How to stop Claude Code asking permission every time

You give Claude Code a real job — refactor a module, run the suite, fix what breaks — and then you watch it stop. Not because it failed, but because it wants to run npm test and it needs you to say yes.

  Do you want to run this command?

  ❯ 1. Yes
    2. No, tell Claude what to do differently

Sitting there pressing Enter is fine when you are at the desk. It is useless when you have gone to a meeting, because the agent will wait for you the entire time. You come back an hour later to a run that stopped in the first two minutes.

Auto-Yes

TermLink has a per-session toggle called Auto-Yes. Turn it on, and TermLink watches the session for exactly that prompt — Claude's numbered permission menu — and confirms the highlighted option for you.

That is the whole feature. The agent asks, TermLink answers, the run keeps going. You go to your meeting and come back to a finished job instead of a blocked one.

It is off by default, and it is scoped to one session — turning it on for the refactor running on your workstation does not turn it on for the agent on your laptop.

What it does not do

This matters, so it is worth being blunt about it: Auto-Yes is a convenience, not a safety feature.

• It confirms whichever option is currently highlighted, which is normally Yes. It does not read the command Claude is about to run and form an opinion about whether that is a good idea.
• It only handles the numbered Yes/No menu. When Claude asks you a free-form question — which approach do you want, is this schema right — Auto-Yes leaves it alone and the agent waits for a human. That is deliberate.

So the rule of thumb is the boring one. Leave Auto-Yes on for work whose blast radius you already accept: a test run, a refactor inside one module, a build. Leave it off when Claude is touching anything you would want to look at before it happens — migrations, deletions, deploys, anything against production.

Why not just --dangerously-skip-permissions?

Claude Code has its own flag for skipping permission prompts entirely. It works, and if that is what you want, use it — but notice what you give up: the prompts stop existing at all, on that machine, for that whole session, whether or not you are watching.

Auto-Yes is a different trade. The prompts still exist. You can watch them scroll by. You can turn the toggle off mid-session the moment the agent starts doing something you would rather approve by hand, and the very next prompt waits for you again. It is a dial you keep your hand on, not a switch you flip at launch and forget.

Turning it on

Auto-Yes lives in the session view, next to the terminal:

1. Open the machine from your session list in the web client.
2. Run claude and start the job.
3. Flip Auto-Yes on.

The header shows Auto-Yes on for as long as it is active, and confirmed prompts are marked in the stream, so you can scroll back and see what got auto-answered.

And when the run finishes?

TermLink does not notify you — there is no push, no email, no browser notification today. What you get instead is a glanceable list: every machine you have registered shows that session's most recent Claude message on its card. One line each. You can tell at a glance which agent is still working and which one is sitting there waiting on a question Auto-Yes deliberately did not answer.

That is usually enough. Open the tab, read four lines, and go to the one that needs you.

---

Auto-Yes is free on every plan. See running Claude Code on a remote machine for the setup it slots into, or get started in about two minutes.