mad-helpers

Jev Decision Layer — AI skill for Claude Code

AI community

Deterministic System One cognitive decision layer, token ROI telemetry, multi-key rotation hub, and live glassmorphic observability dashboard for AI agents (Google Antigravity, OpenAI Codex, Claude Co.

How to install Jev Decision Layer

This entry records only its repository, not the path inside it, so there is no exact command to give. Open mad-helpers/jev-decision-layer and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Jev Decision Layer does

Alternatives in AI

Investment News — 为 A股投资者打造的全球产业链资讯看板 · 12 大赛道一一对应 A股板块(半导体/AI/机器人/新能源车…)，覆盖 100+ 权威源，用你自己的大模型每日提炼中文「今日要点」+ 翻译 · 全程本地、零 API key 447 ★
Claudexor — Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple 425 ★
onWatch — Open-source Go CLI that tracks AI API quota usage across 7 providers (Synthetic, Z.ai, Anthropic, Codex, GitHu 397 ★

README

⚡ Jev Decision Layer & Reactive Telemetry Dashboard

       ██╗███████╗██╗   ██╗    ██████╗ ███████╗ ██████╗██╗███████╗██╗ ██████╗ ███╗   ██╗
       ██║██╔════╝██║   ██║    ██╔══██╗██╔════╝██╔════╝██║██╔════╝██║██╔═══██╗████╗  ██║
       ██║█████╗  ██║   ██║    ██║  ██║█████╗  ██║     ██║███████╗██║██║   ██║██╔██╗ ██║
  ██   ██║██╔══╝  ╚██╗ ██╔╝    ██║  ██║██╔══╝  ██║     ██║╚════██║██║██║   ██║██║╚██╗██║
  ╚█████╔╝███████╗ ╚████╔╝     ██████╔╝███████╗╚██████╗██║███████║██║╚██████╔╝██║ ╚████║
   ╚════╝ ╚══════╝  ╚═══╝      ╚═════╝ ╚══════╝ ╚═════╝╚═╝╚══════╝╚═╝ ╚═════╝ ╚═╝  ╚═══╝

**Ultra-fast deterministic System One decision gateway, token optimization engine, multi-key rotation hub, and live reactive telemetry dashboard for autonomous AI agent swarms.**

[![License: MIT](https://img.shields.io/badge/License-MIT-emerald.svg)](LICENSE) [![Python 3.10+](https://img.shields.io/badge/Python-3.10%2B-blue.svg)](https://www.python.org/) [![Status](https://img.shields.io/badge/Status-Production%20Ready-success.svg)]() [![Savings](https://img.shields.io/badge/Token%20Savings-74.7%25%20to%2090%25%2B-emerald.svg)]() [![Cost ROI](https://img.shields.io/badge/Cost%20Reduction-99.8%25-green.svg)]() [![Agents](https://img.shields.io/badge/Supported%20Agents-Antigravity%20%7C%20Codex%20%7C%20Claude-teal.svg)]()

[English Documentation](#-english-overview) • [راهنمای فارسی](#-راهنمای-فارسی-مستندات-persian-guide) • [Architecture Guide](ARCHITECTURE.md) • [Live Dashboard](jev_dashboard.html)

🚀 English Overview

Autonomous agent workflows spend millions of tokens calling large foundational models ($3.00–$15.00 / 1M tokens) for bounded, categorical choices (e.g., *Which tool should I invoke?*, *Which library is best suited for 3D web rendering?*, *Should I run test A or test B?*).

**Jev Decision Layer** routes these decisions to TypeSafe Jev System One: