Run an agent's commands in one click
1:22 · 5 chapters ·
Claude Code and Codex end their answers with commands to run: npm test, npm run dev, a clean reinstall. In lpm you don't copy them into another terminal: hover a command and click Run to see its output in a card, open a long-running one in a new tab, or ⌘-click it to run it straight away. Risky commands like rm -rf ask once more first.
Transcript
The narration, chapter by chapter. Pick a time to play from there.
Intro
Your agent suggests a command? Don't paste it into another terminal. Click it, and it runs right there.
Ask Claude Code
Open a project, click Claude in the header, and ask how to run the tests and start the dev server. Send it, and Claude answers with the commands.
Click to run
Hover a command, like npm test, and a Run chip appears right next to it. Click Run, and the output opens in a card over the terminal. All three tests passed, and Claude's answer is still right there. For a command that keeps running, like the dev server, choose Run in new tab, and it gets a terminal of its own.
Codex too
It works the same in Codex. Click Codex in the header, ask how to lint the code and do a clean reinstall, and send it. Even faster: hold Command and click npm run lint itself. It runs straight away, no chip needed.
Risky commands
A command that can do damage, like this clean reinstall, asks once more before it runs, so you choose Run anyway or Cancel. Now every command your agent suggests is one click away, in Claude Code, Codex, or any terminal tab in lpm.
