Usage Trends

Pulls analytics from Agent Monitor's API and gives you trend breakdowns: daily session counts, token volumes, tool usage rankings, model distribution, all across a 365-day window. You ask for "last 30 days" or "tool trends" and get markdown tables with completion rates, cache efficiency ratios, week-over-week deltas. The cache read metric is especially useful if you're trying to see whether prompt caching is actually saving you money over time. It's thorough but assumes you're already running Agent Monitor and care about the operational side of your Claude deployments. If you just want a quick pulse check, the ASCII trend indicators (▲▼→) keep it readable without spinning up a dashboard.

GitHub stars: 455
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add hoangsonww/claude-code-agent-monitor --skill usage-trends --agent claude-code

Installs into .claude/skills of the current project.

Files

Usage Trends

Analyze usage patterns and trends from the Agent Monitor analytics data.

Input

The user provides: $ARGUMENTS

Options: "last 7 days", "last 30 days", "last quarter", "peak hours", "tool trends", "model usage".

Data Sources

Endpoint	Returns
`GET /api/analytics`	Comprehensive analytics object (see schema below)
`GET /api/stats`	`{ total_sessions, active_sessions, active_agents, total_agents, total_events, events_today, ws_connections, agents_by_status, sessions_by_status }`
`GET /api/sessions?limit=200`	Full session records with timestamps and metadata