",{"title":53,"path":65,"acronym":6,"category":40,"difficulty":66,"description":67},"\u002Fterms\u002Fc\u002Fclaude-code","beginner","Claude Code is Anthropic's agentic coding tool that lives in your terminal.",{"title":52,"path":69,"acronym":6,"category":70,"difficulty":42,"description":71},"\u002Fterms\u002Fc\u002Fcontext-window","vibecoding","A context window is how much text an AI can 'see' at once — its working memory.",{"title":49,"path":73,"acronym":6,"category":40,"difficulty":42,"description":74},"\u002Fterms\u002Fm\u002Fmulti-agent","Multi-agent means multiple AI agents working together, each handling a different task.",{"title":51,"path":76,"acronym":6,"category":40,"difficulty":42,"description":77},"\u002Fterms\u002Fo\u002Forchestrator-worker-pattern","This is a project manager who breaks a big job into tickets, hands each one to a specialist, and stitches the finished pieces back into one result, except...",1792528127612]