Deciding how much to hand over

What you will learn The four autonomy levels you choose when handing over a task, and which situation each suits.

The four levels

When you direct a task you also choose the width of its autonomy.

Choice	How it behaves
Fully automatic (default)	runs to the end without stopping to ask
Auto-approve file edits	file changes proceed unasked; everything else confirms as needed
Plan only	shows you a plan and does not execute
Standard	Claude Code's own default behaviour

When to use each

Plan only — first time, or risky

text

Use when:  □ it's your first time working in this folder  □ you have no feel for what it will touch  □ the work is hard to undo (migrations, bulk edits)  □ you have to show someone else the plan

It is safe because nothing executes. It also produces nothing.

Auto-approve file edits — the recommended starting point

File changes happen on their own; anything else (running commands and so on) asks for confirmation. It draws the line between what can be undone and what cannot.

If you use git, file changes are generally reversible. That is what makes this level the balance point between safety and convenience.

It is not the default, so you have to select it. See the box below.

Fully automatic — this is the default. Which is why you must be careful

If you choose nothing when creating a task, you get this level. It runs to the end without stopping to ask, so for a folder you are new to, or work that is hard to undo, always change it to something else.

text

Use when:  □ you've done this type of work several times with stable results  □ nobody is watching, as with scheduled runs  □ failure has small consequencesDo not use when:  □ it's a type of work you're doing for the first time  □ it affects production  □ it's hard to undo

Standard — Claude Code as-is

Exactly how you have always used Claude Code. For people who are already comfortable with it.

How to climb

graph TD
  A["Plan only<br/>run it a few times"] --> B["Do the results match expectations?"]
  B -->|"yes"| C["Auto-approve file edits"]
  B -->|"no"| D["Fix the instruction"]
  D --> A
  C --> E["Have you done this type several times?"]
  E -->|"yes"| F["Fully automatic"]

Do not go straight to fully automatic. Checking the results at each step and climbing is faster — because there is no incident to clean up.

Different per working directory

This is why splitting working directories by risk was suggested.

Folder	Default autonomy
Experimental / personal projects	fully automatic
Work projects	auto-approve file edits
Anywhere with production deployment scripts	plan only

Set a different default per folder and the right level applies without you choosing every time.

Autonomy and safety nets are separate

Raising autonomy and having safety nets are two different things.

text

High autonomy  +  safety nets     → fast and safeHigh autonomy  +  no safety nets  → dangerousLow autonomy   +  no safety nets  → slow and anxious

Safety nets look like this:

text

□ commit before starting□ keep the working directory narrow□ never register a folder holding production data□ the habit of checking results

With safety nets you can raise autonomy, because you can undo.

Common misconceptions

"Isn't fully automatic just the best?"

Fast and good are different. Set fully automatic on a type of work you are doing for the first time and the agent goes just as hard in the wrong direction. With no checkpoint, you find out later.

"Isn't plan only a waste, since there's no output?"

The time spent reading the plan and fixing the instruction is shorter than the time spent undoing something executed wrongly. Especially for the first few runs.

Check yourself

1. Which level do you get if you choose nothing?

Answer

Fully automatic. It runs to the end without stopping to ask, so for a folder you are new to or work that is hard to undo you must change it. The balance point between safety and convenience is auto-approve file edits, but you have to select that yourself.

2. How should you climb through autonomy levels?

Answer

Plan only → auto-approve file edits → fully automatic, checking at each step that the results match expectations. Going straight to fully automatic costs more in incident cleanup.

3. Under what condition is it fine to raise autonomy?

Answer

When safety nets exist — commit before starting, a narrow working directory, production data excluded, the habit of checking results. If you can undo it, you can raise autonomy.

Next, the always-open command window → The terminal