Help › For AI agents
Text me when Claude Code is done or waiting
Start a long Claude Code task, walk away, and get a text when it's done or waiting for you: a permission prompt, a question, a finished run.
On this page
1. Put your API key in your shell profile
In ~/.bashrc or ~/.zshrc (not in a project file, so it never ends up in a repo):
export UX_KEY="YOUR_API_KEY"
Open a new terminal before starting Claude Code.
2. Text me when it's waiting (recommended)
Claude Code runs hooks on events. The Notification event fires when it's waiting for you. Add this to ~/.claude/settings.json:
{
"hooks": {
"Notification": [
{ "matcher": "idle_prompt",
"hooks": [ { "type": "command",
"command": "curl -s -X POST https://useralertx.com/cgi-bin/itmessages.cgi -H \"X-Api-Key: $UX_KEY\" --data-urlencode \"body=Claude Code is waiting for you\" >/dev/null" } ] },
{ "matcher": "permission_prompt",
"hooks": [ { "type": "command",
"command": "curl -s -X POST https://useralertx.com/cgi-bin/itmessages.cgi -H \"X-Api-Key: $UX_KEY\" --data-urlencode \"body=Claude Code needs your permission\" >/dev/null" } ] }
]
}
}
NoteDon't use the Stop hook: it fires after every reply and would text you constantly.
3. Or let Claude Code text you itself
claude mcp add --transport http useralertx https://useralertx.com/mcp --header "Authorization: Bearer $UX_KEY"
Then tell it, in a prompt or your CLAUDE.md: "When you finish a long task, text me a one-line summary via UserAlertX."
Full page: https://useralertx.com/claudecode.html
Related topics
Connect your AI agentGive your AI assistant UserAlertX and it can text you, ask your approval, read your agent inbox, email you summaries and send video messages.TeXt Approval: approve by textPut uxapprove in front of anything that should need your OK first: a backup cleanup, a deploy, a script an AI agent runs.