How to reach your machines, run Claude Code on them, and keep an agent moving while you are somewhere else.
Four ways to reach an agent running on another machine, and what each one actually costs you — an exposed port, a detached daemon, a streamed desktop, or a relayed terminal.
Read it →Paste from the clipboard or drop a file onto the terminal. TermLink uploads it to the machine the agent is running on and types the saved path in for you, so your next prompt can just point Claude at the file — even when the agent is on another computer and you are holding a phone.
Read it →A laptop, a workstation, and a box that exists only to run agents. Keeping three or ten Claude Code agents in one list — and telling at a glance which one is waiting on you.
Read it →The Esc key is the one Claude Code cannot live without, and PowerShell eats it. Why the TermLink host defaults to cmd.exe on Windows, what that means for your sessions, and how to reach a Windows machine from a Mac or a phone.
Read it →A terminal on a phone sounds miserable. It is not, if the terminal is one your agent lives in — a control-key row, a chat-style message box, and the session still running on your own machine. No app to install.
Read it →Auto mode already asks you about less, but it still stops for the actions that matter — and if you are away, the run stops with it. Here is what each permission mode covers, what auto-accept edits does not, and how Auto-Yes keeps a long run moving while you are gone.
Read it →Start Claude Code on your workstation, walk away, and pick the conversation back up from a browser or phone. Two commands on the host, no SSH keys, and Auto-Yes to keep a long run moving while you are gone.
Read it →Reach a shell on your own machine from anywhere — install the binary, sign in with Google, run one command on the host, and connect. No SSH keys, no VPN, no open ports, nothing to install on the device you connect from.
Read it →