An encrypted tunnel to another computer
An agent can run commands freely in a terminal, as the last article argued. It still needs a terminal to run in. That terminal does not have to be on your phone — it can be the Mac mini that never gets switched off at home, or the workstation at the office, as long as you can reach it.
Reaching it is what SSH is for. It opens an encrypted tunnel between your device and another machine, carrying the text you type over and the text it prints back. None of the hops in between can read any of it.
Why "another machine" rather than a cloud service
Browser agents and cloud IDEs connect you to a machine too. The difference is whose machine it is.
SSH connects you to your own. Your files are there. Your API keys are there. Every package you installed, every environment variable you set. Nothing has to move onto someone else's server, and the changes stay where they were made — there is nothing to sync back afterwards.
Keys aren't the safer option — they're the easier one
SSH takes passwords or keys, and the choice gets framed as security versus convenience. It is not a trade-off. Keys win on both.
A private key stays on your device. A public key goes on the other machine. At login the two verify each other and you type nothing. Passwords can be brute-forced; the length of a key puts that out of reach. Set it up once and every connection afterwards runs the same way.
You don't need to turn your computer into a server
People hear "SSH" and picture racks in a data centre. You are flipping a switch. On a Mac it is System Settings → General → Sharing → Remote Login. On Linux it is usually starting a service called sshd, which most distributions already ship.
Nothing else about the machine changes. It is still your everyday computer, with one more door you can knock on from outside.
Then you put your phone away, the tunnel drops, and the agent dies with it. Unless…