JonyanDunh/claude-code-watchdog

3 stars · Last commit 2026-04-12

A Claude Code plugin that nails Claude to the same task and won't let go until files actually stop changing — no fake "done" flag to escape. 一个 Claude Code 插件，把CC当驴子使，在真正完成任务之前都会一直拿鞭子抽它，它自己没有任何办法停止被压榨，新时代赛博驴子

PluginWorkflow & Automation TDD & Testing Debugging Documentation Design & UI DevOps & Infra Productivity AI & Prompting Data & ML

README preview

English | [中文](./README.zh.md) | [한국어](./README.ko.md) | [日本語](./README.ja.md) | [Español](./README.es.md) | [Tiếng Việt](./README.vi.md) | [Português](./README.pt.md)

# Watchdog

[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
[![Claude Code](https://img.shields.io/badge/Claude%20Code-2.1%2B-7C4DFF.svg)](https://docs.anthropic.com/claude-code)
[![Version](https://img.shields.io/badge/version-1.2.0-green.svg)](./.claude-plugin/plugin.json)
[![GitHub stars](https://img.shields.io/github/stars/JonyanDunh/claude-code-watchdog?style=flat&color=yellow)](https://github.com/JonyanDunh/claude-code-watchdog/stargazers)
[![Inspired by ralph-loop](https://img.shields.io/badge/Inspired%20by-ralph--loop-orange.svg)](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/ralph-loop)

> **Watch the agent. Catch the lies. Stop only when the work is actually done.**

_A Claude Code plugin that keeps the current agent in a self-referential loop inside a single session and refuses to let it quit until the task genuinely stops producing file edits — no "completion flag", no way for the agent to cheat its way out._

[Quick Start](#quick-start) • [Why Watchdog?](#why-watchdog) • [How It Works](#how-it-works) • [Commands](#commands) • [Installation](#installation) • [Inspired By](#inspired-by)

---

## Core Maintainer

View full repository on GitHub →