Skip to main content

Claude Code Basics Lesson 18 of 46

Your First Task: Small, Yours, and It Works

In short
  • The first task has to succeed: so small, yours and checkable.
  • It's not there to measure Claude Code: it's there to make you go through the whole motion once.
  • You'll see a permission request pop up: that's normal, and it's the bridge to the next chapter.
  • If you don't like the result, you tell it: correcting is part of the loop.

How to pick your first task

There's one rule, and it's not about playing it safe: the first task has to succeed. A first attempt that goes well gives you the confidence to try a hundred more; a first attempt that fails convinces you "this isn't for me," which is almost always false.

So pick something with three qualities:

  • Small. One single thing, done in a couple of minutes.

  • Yours. Something real of yours, not a fake exercise: you feel the difference between "it worked" and "it actually helped me" right away.

  • Checkable. You have to be able to look at the result and say for sure whether it's right or not.

A few ideas, if nothing comes to mind

  • Drop three or four documents in a folder and ask it for an index of what they contain.

  • Take a batch of files with messy names and get it to rename them according to a pattern you decide.

  • Give it a long piece of text and ask it to pull out a list of the key points, saved into a new file.

  • Have it tidy up a folder where you've dumped stuff at random, according to a rule you explain to it.

Notice what they have in common: none of them requires a single line of code. They're office jobs, and that's exactly the point of this course.

The bottom part of the Claude Code window: the working folder, the field where you write the request, and on the row below, Manual mode on the left and the Opus 5 model with High effort on the right.
This is where you write the task. On the row below, the three commands from the next chapters are already there: the mode on the left, the model and the effort on the right.

What happens while it works

You'll recognize all of this by now, because you've already seen it in chapter 2: it looks around, says what it's about to do, acts, checks, and finally talks to you.

With one new thing: at some point it stops and asks you for permission. That's not a glitch, and it's the most important thing in this lesson. The model asked for a tool that actually touches your files, and before using it, the toolkit checks with you.

How it shows up, in the two places:

  • In the desktop app — by default you're in Manual mode: Claude proposes the change and shows you a comparison between the file as it was and as it would become, with two buttons to accept or reject. Until you accept, your file isn't touched. If you reject, it asks how you'd rather proceed.

  • From the terminal — the request shows up inline, in the flow of text, and you answer right there.

For now, look at what it's asking and, if it looks right to you, say yes.

If the result isn't what you wanted

It happens, and it's normal. The right reaction isn't to start over from scratch, or to quietly fix it by hand: tell it. "Not like that: more like this." You're inside a loop, and correcting is the intended way to use it.

In most cases it's settled right there, without touching either the model or the effort.

What's next

You've done the full loop: installed it, opened it in the right folder, picked the engine, given it a task, gotten a result. From here on you're no longer learning how to get it started: you're learning how to direct it.

And it starts with the question that already popped up on your screen by itself, when it asked for permission: what do I let it touch? That's the first bucket, and it's the next chapter.

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 qualities should the first task have?

While it's working, it stops and asks you for permission. What does that mean?

The result isn't what you wanted. What's the right reaction?

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.