Verified:Website 𝕏@julianobarbosa GitHub

session-report

Generate an explorable HTML report of Claude Code session usage from local transcript data.

Updated Aug 23, 2026

Search Tags:#cost optimization #token usage #session analysis #cache efficiency #HTML reporting #Claude Code transcripts

Ready to run

npx skills add https://github.com/julianobarbosa/.claude --skill session-report-julianobarbosa

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: session-report
Source: https://github.com/julianobarbosa/.claude/tree/main/plugins/marketplaces/claude-plugins-official/plugins/session-report/skills/session-report
Command: npx skills add https://github.com/julianobarbosa/.claude --skill session-report-julianobarbosa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill converts messy Claude Code transcript history into a readable report that highlights token spend, cache behavior, subagents, and expensive prompts.

Core Features & Use Cases

Generates an explorable HTML report summarizing session usage metrics (tokens, cache reads/creates, outputs) across recent or all-time windows.
Surfaces cost drivers with drilling lists for “most expensive prompts” and token spend attributed by skill/slash command.
Detects performance anomalies by flagging cache breaks above a configurable uncached-token threshold and grouping results by project and subagent type.

Quick Start

Ask for a session report covering the last 7 days and save the resulting HTML file in your current working directory.

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 and token spend?▼

To generate an HTML report of Claude Code session usage, the tool analyzes local transcript data and embeds computed metrics into an explorable HTML template. It summarizes token spend, cache behavior, and subagent activity over a specified time window or all-time.

What is the best way to analyze Claude Code transcript history for expensive prompts?▼

The best way to analyze Claude Code transcript history for expensive prompts is to parse local transcripts and surface cost drivers. This process generates drilling lists for the most expensive prompts and attributes token spend by skill or slash command.

Can I detect cache efficiency anomalies in my Claude Code sessions?▼

Yes, you can detect cache efficiency anomalies in Claude Code sessions by analyzing local transcript data. The process flags cache breaks above a configurable uncached-token threshold and groups results by project and subagent type to highlight performance issues.

Does the session analysis report require external dependencies to process transcripts?▼

No, the session analysis report requires no external dependencies to process transcripts. It runs a bundled analyzer directly on local Claude Code transcript data to produce JSON output, which is then embedded into an HTML template to populate findings and optimizations.