Skip to main content

Claude Code Basics Lesson 22 of 46

Plan Mode: Get the Plan Before the Work

In short
  • In Plan mode Claude looks, explores, and tells you what it would do — without touching anything.
  • It's there to catch early that you'd each understood something different.
  • Your role changes: from executor to approver.
  • Not for everything: it pays off on large jobs or where the path isn't obvious.

"Tell me what you'd do first"

With a new collaborator, before an important job, you wouldn't say "go ahead." You'd say: "walk me through how you're planning to do this." Not because you don't trust them — because in two minutes you find out whether you're both picturing the same thing.

Plan mode is that gesture. Claude goes and looks at the situation — opens the files, builds a picture, explores — and then shows you a plan instead of executing it. Your files, meanwhile, stay untouched.

It's the first rung on the ladder of modes: the most cautious of all, and — paradoxically — the one that makes you work better, not just safer.

What's actually happening while it plans

Careful not to mistake it for a pause. In Plan mode Claude is genuinely working: it reads your files, looks at how the folder is organized, builds a picture. It just stops before writing anything.

And that's exactly what makes the plan useful: it isn't an invented outline, it's an outline built by looking at the real situation.

The cheapest moment to catch a misunderstanding

This is the real payoff, and it isn't safety. When you read the plan, almost always one of three things happens:

  • It all checks out. You give the go-ahead and move on with confidence.

  • Something's missing. You catch it while reading, tell Claude, the plan updates. Cost: one sentence.

  • It had understood something different. This is the golden case. Because that misunderstanding existed either way — the only difference is whether you find out now or after the work is done.

Fixing a line of the plan costs a sentence. Catching it afterward costs the finished work, plus the work of undoing it.

Your role changes

There's a side effect worth being aware of: with a plan in front of you, you stop being the one who executes and become the one who approves.

It's a different skill, and it has to be learned: reading a plan carefully, asking what's missing, saying "no, do it this way instead." The people who get the most out of these tools aren't the ones who write the most elaborate requests: they're the ones who read plans well.

When to use it, and when it's overkill

  • Yes when the job touches a lot of things at once, when the path isn't obvious, when undoing it would be a mess.

  • No when the task is tiny: if the plan is longer than the work, the plan is overkill.

In the desktop app you pick it from the modes next to the text box. From the terminal you get there with the shortcut that cycles through modes. And if you don't feel like looking for it, the poor man's version also works: just tell it — "don't change anything, first tell me how you'd do it" — which gets you nearly the same result with one thing missing: the guarantee. The real plan is the one where the files can't be touched, by construction.

What's next

The plan tells you what Claude intends to do. The other half of the problem remains: once it's done, how do you know if it turned out well? In the next lesson you'll learn to give it a yardstick.

Did you get it?

Two minutes, no grade. Trying to answer — even getting it wrong — cements the concepts far more than rereading. Not in the mood? Skip it: the lesson still counts as complete.

What can Claude do in Plan mode?

What's the real payoff of planning first?

Which jobs is it worth switching to plan mode for?

Course Claude Code Basics
  1. Chapter 1 Introduction

    1. 1 The Claude Ecosystem and Where Claude Code Fits
    2. 2 What Claude Code Is: The Collaborator Who Walks Into Your Studio
    3. 3 How an Agent Works: The Loop
  2. Chapter 2 What's Underneath

    1. 4 Claude Code in Action: The Loop, for Real
    2. 5 The Model Has No Memory: It Starts Over Every Time
    3. 6 The Harness: The Engine and the Gear Around It
    4. 7 The Map: Four Buckets
  3. Chapter 3 You Choose the Engine

    1. 8 There's No Single Claude: The Model Lineup
    2. 9 Which Model for Which Job
    3. 10 Effort: How Hard It Should Think
    4. 11 Model or Effort? The Question That Trips Everyone Up
    5. 12 The Bill: Why Saving Money Can Cost You More
  4. Chapter 4 First Time at the Controls

    1. 13 Where to Run It: Four Doors In
    2. 14 What You Need Before You Start
    3. 15 Installing Claude Code
    4. 16 The Folder: Where You Open It Decides What It Works On
    5. 17 Choosing the Engine, in Practice
    6. 18 Your First Task: Small, Yours, and It Works
  5. Chapter 5 What You Let It Touch

    1. 19 Why It Asks for Permission
    2. 20 The Rules: Always Yes, Ask Me, Never
    3. 21 The Modes: How Much Leash You Give It
    4. 22 Plan Mode: Get the Plan Before the Work
    5. 23 Verification in the Loop: Give It a Yardstick
    6. 24 Example: Putting the Bucket Together
  6. Chapter 6 What It Knows About You

    1. 25 CLAUDE.md: The Notes It Reads the Moment It Walks In
    2. 26 How to Write a CLAUDE.md That Actually Works
    3. 27 The Context Window: How Much It Can Hold at Once
    4. 28 Cleaning Up: Compact and Clear
    5. 29 Automatic Memory
    6. 30 Example: From Repeating Yourself to Never Again
  7. Chapter 7 Skills

    1. 31 What a Skill Is: A Procedure Written Once
    2. 32 Creating Your First Skill
    3. 33 The Description Decides Whether It Gets Used
    4. 34 Example: A Skill That Saves You the Week
  8. Chapter 8 How Many You Put to Work

    1. 35 The Subagent: A Helper With Its Own Desk
    2. 36 When a Helper Is Worth It (and What It Costs)
    3. 37 Teams: When Agents Talk to Each Other
    4. 38 Example: Searching Without Cluttering the Desk
  9. Chapter 9 What It's Connected To

    1. 39 MCP: The Standard Plug Into Your Tools
    2. 40 Plugins: Packaging Up and Borrowing
    3. 41 Example: When You Stop Copying and Pasting
  10. Chapter 10 Automating the Setup

    1. 42 Hooks: The Thing That Always Happens
    2. 43 Where It Fires and What It Can Do
    3. 44 When You Actually Need One (and When It's Too Much)
  11. Chapter 11 Wrap-Up

    1. 45 The Project: Your Expense Tracker
    2. 46 Wrap-Up: What You're Taking Home
From a Confusing Brief to a Complete UX/UI A vague brief becomes a navigable app. Product Ad From a Single Photo A photo becomes an animated ad, no code required. Get Claude to Watch Your Videos Claude watches your videos and turns them into text. Higgsfield Inside Claude Code Generate images and video while you code in Claude Code. Turn a Loom Recording Into a Web Page A screen recording becomes a web page, no code. Vertical Shorts With NotebookLM Your sources become a vertical short. Luxury Landing Pages on Lovable A luxury landing page from a single prompt. Excalidraw Running Locally Excalidraw free on your computer, no code. Mistral OCR in Your Workflow Extract text from documents with Mistral OCR. Claude SEO in the Terminal 25 free SEO skills inside Claude Code. Google Search Console inside Claude Code Search Console data inside your terminal. Claude Code Routines Claude working on its own, computer off. Clone a Landing Page in React With v0 Clone a real landing page into React code. Context Economy With Claude Work light and don't burn through Claude's limits. From Prompt to Self-Improving Skill Claude skills that learn from your mistakes. From NotebookLM to Canva: Presentations NotebookLM slides, finally editable in Canva. The Map for Understanding Every AI Tool 12 categories for placing any AI tool. Transparent PNGs With ChatGPT Real transparency, not a fake checkerboard. Animated Infographics With Gemini Infographics that loop, animated with Gemini. Market Research With Deep Research Deep Research as your market analyst. Get Cited by AI Search Engines (AEO) Become a source that ChatGPT and Perplexity cite.