npx claudepluginhub 1Shot-Labs/marketplace --plugin chief-of-staff# /monitor Command Access real-time monitoring, metrics, alerts, and debugging features. ## Usage ## Subcommands ### Dashboard Open the monitoring dashboard overview. ### Alerts View and manage alerts. ### Metrics View system and application metrics. ### Logs View and search logs. ### Debug Enable/disable debug mode with detailed logging. ## Examples ### Quick Status Check Shows overview of system health, active alerts, and recent activity. ### Investigate Issues ### Performance Analysis ### Debugging Session ## Dashboard Endpoints When the dashboard server is runn...
/monitorSets up monitoring, alerting, and observability for the app: analyzes stack, generates Prometheus/Grafana/Datadog configs, alerts, health endpoints, structured logs, and OpenTelemetry tracing. Writes to monitoring/ dir.
/monitorLive-monitors CPU, RAM, GPU utilization, memory, and temperatures across cluster hosts. Outputs interactive TUI (default), plain-text (--simple), or JSON (--json) streams.
/monitorMonitors customer account transactions for AML compliance, detects suspicious patterns like structuring and velocity anomalies, generates analysis reports and SAR drafts.
/monitorConfigures monitoring dashboards, metrics collection, and alerting rules for a target using Datadog (default), CloudWatch, Prometheus, or Grafana.
/monitorMonitors instance health: checks connection status, displays QR codes, and manages connect/disconnect for a specific instance or --all.
Access real-time monitoring, metrics, alerts, and debugging features.
/monitor [subcommand] [options]
Open the monitoring dashboard overview.
/monitor dashboard
/monitor dashboard --port 3001
View and manage alerts.
/monitor alerts # List active alerts
/monitor alerts list # List all alerts
/monitor alerts summary # Get alert summary
/monitor alerts acknowledge <id> # Acknowledge an alert
/monitor alerts silence <id> 1h # Silence alert for 1 hour
View system and application metrics.
/monitor metrics # Show all metrics summary
/monitor metrics cpu # Show CPU metrics
/monitor metrics memory # Show memory metrics
/monitor metrics agents # Show agent metrics
/monitor metrics routing # Show message routing metrics
/monitor metrics export # Export Prometheus format
View and search logs.
/monitor logs # Show recent logs
/monitor logs --level error # Filter by level
/monitor logs --source agent # Filter by source
/monitor logs --search "failed" # Search logs
/monitor logs --tail 100 # Show last 100 entries
Enable/disable debug mode with detailed logging.
/monitor debug on # Enable debug mode
/monitor debug off # Disable debug mode
/monitor debug status # Check debug status
/monitor debug session start # Start debug session
/monitor debug session stop # Stop and export session
/monitor debug session export <id> # Export a session
/monitor
Shows overview of system health, active alerts, and recent activity.
/monitor alerts
/monitor logs --level error --since 1h
/monitor metrics agents
/monitor metrics routing
/monitor agents performance
/monitor agents top
/monitor debug on
/monitor debug session start
# ... reproduce issue ...
/monitor debug session stop
/monitor debug off
When the dashboard server is running, access:
http://localhost:3001/ - Dashboard UIhttp://localhost:3001/api/overview - System overviewhttp://localhost:3001/api/alerts - Alerts APIhttp://localhost:3001/api/metrics - Metrics APIhttp://localhost:3001/metrics - Prometheus metricscos_system_cpu_usage - CPU usage percentagecos_system_memory_usage - Memory usage percentagecos_process_uptime_seconds - Process uptimecos_messages_total - Total messages processedcos_message_processing_duration_seconds - Message latencycos_agent_tasks_total - Agent task countscos_agent_task_duration_seconds - Agent task latencycos_workflows_total - Workflow executionscos_errors_total - Error countscos_alerts_total - Alert counts