skills.rest
cline
clineOFFICIAL
Explore all skills by this author →
WebsiteGitHub

session-report

Analyze Claude Code JSONL transcripts to generate interactive HTML usage reports.

19|3|Updated May 17, 2026
Search Tags:#claude code#cost optimization#token usage#usage analytics#session reporting#cache analysis#subagent tracking
One-click install
npx skills add https://github.com/cline/skills --skill session-report-cline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: session-report
Source: https://github.com/cline/skills/tree/main/skills/session-report
Command: npx skills add https://github.com/cline/skills --skill session-report-cline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually parsing Claude Code session transcripts to extract token usage, cache performance, subagent activity, and skill invocation data is tedious and error-prone. This Skill automates that analysis to deliver clear, actionable insights into your Claude Code usage patterns.

Core Features & Use Cases

  • Automated Usage Aggregation: Scans ~/.claude/projects JSONL transcripts to calculate total token consumption, cache hit rates, subagent call volumes, and skill usage across all sessions and projects.
  • Interactive HTML Reporting: Generates a self-contained, explorable HTML report with visualizations including session timelines, token breakdowns by project, top expensive prompts, and cache break details with drill-down context.
  • Use Case: Use this Skill to identify anomalous usage patterns (e.g., a single project consuming 40% of your weekly tokens), optimize cache performance, and reduce unnecessary token spend from overzealous subagent spawning.

Quick Start

Use the session-report skill to generate an interactive HTML usage report for your last 7 days of Claude Code sessions.

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 from session transcripts?▼

Claude Code session reporting automates analysis of JSONL transcript files from ~/.claude/projects to aggregate token consumption, cache performance, and subagent activity. It processes session data to generate an interactive HTML report with visualizations for usage trends and cost optimization insights.

Can I track subagent activity and cache hit rates in Claude Code sessions?▼

Yes, tracking subagent activity and cache hit rates is possible by processing Claude Code session transcripts. The analyzer scans JSONL files to calculate subagent call volumes and cache performance metrics across projects, helping identify anomalous usage patterns and reduce unnecessary token spend.

Does generating a Claude Code usage report require any specific dependencies?▼

Generating a Claude Code usage report requires only Node.js to execute the bundled analyzer script. It processes JSONL transcript files from the ~/.claude/projects directory without requiring additional external dependencies or complex environment setups.

What is the best way to identify anomalous token consumption across Claude Code projects?▼

The best way to identify anomalous token consumption is to generate an interactive HTML report that visualizes token breakdowns by project and highlights top expensive prompts. This allows you to quickly spot anomalies, such as a single project consuming a disproportionate percentage of weekly tokens.

How do I generate an interactive HTML report for my last 7 days of Claude Code sessions?▼

You generate an interactive HTML report for your last 7 days of Claude Code sessions by running the bundled analyzer script with Node.js. The script scans JSONL transcripts within a configurable time range to produce a self-contained file with usage visualizations and cost optimization insights.

Related Skills

Explore More Software Engineering Skills→
openclawopenclaw
1.0k

session-viewer

Convert JSONL session transcripts from Codex, Claude Code, OpenClaw, or Pi into interactive HTML files.

Official
Intermediate
ice-droid-99ice-droid-99

querying-mlflow-metrics

Fetch aggregated MLflow trace metrics for token usage, latency, and quality scores.

Community
Intermediate
markshd12-cloudmarkshd12-cloud

session-report

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

Community
Intermediate
vladolaruvladolaru
6

analyzing-cc-sessions

Parse JSONL transcripts to extract metrics and diagnose subagent behavior.

Community
Advanced