X-ray every source of auto-injected context Claude Code loads at session start — MCP servers, CLAUDE.md files, skills, subagents, and slash commands — and report estimated tokens per source. Use this skill when the user runs /claude-papercuts:token-x-ray, asks where their context tokens went, says Claude feels slow or expensive, mentions /context showing surprising numbers, or wants to know what to disable. Runs the audit.py script in this skill's directory and presents the result verbatim.
$npx -y skills add dhruba-datta/claude-papercuts --skill token-x-rayInstalls into the current project.
Run `npx skills use "https://github.com/dhruba-datta/claude-papercuts" --skill "dhruba-datta/claude-papercuts/token-x-ray"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/dhruba-datta/claude-papercuts" that are relevant to the current task. Run `npx skills add "https://github.com/dhruba-datta/claude-papercuts"` and select the relevant skills, then follow their instructions.