Weekly Report

If you're running Agent Monitor locally and want to understand where your AI budget is actually going, this compiles everything into a readable weekly digest. It hits the analytics API to pull session counts, token volumes, per-session costs, and tool usage, then structures it into week-over-week comparisons with daily breakdowns and actionable recommendations. The output is table-heavy with emoji section headers, which makes it easy to scan during standups or retrospectives. Most useful if you're tracking multiple agents or workflows and need to spot cost spikes, error patterns, or workflow inefficiencies before they become problems. It defaults to the current week but accepts "last week" or custom date ranges.

Install to Claude Code

npx -y skills add hoangsonww/claude-code-agent-monitor --skill weekly-report --agent claude-code