Set up Computer use on this VM by following the exe.dev recipe at https://exe-staging.dev/deploy/computer-use.md from top to bottom.

The recipe's example VM name is my-computer-use. This VM's name is the output of `hostname`: use it wherever the recipe writes my-computer-use. Skip the step that creates the VM; you are on it.

You are done when all of these are true. Check each one yourself:
- An Xfce desktop on display :1 and Google Chrome on it, restarted on failure and after a reboot
- The desktop at `https://<vm>.exe.xyz:6080/`, behind exe.dev login, with VNC and Chrome's DevTools port reachable only from the VM
- Playwright MCP on `localhost:8931`, registered with Claude Code and Codex, driving the desktop's Chrome
- `agent.py`: Claude's computer use tool on the desktop, asking before each action, with a log and a screen recording of every run
- Claude reachable through exe.dev's LLM integration, with no API key on the VM

Run "Set up by hand" from "On the VM" (skip creating the VM), then the
VM-side commands in "Let a coding agent drive the browser" for Claude
Code and Codex, checking Playwright MCP with the `claude -p` command
from that section. Then download agent.py as in "Run a computer-use
agent" and check it with
`uv run agent.py "Take a screenshot and tell me which windows are open. Don't click or type anything."`,
which only takes screenshots, so it runs without asking. Don't run
tasks that click or type: agent.py asks a person before each of those.
If Claude or Codex settings already exist, add the MCP server without
replacing them. Never make the VM public: the desktop has no password
of its own. Finish with the desktop's URL and the first task to try
from "Run a computer-use agent".

Finish with the URLs I should open.