Renders a model-router analytics response as a self-contained HTML report: delegation rate, worker usage, tokens avoided, estimated savings and their measurement coverage, latency, governance decisions and data quality. Read-only, and it never recomputes cost.
Plugin router-dashboard from marketplace claude-model-router in mirabeltech/claude-model-router. Commands read from the repo's manifest — 1 month ago.
router-reportRender or explain a model-router delegation report. Use when the user asks what delegation saved, how often tasks were delegated, what the worker cost, why a cost or saving is unavailable, or asks for an analytics report or dashboard over the telemetry store.
Keeps Claude as the primary reasoning agent while shunting bulk file reading to a cheap worker model. A PreToolUse hook gates large reads, the gate fails open so a broken worker degrades to plain Claude Code, and every delegation is measured. Slash commands expose the diagnostic and the report.
2 commands · hooks
Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Token usage tracking, model cost attribution per agent, budget alerts, and optimization recommendations
24 skills · 1 command · 1 agent · hooks
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.