session-report

Generate HTML reports of Claude Code session token and cache usage.

Updated Jul 8, 2026
One-click install
npx skills add https://github.com/markshd12-cloud/Jarvis --skill session-report-markshd12-cloud
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-report
Source: https://github.com/markshd12-cloud/Jarvis/tree/main/agents/.claude/plugins/marketplaces/claude-plugins-official/plugins/session-report/skills/session-report
Command: npx skills add https://github.com/markshd12-cloud/Jarvis --skill session-report-markshd12-cloud

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill creates a comprehensive HTML report detailing Claude Code session usage, helping users track their session activities.

Core Features & Use Cases

  • Usage Reporting: Summarizes token usage, cache details, and subagent/skill invocations from session transcripts.
  • Timeframe Flexibility: Supports reporting on sessions based on a custom time range (e.g., last 7 days, all-time).
  • Detailed Insights: Identifies cache breaks, most expensive prompts, and project-level analytics.

Quick Start

Use the session-report skill with a time range to generate a report: session-report --since 7d.

Frequently Asked Questions about session-report

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an HTML report for Claude Code session usage analytics?

To generate a Claude Code session usage report, use the session-report command with a specified time range to analyze local session transcripts and output a detailed HTML file in your current working directory.

What analytics are included in a Claude Code session report?

A Claude Code session report includes token consumption metrics, cache statistics, subagent and skill activities, cache breaks, most expensive prompts, and project-level analytics derived from session transcripts.

How do I track token consumption and cache breaks from Claude Code sessions over a custom time range?

You can track token consumption and cache breaks over a custom time range by running the session-report command with a time filter, such as --since 7d, to analyze transcripts from the last seven days.

Does the session reporting tool require external dependencies to analyze AI session transcripts?

No external dependencies are required to analyze AI session transcripts, as the tool operates locally by reading session data directly from the ~/.claude/projects directory without needing additional packages.

Can I identify the most expensive prompts in my Claude Code session history?

Yes, you can identify the most expensive prompts in your Claude Code session history by generating a report, which parses local session transcripts to highlight high token consumption and cache break events.

What is the best way to analyze subagent and skill activities from Claude Code projects?

The best way to analyze subagent and skill activities is to generate a session report, which parses local Claude Code project transcripts to summarize invocation data into a comprehensive HTML file.