sentrux

Sentrux — AI skill for Claude Code

AI community

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality.

How to install Sentrux

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

What Sentrux does

Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.

Alternatives in AI

  • Manifest — Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage 4.1k ★
  • Paul — Plan-Apply-Unify Loop — Structured AI-assisted development for Claude Code 1.2k ★
  • Agentrq — AgentRQ: Human-in-loop realtime conversational task manager for AI Agents 1.1k ★

README

sentrux

**The sensor that helps AI agents close the feedback loop.
Recursive self-improvement of code quality.**

[![CI](https://github.com/sentrux/sentrux/actions/workflows/ci.yml/badge.svg)](https://github.com/sentrux/sentrux/actions/workflows/ci.yml) [![Release](https://img.shields.io/github/v/release/sentrux/sentrux)](https://github.com/sentrux/sentrux/releases) [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)

**English** | [中文](README.zh-CN.md) | [Deutsch](README.de.md) | [日本語](README.ja.md)

[How it Works](#how-it-works) · [Quick Start](#quick-start) · [MCP Integration](#mcp-server) · [Rules Engine](#rules-engine) · [Releases](https://github.com/sentrux/sentrux/releases)


![sentrux demo](assets/demo.gif)

Live: Claude Code Opus 4.6 builds a FastAPI project. Even with good prompts, quality lands at 6772.
Not because the agent can't do better — but because without a sensor, it doesn't know what to improve.
Quality Signal

How it works

How sentrux works: scan → score → agent improves → rescan → better score → repeat

Quick Start

**Install** (macOS · Linux · Windows)

**macOS**

brew install sentrux/tap/sentrux

**Linux**

curl -fsSL https://raw.githubusercontent.com/sentrux/sentrux/main/install.sh | sh

**Windows** — download from [Releases](https://github.com/sentrux/sentrux/releases), or:

curl -L -o sentrux.exe https://github.com/sentrux/sentrux/releases/latest

Related Skills

Skill Evolution — AI skill for Claude Code

Skill Evolution

Self-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement pro

AI community
Review Video — AI skill for Claude Code

Review Video

Review a rendered video with AI vision. Uses TwelveLabs to watch the output, analyze pacing/composition/audio

AI community
Code Auditor MCP — AI skill for Claude Code

Code Auditor MCP

Architectural invariants and code quality analysis, enforced inside your AI agent's edit loop. MCP server + CL

AI community
Improve Lint — AI skill for Claude Code

Improve Lint

Run the AI-augmented lint self-improvement loop on the current project. Scans .lint-history/ for recurring vio

AI community
Quality Babysit — AI skill for Claude Code

Quality Babysit

AI Quality Ratchet babysitting loop — read quality-report.md, fix one regression at a time, push, repeat. PR-1

AI community
SoloDawn — AI skill for Claude Code

SoloDawn

Catches and repairs AI hallucinations before delivery: three quality gates, 31 built-in rules, a self-healing

AI community

Related Agents

Self Audit Orchestrator — Security agent for Claude Code

Self Audit Orchestrator

Use this agent at the start of a new 14-day cycle (Day 1), during the cycle to execute the 2-hour sprint, and

Security community
Claude Code Flow — Testing & QA agent for Claude Code

Claude Code Flow

by ruvnet - This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and op

Testing & QA community
Fd Feedback Loops — Development agent for Claude Code

Fd Feedback Loops

fd-feedback-loops — Self-Improvement Domain Reviewer

Development community