session-report

Analyze Claude Code transcripts to generate an explorable HTML usage report.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/cjrfoto/claude-config --skill session-report-cjrfoto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-report
Source: https://github.com/cjrfoto/claude-config/tree/main/plugins/marketplaces/claude-plugins-official/plugins/session-report/skills/session-report
Command: npx skills add https://github.com/cjrfoto/claude-config --skill session-report-cjrfoto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill generates a self-contained HTML report that surfaces Claude Code session usage from transcripts, enabling quick insight into token flows, cache behavior, subagent activity, and skill invocations.

Core Features & Use Cases

  • Aggregates per-session and per-project token totals, wall-clock and active time, and cache-break events to identify inefficiencies.
  • Produces an explorable HTML report using the bundled template, including top prompts, by-day timeline, and per-skill attribution.
  • Use cases include auditing usage patterns, identifying expensive prompts, and sharing actionable usage dashboards with teammates.

Quick Start

Run the bundled analyzer to generate the usage JSON and copy the template.html to the output path, then edit and save the resulting HTML report.

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 of Claude Code session usage?

You can analyze Claude Code transcripts to summarize usage by computing token totals, wall-clock time, active time, and cache-break events across sessions, projects, subagents, and skills to identify inefficiencies.

How do I audit Claude Code token usage by project and subagent?

The analyzer aggregates session transcripts to compute per-project and per-subagent token totals, wall-clock time, active time, and cache-break events, returning a structured JSON payload with by-project and by-subagent views.

Can I track per-skill attribution and daily timelines for Claude Code prompts?

Yes, analyzing Claude Code transcripts computes per-skill attribution and optional daily-by-day timelines, returning a structured JSON payload containing top prompts and daily summaries alongside by-skill views.

What data do I need to create an explorable usage dashboard for Claude Code?

You need Claude Code session transcripts as input data, which the analyzer script processes to compute token totals, wall-clock time, and cache-break events, producing a structured JSON payload and an explorable HTML report.

Does the session analytics report require any external dependencies?

No external dependencies are required, as the bundled scripts and template analyze Claude Code transcripts to compute usage stats and produce a self-contained explorable HTML report with by-project, by-subagent, and by-skill views.

How do I identify expensive prompts and cache break events in Claude Code sessions?

Analyzing Claude Code transcripts surfaces cache-break events and extracts top prompts, producing a structured JSON payload that identifies expensive prompts within an explorable HTML report for auditing usage patterns.