Claude Code plugin for Scalene — the AI coding scorecard.
claude plugin install https://github.com/scaleneai/mcp
Then set your credentials (from your dashboard → Connect):
export SCALENE_API_URL=https://getscalene.com/u/<your-token>
export SCALENE_TOKEN=<your-bearer-token>
That's it. Every session auto-syncs when it ends.
The plugin registers a SessionEnd hook that fires once when you close a Claude Code session. It runs a Python script locally that reads the session's JSONL file and POSTs metadata to your Scalene dashboard.
Want your past sessions too?
curl -sL https://raw.githubusercontent.com/scaleneai/mcp/main/sync_script.py | python3 - --api-url 'https://getscalene.com/u/<your-token>' --token '<your-bearer-token>'
The sync script runs entirely on your machine. Only metadata crosses the network:
| Exported | Never exported |
|---|---|
| Session ID, timestamps | Prompt text |
| Token counts (input/output/cache) | Response text |
Model ID (e.g. claude-opus-4-6) | File contents |
Tool name (e.g. Edit, Bash) | Tool inputs or outputs |
| Stop reason, content block types | Thinking blocks |
| Git branch, project path | Any conversation content |
The privacy whitelist is enforced on your machine, not the server. The script is ~300 lines of stdlib Python with zero dependencies. Audit it:
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI Engineering Intelligence
npx claudepluginhub scaleneai/mcpTracks Claude Code session usage (tokens, costs, skills, MCP, subagents) and sends data to a self-hosted dashboard.
Real-time session dashboard for Claude Code — cost tracking, analytics, and smart alerts
Meta-Cognition tool for Claude Code: session history analysis, workflow optimization, and 21 MCP tools for deep session insights.
OTel + Hooks analytics for Claude Code. Run /init-claudalytics to configure telemetry and hooks capture for this project.
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.