session-report

Analyzes Claude Code transcripts to produce structured JSON summaries and HTML reports of usage metrics.

Updated May 1, 2026
One-click install
npx skills add https://github.com/oguzhanguvenkaya/oguzhan_claude_code_configurations --skill session-report-oguzhanguvenkaya
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-report
Source: https://github.com/oguzhanguvenkaya/oguzhan_claude_code_configurations/tree/main/plugins/marketplaces/claude-plugins-official/plugins/session-report/skills/session-report
Command: npx skills add https://github.com/oguzhanguvenkaya/oguzhan_claude_code_configurations --skill session-report-oguzhanguvenkaya

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyzes Claude Code session transcripts to produce a self-contained explorable HTML report that reveals token usage, caching behavior, subagent activity, and costlier prompts across projects and sessions.

Core Features & Use Cases

  • Generates an HTML report from transcripts stored under ~/.claude/projects, including per-project and per-subagent breakdowns.
  • Deduplicates resumed sessions, aggregates in-flight metrics, and uses a bundled analyzer (analyze-sessions.mjs) plus a templated HTML template to render results.
  • Supports time-range filtering (e.g., 7d, 24h, all) and provides insights into anomalies, cache behavior, and high-cost prompts for optimization.

Quick Start

Run the bundled analyzer to produce a JSON summary and render an explorable HTML report by applying the template.

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 session transcripts for token usage and cache activity?

You can analyze Claude Code session transcripts for token usage and cache activity by running a bundled analyzer that processes transcripts stored under ~/.claude/projects and aggregates metrics into a structured summary.

Can I generate an explorable HTML report of my Claude Code sessions?

Yes, you can generate an explorable HTML report of Claude Code sessions by applying a templated HTML generator to the aggregated session data, which renders token usage, subagent behavior, and prompt costs into a self-contained document.

How do I filter Claude Code transcript analysis by time range?

Filtering Claude Code transcript analysis by time range is supported through range-filtering options like 7d, 24h, or all, allowing you to narrow the scope of token usage and subagent behavior metrics to specific periods.

Does the session report show per-project and per-subagent breakdowns?

Yes, the session report provides end-to-end data aggregation across overall, per-project, per-subagent, and per-skill views, delivering detailed breakdowns of token usage and caching behavior for each scope.

How do I identify high-cost prompts in my Claude Code transcripts?

To identify high-cost prompts in Claude Code transcripts, the analyzer surfaces costlier prompts and anomalies across projects and sessions, helping you optimize caching behavior and overall token consumption.

Are resumed sessions deduplicated when analyzing Claude Code transcripts?

Yes, resumed sessions are deduplicated and in-flight metrics are aggregated when analyzing Claude Code transcripts, ensuring accurate token usage and cache activity reporting without duplicated session data.