Get woken up on CI failures, deploy crashes, and runtime error spikes — without polling for them yourself. The agent then walks you through the fix; it does not apply fixes without your say-so.
Claude Code’s Monitor tool registers background watchers that fire on external events (CI failure, deploy crash, error threshold breach). Zero token cost while idle. Wakes only when something happens, shows you what fired, and suggests the right next command (/ci-fix, /restart, /sre, etc.) — you decide whether to run it.
In Claude Code (skip if auto-update is enabled):
/plugin marketplace update arthai
/plugin uninstall <your-bundle>@arthai # then reinstall, e.g. prime
/plugin install <your-bundle>@arthai
/reload-plugins
Then fully quit and reopen Claude Code. A running session loads its command list at
startup, so a newly added command won’t appear from /reload-plugins alone — only a full
restart (quit the app/CLI completely, not /clear) rebuilds the command set.
cd /path/to/your/project
/monitor/monitor doesn’t need any project detection step — just tell it what to watch:
/monitor logs <service> # watch a service's log output for error patterns
/monitor pr <owner/repo> # watch a GitHub repo for PR state changes
/monitor deploy <service> # watch deployment health
/monitor ci # watch CI run results
Each subcommand writes a watcher script to .claude/monitors/ and registers it with Claude
Code’s Monitor tool. There is no separate config-generation step — /monitor <subcommand>
does the setup directly, and confirms with a summary of what it’s watching and how to stop it
(/monitor stop [<watcher-id>]).
From this point, the watcher runs in the background at zero token cost until it sees a match.
| Event | What happens |
|---|---|
| A log line matches the error pattern | The agent wakes, shows you the error context, and suggests /ci-fix (test failure), /restart (crash), or /sre (infra error). It does not auto-fix — you confirm before anything runs. |
| A watched PR changes state | The agent wakes and reports the change. |
| A watched deploy’s health check fails | The agent wakes and reports the failure. |
| A CI run finishes | The agent wakes and reports the result. |
Monitor is intentionally hands-on-the-wheel: it replaces polling loops with an event-driven wake-up, but every remediation step still needs your confirmation.
/ci-fix, /sre, /fix, /qa, and /pr work exactly as before — a Monitor watcher just adds an event-driven wake-up on top. If you never start a watcher, behavior is unchanged.
/monitor stop <watcher-id> # stop one watcher
/monitor stop # stop all active watchers
/monitor with no arguments shows usage and lists currently active watchers (read from
.claude/monitors/.active).
/monitor| Bundle | Includes /monitor |
|---|---|
| prime | Yes |
| forge | No |
| sentinel | No |
| scalpel | No |
If your bundle doesn’t include /monitor, switch to prime (Step 1 above) to get it.
| Subcommand | Watches |
|---|---|
/monitor logs <service> |
Docker container logs or a log file, for a configurable error pattern (--pattern <regex>) |
/monitor pr <owner/repo> |
GitHub PR state changes (--state <open\|closed\|merged>), via the gh CLI |
/monitor deploy <service> |
Deployment health, via a health-check endpoint (--url <health-endpoint>) |
/monitor ci |
CI run results (--branch <branch>, --repo <owner/repo>), via the gh CLI |
There’s no webhook or platform-specific config to wire up — each subcommand writes a small bash watcher script and polls or tails the relevant source directly.