Monitor Tool - Claude Code
Background monitoring of logs, files, and long-running processes.
Monitor watches a process, file, or log stream in the background and pushes new output into the conversation as it arrives.
What it does
You hand Monitor a command or a file path and it keeps streaming. Each line of output becomes a notification Claude can react to. It's designed for the "until this condition is true" pattern - tail a deploy log until you see "ready", watch a test file for a green run, or poll a dev server's health endpoint.
When to use it
- Waiting on a deploy or CI job without wasting a
sleeploop. - Tailing a log for a specific event.
- Keeping eyes on a dev server while Claude works on other code.
- Long-running background work where polling would be wasteful.
Gotchas
- Monitor is in preview. Behavior may change between Claude Code releases.
- Very chatty output floods the conversation quickly. Filter at the source.
- Always stop the monitor when you're done or it burns context for nothing.
Official docs: https://code.claude.com/docs/en/tools-reference.md#monitor-tool
Technical content at the intersection of AI and development. Building with AI agents, Claude Code, and modern dev tools - then showing you exactly how it works.
Get the weekly deep dive
Tutorials on Claude Code, AI agents, and dev tools - delivered free every week.
Was this helpful?
