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.

GitHub stars: 455
last updated: Jun 11, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Weekly Report

Generate a comprehensive weekly productivity report from Agent Monitor data.

Input

The user provides: $ARGUMENTS

This may be:

"this week" or empty (default: current week Mon-Sun)
"last week" for the previous week
A date range: "2025-04-07 to 2025-04-13"

Procedure

Fetch weekly data from http://localhost:4820:
- GET /api/sessions?limit=200 — filter to target week (default sort: most recently updated first)
- GET /api/analytics — aggregated analytics
- GET /api/pricing/cost — cost data
Build the weekly report:

📊 Week at a Glance

Metric This Week Last Week Change
Sessions N N ↑/↓ N%
Total Hours N N ↑/↓ N%
Tokens Used N N ↑/↓ N%
Total Cost $X.XX $X.XX ↑/↓ N%
Completion Rate N% N% ↑/↓

🏆 Highlights
- Most productive day (by sessions completed)
- Longest session and what it accomplished
- Most used tools and any new tools adopted
- Notable achievements (complex tasks completed, errors resolved)