Skip to content

Claude Code Session Report

Builds an HTML report of your Claude Code token usage, cache, subagents and costly prompts

Stars
45,770
Licence
Apache-2.0
Files
3 files

What it does

Once installed, the agent can read your local Claude Code session logs (stored under ~/.claude/projects) and summarise how many tokens you used over a chosen period, broken down by project, subagent type, skill, cache misses and expensive prompts. It then fills a bundled HTML template with that data and saves a self-contained, explorable report file in your current folder, plus a few plain-English findings and optimisation tips.

Great for

  • Developers who use Claude Code heavily and want to see where their tokens go
  • Teams trying to cut down on subagent or cache-related costs
  • Anyone who wants a weekly summary of their Claude Code usage

Skip it if

  • People who do not use Claude Code, since there are no transcripts to analyse
  • Users sharing their machine or reports publicly: the report contains prompt excerpts and project names from your private session history

Try asking

  • “Generate a session report for the last 7 days”
  • “Make a Claude Code usage report for the last 30 days and highlight expensive prompts”
  • “Show me which projects used the most tokens all time in an HTML report”
  • “Create a 24h session usage report with cache hit analysis”
Step-by-step guide: how to use Claude Code Session ReportInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the Apache-2.0 licence and an attribution note.

    session-report.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip session-report.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip session-report.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Start with the default 7-day window to keep the report focused and quick to generate
  • Review the saved HTML and the embedded prompt excerpts before sharing it with anyone
  • Check the saved file path reported by the agent rather than assuming a location

What's inside

  • analyze-sessions.mjs
  • SKILL.md
  • template.html

Redistributed unmodified from anthropics/claude-plugins-official under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.