docs: fix stale .sh references and version badge in all 7 READMEs (#7)

Two leftover artifacts that the v1.1.0 rewrite PR missed because the
translation subagents were scoped to Requirements / Install / Platform
/ Plugin Layout / Testing / Inspired By — they did not touch other
sections.

1. "How It Works" section (line ~87 in every README) still mentioned
   `hooks/stop-hook.sh`. That file was deleted in the v1.1.0 rewrite —
   the current hook is `hooks/stop-hook.js`.

2. The "version" shield badge (line 7) has been hardcoded to
   `version-1.0.0-green.svg` since the initial release. Every
   subsequent release (v1.0.1, v1.0.2, v1.0.3, v1.1.0) left it
   stale. Bump to 1.1.0 and leave a TODO for next time.

Fixed across all 7 READMEs (English + zh/ja/ko/es/vi/pt) with a single
sed pass — the edit is identical in every file.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: JonyanDunh

README.es.md

@@ -4,7 +4,7 @@
 
 [![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-1.0.0-green.svg)](./.claude-plugin/plugin.json)
+[![Version](https://img.shields.io/badge/version-1.1.0-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)
 
@@ -84,7 +84,7 @@ Tú ejecutas el comando **una sola vez** y Claude Code se encarga del resto:
 #    (o se alcanza --max-iterations)
 ```
 
-El bucle ocurre **dentro de tu sesión actual** — sin `while true` externo, sin proceso orquestador. El `Stop hook` en `hooks/stop-hook.sh` bloquea la salida normal de la sesión y vuelve a inyectar el prompt como un nuevo turno de usuario usando el protocolo nativo de Claude Code: `{"decision": "block", "reason": ...}`.
+El bucle ocurre **dentro de tu sesión actual** — sin `while true` externo, sin proceso orquestador. El `Stop hook` en `hooks/stop-hook.js` bloquea la salida normal de la sesión y vuelve a inyectar el prompt como un nuevo turno de usuario usando el protocolo nativo de Claude Code: `{"decision": "block", "reason": ...}`.
 
 Esto crea un **bucle de retroalimentación autorreferente** donde:
 - El prompt no cambia entre iteraciones

README.ja.md

@@ -4,7 +4,7 @@
 
 [![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-1.0.0-green.svg)](./.claude-plugin/plugin.json)
+[![Version](https://img.shields.io/badge/version-1.1.0-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)
 
@@ -84,7 +84,7 @@ _`Watchdog` は `Claude Code` のプラグインです。同一セッション
 #    (or --max-iterations is reached)
 ```
 
-ループは**現在のセッションの内部**で起こります。外部の `while true` もオーケストレーター的なプロセスも不要です。`hooks/stop-hook.sh` の Stop hook が通常のセッション終了をブロックし、Claude Code ネイティブの `{"decision": "block", "reason": ...}` プロトコルを使って prompt を新しいユーザーターンとして再注入します。
+ループは**現在のセッションの内部**で起こります。外部の `while true` もオーケストレーター的なプロセスも不要です。`hooks/stop-hook.js` の Stop hook が通常のセッション終了をブロックし、Claude Code ネイティブの `{"decision": "block", "reason": ...}` プロトコルを使って prompt を新しいユーザーターンとして再注入します。
 
 これによって作られるのは**自己参照的なフィードバックループ**です。
 

README.ko.md

@@ -4,7 +4,7 @@
 
 [![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-1.0.0-green.svg)](./.claude-plugin/plugin.json)
+[![Version](https://img.shields.io/badge/version-1.1.0-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)
 
@@ -84,7 +84,7 @@ _`Claude Code` 플러그인입니다. 하나의 세션 안에서 현재 agent를
 #    (또는 --max-iterations에 도달할 때까지)
 ```
 
-이 루프는 **현재 세션 내부에서** 돌아갑니다. 외부 `while true`도, 오케스트레이터 프로세스도 없습니다. `hooks/stop-hook.sh`의 `Stop hook`이 일반적인 세션 종료를 막고, `Claude Code`의 네이티브 `{"decision": "block", "reason": ...}` 프로토콜을 이용해 prompt를 새로운 user turn으로 다시 주입합니다.
+이 루프는 **현재 세션 내부에서** 돌아갑니다. 외부 `while true`도, 오케스트레이터 프로세스도 없습니다. `hooks/stop-hook.js`의 `Stop hook`이 일반적인 세션 종료를 막고, `Claude Code`의 네이티브 `{"decision": "block", "reason": ...}` 프로토콜을 이용해 prompt를 새로운 user turn으로 다시 주입합니다.
 
 이를 통해 **자기 참조 피드백 루프**가 만들어집니다.
 

README.md

@@ -4,7 +4,7 @@ English | [中文](./README.zh.md) | [한국어](./README.ko.md) | [日本語](.
 
 [![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-1.0.0-green.svg)](./.claude-plugin/plugin.json)
+[![Version](https://img.shields.io/badge/version-1.1.0-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)
 
@@ -84,7 +84,7 @@ You run the command **once**, then Claude Code handles the rest:
 #    (or --max-iterations is reached)
 ```
 
-The loop happens **inside your current session** — no external `while true`, no orchestrator process. The Stop hook in `hooks/stop-hook.sh` blocks normal session exit and re-injects the prompt as a new user turn using Claude Code's native `{"decision": "block", "reason": ...}` protocol.
+The loop happens **inside your current session** — no external `while true`, no orchestrator process. The Stop hook in `hooks/stop-hook.js` blocks normal session exit and re-injects the prompt as a new user turn using Claude Code's native `{"decision": "block", "reason": ...}` protocol.
 
 This creates a **self-referential feedback loop** where:
 - The prompt never changes between iterations

README.pt.md

@@ -4,7 +4,7 @@
 
 [![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-1.0.0-green.svg)](./.claude-plugin/plugin.json)
+[![Version](https://img.shields.io/badge/version-1.1.0-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)
 
@@ -84,7 +84,7 @@ Você roda o comando **uma vez** e o `Claude Code` cuida do resto:
 #    (ou até bater em --max-iterations)
 ```
 
-O loop acontece **dentro da sua sessão atual** — nada de `while true` externo, nada de processo orquestrador. O Stop hook em `hooks/stop-hook.sh` bloqueia a saída normal da sessão e reinjeta o prompt como um novo turno de usuário usando o protocolo nativo do `Claude Code`: `{"decision": "block", "reason": ...}`.
+O loop acontece **dentro da sua sessão atual** — nada de `while true` externo, nada de processo orquestrador. O Stop hook em `hooks/stop-hook.js` bloqueia a saída normal da sessão e reinjeta o prompt como um novo turno de usuário usando o protocolo nativo do `Claude Code`: `{"decision": "block", "reason": ...}`.
 
 Isso monta um **loop de feedback auto-referencial** onde:
 - O prompt nunca muda entre iterações

README.vi.md

@@ -4,7 +4,7 @@
 
 [![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-1.0.0-green.svg)](./.claude-plugin/plugin.json)
+[![Version](https://img.shields.io/badge/version-1.1.0-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)
 
@@ -84,7 +84,7 @@ Bạn chỉ chạy lệnh **một lần**, phần còn lại Claude Code lo:
 #    (hoặc khi chạm --max-iterations)
 ```
 
-Vòng lặp diễn ra **ngay trong session hiện tại** — không có `while true` bên ngoài, không có tiến trình orchestrator nào cả. Stop hook trong `hooks/stop-hook.sh` chặn cú thoát session bình thường và nhét lại prompt dưới dạng một user turn mới bằng giao thức gốc của Claude Code: `{"decision": "block", "reason": ...}`.
+Vòng lặp diễn ra **ngay trong session hiện tại** — không có `while true` bên ngoài, không có tiến trình orchestrator nào cả. Stop hook trong `hooks/stop-hook.js` chặn cú thoát session bình thường và nhét lại prompt dưới dạng một user turn mới bằng giao thức gốc của Claude Code: `{"decision": "block", "reason": ...}`.
 
 Cái này tạo ra một **vòng lặp phản hồi tự tham chiếu**, trong đó:
 - Prompt không bao giờ đổi giữa các iteration

README.zh.md

@@ -4,7 +4,7 @@
 
 [![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-1.0.0-green.svg)](./.claude-plugin/plugin.json)
+[![Version](https://img.shields.io/badge/version-1.1.0-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)
 
@@ -84,7 +84,7 @@ _一个 Claude Code 插件：把 agent 按在同一个会话里反复干同一
 #    （或者达到 --max-iterations 上限）
 ```
 
-这里的"循环"不是外部的——没有 `while true`、没有 orchestrator 进程。`hooks/stop-hook.sh` 里的 Stop hook 会阻止 Claude Code 的会话退出，并通过 Claude Code 原生的 `{"decision": "block", "reason": ...}` 协议把原始 prompt 作为新的 user turn 再注入回去。
+这里的"循环"不是外部的——没有 `while true`、没有 orchestrator 进程。`hooks/stop-hook.js` 里的 Stop hook 会阻止 Claude Code 的会话退出，并通过 Claude Code 原生的 `{"decision": "block", "reason": ...}` 协议把原始 prompt 作为新的 user turn 再注入回去。
 
 说白了就是一个**循环自己喂自己**的结构：
 - 每轮喂的 prompt 都是同一个