By l1nusb
Track and analyze Claude Code skill usage - invocation counts, duration, token consumption
Claude Code plugin that automatically tracks skill usage and provides analytics.
/plugin marketplace add L1nusB/skill-tracker
/plugin install skill-tracker@skill-tracker
After installation, tracking happens automatically via hooks. Use the /skill-stats command to view analytics:
/skill-stats # Global stats
/skill-stats --project /path/to/repo # Per-project stats
/skill-stats --session abc123 # Per-session stats
/skill-stats --since 2026-03-01 # Since date
/skill-stats --format json # JSON output
All data is stored in ~/.claude/skill-tracker/logs/:
skill-usage.jsonl — detailed recent entriesskill-summary.json — compacted historical aggregatesLogs are automatically compacted on session end:
skill-summary.jsonBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub l1nusb/skill-tracker --plugin skill-trackerTracks Claude Code session usage (tokens, costs, skills, MCP, subagents) and sends data to a self-hosted dashboard.
OTel + Hooks analytics for Claude Code. Run /init-claudalytics to configure telemetry and hooks capture for this project.
Track and analyze skill usage by AI agents, and clean up redundant or overlapping skills.
Core skills: ecosystem guide, skill creator, research patterns, session reflection, and plugin development. Includes UserPromptSubmit hook for forced skill evaluation.
Skill synchronization and management for Claude Code, Codex, GitHub Copilot, and Cursor. Provides 27 MCP tools for validation, sync, intelligence, and tracing.
Generate an explorable HTML report of Claude Code session usage — tokens, cache efficiency, subagents, skills, and the most expensive prompts — from local ~/.claude/projects transcripts.