[{"data":1,"prerenderedAt":77},["ShallowReactive",2],{"term-p\u002Fplan-mode":3,"related-p\u002Fplan-mode":66},{"id":4,"title":5,"acronym":6,"body":7,"category":49,"description":50,"difficulty":51,"extension":52,"letter":16,"meta":53,"navigation":54,"path":55,"related":56,"seo":60,"sitemap":61,"stem":64,"subcategory":6,"__hash__":65},"terms\u002Fterms\u002Fp\u002Fplan-mode.md","Plan Mode",null,{"type":8,"value":9,"toc":42},"minimark",[10,15,19,23,35,39],[11,12,14],"h2",{"id":13},"eli5-the-vibe-check","ELI5 — The Vibe Check",[16,17,18],"p",{},"Plan mode is AI-first read-only planning — the AI reads your codebase, outlines what it'll do, and waits for you to say go. No files get touched. No code gets written. It just thinks out loud and shows you the plan. Think of it as the AI raising its hand before speaking. Shockingly useful for not waking up to a completely rewritten codebase.",[11,20,22],{"id":21},"real-talk","Real Talk",[16,24,25,26,30,31,34],{},"In Claude Code, plan mode (",[27,28,29],"code",{},"\u002Fplan"," or ",[27,32,33],{},"--plan",") sets the agent to read-only exploration before any changes. The model analyzes the codebase, identifies affected files, and produces a structured plan of action. No writes, no shell commands. You review and approve before execution begins. It's the professional version of vibing — which still counts as vibing.",[11,36,38],{"id":37},"when-youll-hear-this","When You'll Hear This",[16,40,41],{},"\"Run it in plan mode first — I want to see what it thinks before it touches anything.\" \u002F \"The plan mode output was honestly better than our sprint planning doc.\"",{"title":43,"searchDepth":44,"depth":44,"links":45},"",2,[46,47,48],{"id":13,"depth":44,"text":14},{"id":21,"depth":44,"text":22},{"id":37,"depth":44,"text":38},"vibecoding","Plan mode is AI-first read-only planning — the AI reads your codebase, outlines what it'll do, and waits for you to say go.","beginner","md",{},true,"\u002Fterms\u002Fp\u002Fplan-mode",[57,58,59],"Vibe Coding","Claude Code","Auto Mode",{"title":5,"description":50},{"changefreq":62,"priority":63},"weekly",0.7,"terms\u002Fp\u002Fplan-mode","EhxxqjBCpt39onbAoFn2HU2rjYHtyi_D40DjLSPomfY",[67,70,74],{"title":59,"path":68,"acronym":6,"category":49,"difficulty":51,"description":69},"\u002Fterms\u002Fa\u002Fauto-mode","Auto mode is Claude Code's permission classifier — the middle ground between confirm-everything and YOLO mode.",{"title":58,"path":71,"acronym":6,"category":72,"difficulty":51,"description":73},"\u002Fterms\u002Fc\u002Fclaude-code","ai","Claude Code is Anthropic's agentic coding tool that lives in your terminal.",{"title":57,"path":75,"acronym":6,"category":49,"difficulty":51,"description":76},"\u002Fterms\u002Fv\u002Fvibe-coding","Vibe coding is writing software by vibes — you describe what you want to an AI, it writes the code, and you just... vibe.",1775560920242]