session-report

Analyze Claude Code session transcripts to calculate token usage and generate HTML reports.

Updated Nov 3, 2016
One-click install
npx skills add https://github.com/xleliberty/mydotfiles --skill session-report-xleliberty
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-report
Source: https://github.com/xleliberty/mydotfiles/tree/main/.config/.claude/plugins/marketplaces/claude-plugins-official/plugins/session-report/skills/session-report
Command: npx skills add https://github.com/xleliberty/mydotfiles --skill session-report-xleliberty

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, and includes scripts (resource) components.

What problem does it solve?

This skill addresses the lack of visibility into AI development workflows by providing a clear, explorable HTML report of token usage, subagent activity, and expensive prompts across your Claude Code projects.

Core Features & Use Cases

  • Usage Analytics: Track token consumption, cache efficiency, and subagent overhead to identify cost-heavy patterns.
  • Performance Insights: Pinpoint specific prompts or skills that trigger excessive API calls or cache breaks.
  • Workflow Optimization: Use the generated HTML report to drill down into session history and refine your interaction patterns for better efficiency.

Quick Start

Run the session-report skill to generate an HTML analysis of your Claude Code activity from the last seven days.

Frequently Asked Questions about session-report

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

FAQPage Schema
How do I analyze Claude Code token usage and subagent activity from session transcripts?

You can analyze Claude Code token usage by processing JSONL session transcripts to calculate subagent activity, cache efficiency, and cost metrics. This generates an explorable HTML report highlighting expensive prompts and performance bottlenecks.

Can I visualize cache efficiency metrics to identify expensive prompts in my AI development workflow?

Yes, visualizing cache efficiency metrics allows you to pinpoint specific prompts that trigger excessive API calls or cache breaks. The generated HTML report lets you drill down into session history to identify and refine cost-heavy interaction patterns.

Does generating a session report require Node.js to process JSONL log files?

Yes, generating this session report requires Node.js to execute the scripts that parse your JSONL log files. The scripts aggregate the transcript data to produce the final HTML analysis of your recent project activity.

What is the best way to track project-specific costs and API call bottlenecks across Claude Code sessions?

The best way to track project-specific costs is to run an automated data aggregation process over your JSONL logs. This calculates token consumption and subagent overhead, outputting an HTML report for workflow optimization.

Why should I monitor token consumption and subagent overhead in my Claude Code projects?

Monitoring token consumption and subagent overhead identifies performance bottlenecks and expensive patterns in your AI workflows. It provides transparent development monitoring, helping you refine interactions to reduce overall API costs.

Are there limitations when trying to drill down into specific prompts using automated data aggregation from JSONL logs?

The automated data aggregation processes JSONL log files from the last seven days to generate actionable insights. If your log files are corrupted, deleted, or older than seven days, the report cannot analyze those session transcripts.