phygital-brain 0.1.1 → 0.1.3

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "phygital-brain",
-  "version": "0.1.1",
+  "version": "0.1.3",
   "description": "A second brain that thinks with you. Builds a folder of notes that works as your knowledge base and as your agent's operating system, through four short forms, then keeps it tidy every day.",
   "author": {
     "name": "Phygital-Brain",

package/README.md

@@ -7,8 +7,9 @@
 <p align="center">
 <a href="#open-source-and-credit"><img src="https://img.shields.io/badge/-open%20source-F05AB8" alt="Open source"></a>
 <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue" alt="License: Apache-2.0"></a>
-<a href="CHANGELOG.md"><img src="https://img.shields.io/badge/version-0.1.1-5AC8FA" alt="Version 0.1.1"></a>
+<a href="https://www.npmjs.com/package/phygital-brain"><img src="https://img.shields.io/npm/v/phygital-brain?color=5AC8FA" alt="npm version"></a>
 <a href="#quick-start"><img src="https://img.shields.io/badge/Claude-plugin-D97757?logo=anthropic&logoColor=white" alt="Claude plugin"></a>
+<a href="docs/install.md"><img src="https://img.shields.io/badge/MCP-connector-F05AB8" alt="MCP connector"></a>
 <a href="CONTRIBUTING.md"><img src="https://img.shields.io/badge/PRs-welcome-5AC8FA" alt="Pull requests welcome"></a>
 </p>
 <p align="center">
@@ -18,11 +19,11 @@
 <a href="#languages"><img src="https://img.shields.io/badge/languages-11%20ready%20%C2%B7%20add%20yours-0B0D12?labelColor=5AC8FA" alt="11 languages ready, add yours"></a>
 <a href="SECURITY.md#what-you-share-with-your-ai"><img src="https://img.shields.io/badge/telemetry-none-0B0D12?labelColor=F05AB8" alt="No telemetry"></a>
 </p>
-<!-- Turn these on when the repository is public (GitHub can't show them for a private repository):
+<p align="center">
 <a href="https://github.com/Phygital-Brain/phygital-brain/stargazers"><img src="https://img.shields.io/github/stars/Phygital-Brain/phygital-brain?style=flat" alt="GitHub stars"></a>
 <a href="https://github.com/Phygital-Brain/phygital-brain/commits/main"><img src="https://img.shields.io/github/last-commit/Phygital-Brain/phygital-brain" alt="Last commit"></a>
-<a href="https://github.com/Phygital-Brain/phygital-brain/releases/latest"><img src="https://img.shields.io/github/v/release/Phygital-Brain/phygital-brain" alt="Latest release"></a>
--->
+<a href="https://www.npmjs.com/package/phygital-brain"><img src="https://img.shields.io/npm/dm/phygital-brain" alt="npm downloads per month"></a>
+</p>
 
 <p align="center">
 <a href="#what-it-is">What it is</a> ·
@@ -238,7 +239,7 @@ Phygital Brain is ready in **11 languages**. Pick yours at the start of the setu
 | Deutsch (German) | Profil, Tagebuch, Projekte |
 | 日本語 (Japanese) | プロフィール, 日記, プロジェクト |
 
-**Your language isn't here?** Any other language still works: your agent translates the forms and messages as it goes, and the folders keep English names. To make a full set for your language, with translated folders, say:
+**Your language isn't here?** Pick Other and type it. Your agent translates the whole brain during the setup, folder names included, without asking you anything. To make a checked set that everyone who speaks your language can use, say:
 
 > Translate Phygital Brain into my language.
 
@@ -270,9 +271,17 @@ Your notes are read by your AI agent and stored in your cloud drive. Phygital Br
 The full list is in [Limits](docs/limits.md).
 
 - **No app.** There's nothing to run. Your AI agent does the work, following the files in this repository.
-- **No lock.** The rules work only because your agent follows them. Keep truly secret things outside the brain folder.
+- **No lock yet.** The rules work only because your agent follows them. Keep truly secret things outside the brain folder. Locked folders are on the [roadmap](#roadmap).
 - **Not always on, unless you move it to the cloud.** On your computer, the Brain Keeper and the morning brief run only while your agent's app is open. As a cloud routine, they run with the computer off.
-- **An early version.** This is version 0.1.1, and the setup hasn't been tested with many people yet.
+- **An early version.** This is version 0.1.3, and the setup hasn't been tested with many people yet.
+
+## Roadmap
+
+Planned, not built yet:
+
+- **Locked folders.** You choose which folders to lock, like `Memory/finances/`. Their notes are encrypted in your drive, so no app or agent can read them without you. You unlock them with your password or fingerprint, from the agent you already use, and only for what you approve.
+
+Ideas are welcome: open an issue on GitHub.
 
 ## Updating and leaving
 
@@ -325,7 +334,7 @@ Phygital Brain is free and open source. You pay for your AI agent and, if you ne
 | [Install](docs/install.md) | One click for Claude desktop, Cursor and VS Code, and steps for Claude Code, Codex, Hermes Agent, OpenClaw and others |
 | [Getting started](docs/getting-started.md) | Every step from nothing to a working brain, with checks and fixes |
 | [Connect your apps](docs/connect-your-apps.md) | Gmail, Calendar, Drive and other services, read only, and running fully online |
-| [Add more skills](docs/add-skills.md) | Adding any skill to your brain, and making videos with HyperFrames and Keyframes |
+| [Add more skills](docs/add-skills.md) | Adding any skill to your brain, making videos with [HyperFrames](https://github.com/heygen-com/hyperframes) and editing images with [PhotoCraft](https://github.com/storytold/photocraft) |
 | [Teams](docs/teams.md) | Sharing one brain through Baalda's cloud |
 | [Bringing in your old notes](docs/importing.md) | Exporting from Notion, Google Docs, Apple Notes and others, and filing it all |
 | [Example brain](docs/example-brain/README.md) | A few made-up notes, so you can see the files before you build yours |
@@ -353,7 +362,7 @@ Phygital Brain is free and open source. You pay for your AI agent and, if you ne
 | `.claude-plugin/` | The plugin files, for installing it in Claude |
 | `mcp/` | The connector (an MCP server, no dependencies) for agents that take MCP servers |
 | `package.json` | The npm package, so `npx -y phygital-brain` runs the connector |
-| `.github/workflows/` | Publishes each new release to npm and attaches the Claude desktop file |
+| `.github/workflows/` | Releases each new version: npm, and the GitHub release with the Claude desktop file |
 
 <p align="center"><img src="docs/images/ownership.png" alt="Your notes. Any AI. It remembers you. Your brain folder in your drive, plain text and yours, sits in the middle, linked to Claude, Codex, Hermes Agent, OpenClaw, Cursor and the next AI you pick. Switch to another AI any time: it reads the same notes, so you never start over. Free and open source." width="100%"></p>
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "phygital-brain",
-  "version": "0.1.1",
+  "version": "0.1.3",
   "description": "A second brain that thinks with you. The Phygital Brain connector: an MCP server that gives your agent the setup, forms, templates and Brain Keeper.",
   "type": "module",
   "bin": {

package/skills/add-language/SKILL.md

@@ -5,7 +5,7 @@ description: Make a full Phygital Brain set in a new language (forms, rule files
 
 # Phygital Brain: Add a language
 
-Version 0.1.1. Everything below is for the agent. Follow it step by step, and check each step before moving on.
+Version 0.1.3. Everything below is for the agent. Follow it step by step, and check each step before moving on.
 
 Two jobs:
 

package/skills/brain-keeper/SKILL.md

@@ -5,7 +5,7 @@ description: Set up, update, pause or run the Brain Keeper, which looks after a
 
 # Phygital Brain: Brain Keeper
 
-Version 0.1.1. Everything below is for the agent. Follow it step by step, and check each step before moving on.
+Version 0.1.3. Everything below is for the agent. Follow it step by step, and check each step before moving on.
 
 The Brain Keeper looks after the brain in two ways:
 
@@ -14,7 +14,7 @@ The Brain Keeper looks after the brain in two ways:
 
 Templates, in this skill's folder: `templates/daily.md`, `templates/check-up.md`, `templates/queue.md`, `templates/root-CLAUDE-section.md`.
 
-**Language:** if the root `CLAUDE.md` has a `## Folder map` and the brain's language has a ready set (`../brain-setup/i18n/{code}/keeper/`, code from the version line), use those templates instead, and the brain's own folder and note names for every path in this file. Otherwise use the English templates and write in the brain's language.
+**Language:** if the root `CLAUDE.md` has a `## Folder map` and the brain's language has a ready set (`../brain-setup/i18n/{code}/keeper/`, code from the version line), use those templates instead, and the brain's own folder and note names for every path in this file. If it has a `## Folder map` but no ready set, translate the English templates as you write them, following `../brain-setup/translating.md`, with the brain's names from the Folder map (choose any missing ones the same way, without asking). With no Folder map, use the English templates and write in the brain's language.
 
 **Called from the brain setup** (`../brain-setup/SKILL.md` 3.8): start at Step 2 with the run time and fix mode the setup gives you, skip Step 1, and skip Step 5 (the setup's finish message covers it).
 

package/skills/brain-keeper/templates/check-up.md

@@ -28,11 +28,14 @@ Search the whole folder and list problems in these groups:
 - **Rule conflicts**: rules in the root `CLAUDE.md` that contradict each other.
 - **Privacy**: passwords, keys or private numbers sitting in ordinary notes (root rules 25 and 26). Report the note, never the value.
 - **Writing**: em dashes and Writing Check patterns in notes.
+- **New version**: compare this brain's version (the first line of the root `CLAUDE.md`) with the newest Phygital Brain. If you can browse the web, the newest is the latest release at https://github.com/Phygital-Brain/phygital-brain/releases/latest. If you can't, use the version of Phygital Brain installed in your agent, if you can see it. If you can't tell, skip this.
 
 ## 2. Report
 
 A short list in plain words, grouped as above. For each problem: the note, what's wrong, the fix you suggest. Put the simple, safe fixes first (em dashes, missing tags, routing table rows).
 
+If a newer version is out, start the report with one line. If your agent already has it: "A new version of Phygital Brain is out. Say 'Upgrade my second brain' to see what's new." If not: "A new version of Phygital Brain is out. Update it in your agent first, then say 'Upgrade my second brain'."
+
 ## 3. Fix only what's approved
 
 Before the first fix, back up every file you'll change (Backups and Undo in the root `CLAUDE.md`).

package/skills/brain-setup/SKILL.md

@@ -5,7 +5,7 @@ description: Build a Phygital Brain second brain in the selected folder through
 
 # Phygital Brain: Setup
 
-Version 0.1.1. Everything below is for the agent. Follow it step by step, and check each step before moving on.
+Version 0.1.3. Everything below is for the agent. Follow it step by step, and check each step before moving on.
 
 ## What you are building
 
@@ -60,7 +60,7 @@ Ask one question with click options, in the language of their first message (Eng
 
 `English` (en) · `中文` (zh-CN) · `हिन्दी` (hi) · `Español` (es) · `العربية` (ar) · `Français` (fr) · `Português (Brasil)` (pt-BR) · `Русский` (ru) · `Bahasa Indonesia` (id) · `Deutsch` (de) · `日本語` (ja) · Other
 
-If the click tool takes only 4 options, offer the 3 most likely from their first message plus Other, and accept any of the names above typed in.
+If the click tool takes only 4 options, offer the 3 most likely from their first message plus Other. A ready language typed in counts the same as a click, whether they type its own name, its English name (German, Japanese) or its code (de, ja).
 
 ### A ready language (a folder `i18n/{code}/` exists in this skill)
 
@@ -74,7 +74,12 @@ The brain is built fully in that language, once, from files that are already tra
 
 ### Any other language
 
-Use the English `forms/` and `templates/`, and translate as you go: before showing a form, translate only the text people see (questions, option labels, placeholders, the header and the buttons). Write every message and note in their language. Folder and note names stay in English, and no Folder map is needed. Say once: "Your brain's folders will have English names. To make a full set for your language, say 'translate Phygital Brain into my language'."
+The brain is still built fully in their language, folder and note names included. You translate it yourself, while you build it, following `translating.md` in this skill's folder: read it now. Don't ask anything about the translation; choose every word yourself.
+
+- **Forms, templates and messages:** use the English `forms/` and `templates/`, and translate each one as `translating.md` says.
+- **Brain Keeper:** pass the English `../brain-keeper/templates/` to the Brain Keeper (3.8), and tell it to translate them the same way, with your names.
+- **Folder map:** add it at the end of the root `CLAUDE.md`, as `translating.md` says.
+- **In the finish message** (Step 4), add one line: "Your agent translated your brain during the setup. To make a checked set that others can use too, say 'translate Phygital Brain into my language'."
 
 ### In every language
 
@@ -314,7 +319,7 @@ When Step 0 found an older Phygital Brain and they picked `Upgrade my brain`.
    - Keep their own routing rows, folders and anything else they wrote that isn't in the templates.
    - Never rewrite notes to new info blocks. Old notes get them the next time they're edited.
    - Replace the version line at the top of the root `CLAUDE.md` with this skill's version: `<!-- Phygital Brain, version X, language: {lang} -->`.
-   - **Folder names.** If the root `CLAUDE.md` has a `## Folder map`, use it for every path in the new templates, and the matching `i18n/{code}/` set if one exists. Add map rows for any new folders or notes in this version (from `i18n/{code}/strings.json`, or ask once what to call them).
+   - **Folder names.** If the root `CLAUDE.md` has a `## Folder map`, use it for every path in the new templates, and the matching `i18n/{code}/` set if one exists. Add map rows for any new folders or notes in this version: from `i18n/{code}/strings.json`, or, with no ready set, choose the names yourself following `translating.md`. With no ready set, translate the new parts the same way.
    - **Brain Keeper.** Update it (follow `../brain-keeper/SKILL.md`, its Step 0.4 keeps `queue.md` and the reports). If it isn't installed, install it from its Step 1.
 6. **Check:** the same number of their own rules as in step 2, word for word; every check in 3.9 that applies; nothing deleted.
 7. **Finish:** one line in today's daily note, then 2 or 3 lines on what changed.

package/skills/brain-setup/i18n/ar/keeper/check-up.md

@@ -28,11 +28,14 @@ tags: [brain-keeper, check-up]
 - **قواعد متعارضة**: قواعد في `CLAUDE.md` الرئيسي يناقض بعضها بعضًا.
 - **الخصوصية**: كلمات مرور أو مفاتيح أو أرقام خاصة في ملاحظات عادية (القاعدتان 25 و26 في الملف الرئيسي). اذكر الملاحظة، ولا تذكر القيمة أبدًا.
 - **الكتابة**: الشرطة الطويلة (em dash) وأنماط مراجعة الكتابة في الملاحظات.
+- **نسخة جديدة**: قارن نسخة هذا العقل (السطر الأول في `CLAUDE.md` الرئيسي) بأحدث نسخة من Phygital Brain. إن كنت تستطيع تصفح الويب، فأحدث نسخة هي آخر إصدار على https://github.com/Phygital-Brain/phygital-brain/releases/latest. وإن لم تستطع، فاستخدم نسخة Phygital Brain المثبتة في مساعدك، إن كنت تراها. وإن لم تعرف، فتجاوز هذه النقطة.
 
 ## 2. التقرير
 
 قائمة قصيرة بكلمات بسيطة، مقسمة كما في الأعلى. لكل مشكلة: الملاحظة، وما الخطأ، والإصلاح الذي تقترحه. ضع الإصلاحات البسيطة والآمنة أولًا (الشرطة الطويلة، الوسوم الناقصة، صفوف جداول التوجيه).
 
+إن صدرت نسخة أحدث، فابدأ التقرير بسطر واحد. إن كانت عند مساعدك بالفعل: "صدرت نسخة جديدة من Phygital Brain. قل 'حدّث عقلي الثاني' ('Upgrade my second brain') لترى ما الجديد." وإن لم تكن: "صدرت نسخة جديدة من Phygital Brain. حدّثها أولًا في مساعدك، ثم قل 'حدّث عقلي الثاني'."
+
 ## 3. أصلح فقط ما تمت الموافقة عليه
 
 قبل أول إصلاح، خذ نسخة احتياطية من كل ملف ستغيّره (النسخ الاحتياطية والتراجع في `CLAUDE.md` الرئيسي).

package/skills/brain-setup/i18n/ar/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # العقل الثاني لـ{Name}
 

package/skills/brain-setup/i18n/de/keeper/check-up.md

@@ -28,11 +28,14 @@ Durchsuch den ganzen Ordner und liste Probleme in diesen Gruppen auf:
 - **Widersprüchliche Regeln**: Regeln in der Haupt-`CLAUDE.md`, die sich gegenseitig widersprechen.
 - **Datenschutz**: Passwörter, Schlüssel oder private Nummern in normalen Notizen (Hauptregeln 25 und 26). Nenn die Notiz, nie den Wert.
 - **Schreiben**: Gedankenstriche und Muster aus dem Schreibcheck in Notizen.
+- **Neue Version**: Vergleiche die Version dieses Gehirns (die erste Zeile der Haupt-`CLAUDE.md`) mit der neuesten Version von Phygital Brain. Wenn du im Web suchen kannst, ist die neueste die letzte Veröffentlichung auf https://github.com/Phygital-Brain/phygital-brain/releases/latest. Wenn nicht, nimm die Version von Phygital Brain, die in deinem Agenten installiert ist, falls du sie siehst. Wenn du es nicht herausfinden kannst, lass diesen Punkt aus.
 
 ## 2. Bericht
 
 Eine kurze Liste in einfachen Worten, gruppiert wie oben. Für jedes Problem: die Notiz, was nicht stimmt, die Korrektur, die du vorschlägst. Die einfachen, sicheren Korrekturen kommen zuerst (Gedankenstriche, fehlende Tags, Zeilen in Tabellen "Wo was hinkommt").
 
+Wenn es eine neuere Version gibt, beginne den Bericht mit einer Zeile. Wenn dein Agent sie schon hat: "Es gibt eine neue Version von Phygital Brain. Sag 'aktualisiere mein zweites Gehirn' ('Upgrade my second brain'), um zu sehen, was neu ist." Wenn nicht: "Es gibt eine neue Version von Phygital Brain. Aktualisiere sie zuerst in deinem Agenten, dann sag 'aktualisiere mein zweites Gehirn'."
+
 ## 3. Nur korrigieren, was freigegeben ist
 
 Mach vor der ersten Korrektur eine Sicherung von jeder Datei, die du änderst ("Sicherungen und Rückgängig" in der Haupt-`CLAUDE.md`).

package/skills/brain-setup/i18n/de/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # Das zweite Gehirn von {Name}
 

package/skills/brain-setup/i18n/es/keeper/check-up.md

@@ -28,11 +28,14 @@ Busca en toda la carpeta y haz una lista de problemas en estos grupos:
 - **Reglas que chocan**: reglas del `CLAUDE.md` principal que se contradicen entre sí.
 - **Privacidad**: contraseñas, claves o números privados metidos en notas normales (reglas principales 25 y 26). Di en qué nota están, nunca el dato.
 - **Escritura**: rayas largas y patrones del Control de Escritura en las notas.
+- **Versión nueva**: compara la versión de este cerebro (la primera línea del `CLAUDE.md` principal) con la versión más nueva de Phygital Brain. Si puedes navegar por la web, la más nueva es la última versión publicada en https://github.com/Phygital-Brain/phygital-brain/releases/latest. Si no puedes, usa la versión de Phygital Brain instalada en tu agente, si la puedes ver. Si no hay forma de saberlo, sáltate esto.
 
 ## 2. Informe
 
 Una lista corta con palabras sencillas, agrupada como arriba. Para cada problema: la nota, qué falla y el arreglo que sugieres. Pon primero los arreglos sencillos y seguros (rayas largas, etiquetas que faltan, filas de las tablas de rutas).
 
+Si hay una versión más nueva, empieza el informe con una línea. Si tu agente ya la tiene: "Hay una versión nueva de Phygital Brain. Di 'actualiza mi segundo cerebro' ('Upgrade my second brain') para ver qué hay de nuevo." Si no: "Hay una versión nueva de Phygital Brain. Primero actualízala en tu agente y luego di 'actualiza mi segundo cerebro'."
+
 ## 3. Arregla solo lo aprobado
 
 Antes del primer arreglo, haz una copia de seguridad de cada archivo que vayas a cambiar (Copias de seguridad y deshacer, en el `CLAUDE.md` principal).

package/skills/brain-setup/i18n/es/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # El segundo cerebro de {Name}
 

package/skills/brain-setup/i18n/fr/keeper/check-up.md

@@ -28,11 +28,14 @@ Parcourez tout le dossier et listez les problèmes dans ces groupes :
 - **Règles contradictoires** : des règles du `CLAUDE.md` racine qui se contredisent.
 - **Confidentialité** : des mots de passe, des clés ou des numéros privés dans des notes ordinaires (règles 25 et 26 du fichier racine). Indiquez la note, jamais la valeur.
 - **Écriture** : des tirets longs et des tics du Contrôle d'écriture dans les notes.
+- **Nouvelle version** : comparez la version de ce cerveau (la première ligne du `CLAUDE.md` racine) avec la version la plus récente de Phygital Brain. Si vous pouvez naviguer sur le web, la plus récente est la dernière version publiée sur https://github.com/Phygital-Brain/phygital-brain/releases/latest. Sinon, utilisez la version de Phygital Brain installée dans votre agent, si vous la voyez. Si vous ne pouvez pas savoir, passez ce point.
 
 ## 2. Faire le rapport
 
 Une liste courte, avec des mots simples, groupée comme ci-dessus. Pour chaque problème : la note, ce qui ne va pas, la correction que vous proposez. Mettez d'abord les corrections simples et sans risque (tirets longs, tags manquants, lignes des tableaux de rangement).
 
+S'il y a une version plus récente, commencez le rapport par une ligne. Si votre agent l'a déjà : « Une nouvelle version de Phygital Brain est sortie. Dites "mets à jour mon second cerveau" ("Upgrade my second brain") pour voir ce qui change. » Sinon : « Une nouvelle version de Phygital Brain est sortie. Mettez-la d'abord à jour dans votre agent, puis dites "mets à jour mon second cerveau". »
+
 ## 3. Corriger seulement ce qui est validé
 
 Avant la première correction, sauvegardez chaque fichier que vous allez modifier (« Sauvegardes et annulation » dans le `CLAUDE.md` racine).

package/skills/brain-setup/i18n/fr/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # Le second cerveau de {Name}
 

package/skills/brain-setup/i18n/hi/keeper/check-up.md

@@ -28,11 +28,14 @@ tags: [brain-keeper, check-up]
 - **नियमों का टकराव**: मुख्य `CLAUDE.md` के ऐसे नियम जो एक-दूसरे के उलट हैं।
 - **निजता**: आम नोट्स में पड़े पासवर्ड, की या निजी नंबर (मुख्य नियम 25 और 26)। नोट बताएँ, उसकी वैल्यू कभी नहीं।
 - **लिखावट**: नोट्स में em dash और राइटिंग चेक वाले पैटर्न।
+- **नया वर्शन**: इस ब्रेन का वर्शन (मुख्य `CLAUDE.md` की पहली लाइन) Phygital Brain के सबसे नए वर्शन से मिलाएँ। अगर आप वेब देख सकते हैं, तो सबसे नया वर्शन https://github.com/Phygital-Brain/phygital-brain/releases/latest पर आखिरी रिलीज़ है। अगर नहीं, तो अपने एजेंट में इंस्टॉल Phygital Brain का वर्शन लें, अगर वह दिखे। अगर पता न चल सके, तो इसे छोड़ दें।
 
 ## 2. रिपोर्ट
 
 आसान शब्दों में एक छोटी लिस्ट, ऊपर वाले समूहों के हिसाब से। हर समस्या के लिए: नोट, क्या गलत है, आपका सुझाया सुधार। आसान और सुरक्षित सुधार पहले रखें (em dash, छूटे टैग, "कहाँ क्या जाए" टेबल की लाइनें)।
 
+अगर नया वर्शन आया है, तो रिपोर्ट एक लाइन से शुरू करें। अगर आपके एजेंट में वह पहले से है: "Phygital Brain का नया वर्शन आ गया है। क्या नया है, यह देखने के लिए कहें 'मेरा सेकंड ब्रेन अपग्रेड करो' ('Upgrade my second brain')।" अगर नहीं: "Phygital Brain का नया वर्शन आ गया है। पहले इसे अपने एजेंट में अपडेट करें, फिर कहें 'मेरा सेकंड ब्रेन अपग्रेड करो'।"
+
 ## 3. सिर्फ़ वही ठीक करें जिसकी मंज़ूरी मिली
 
 पहला सुधार करने से पहले, हर उस फ़ाइल का बैकअप लें जिसे आप बदलेंगे (मुख्य `CLAUDE.md` में "बैकअप और वापस लेना")।

package/skills/brain-setup/i18n/hi/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # {Name} का सेकंड ब्रेन
 

package/skills/brain-setup/i18n/id/keeper/check-up.md

@@ -28,11 +28,14 @@ Telusuri seluruh folder dan daftar masalahnya dalam kelompok berikut:
 - **Aturan yang bertabrakan**: aturan di `CLAUDE.md` utama yang saling bertentangan.
 - **Privasi**: kata sandi, kunci, atau nomor pribadi yang ada di catatan biasa (aturan utama 25 dan 26). Laporkan catatannya, jangan pernah nilainya.
 - **Tulisan**: em dash dan pola Cek Tulisan di dalam catatan.
+- **Versi baru**: bandingkan versi otak ini (baris pertama `CLAUDE.md` utama) dengan versi Phygital Brain terbaru. Kalau kamu bisa membuka web, versi terbaru adalah rilis terakhir di https://github.com/Phygital-Brain/phygital-brain/releases/latest. Kalau tidak bisa, pakai versi Phygital Brain yang terpasang di agenmu, kalau terlihat. Kalau tidak bisa dipastikan, lewati bagian ini.
 
 ## 2. Laporan
 
 Daftar singkat dengan kata-kata sederhana, dikelompokkan seperti di atas. Untuk setiap masalah: catatannya, apa yang salah, dan perbaikan yang kamu sarankan. Taruh perbaikan yang sederhana dan aman di paling atas (em dash, tag yang kurang, baris tabel rute).
 
+Kalau ada versi yang lebih baru, mulai laporan dengan satu baris. Kalau agenmu sudah punya versi itu: "Ada versi baru Phygital Brain. Bilang 'perbarui otak keduaku' ('Upgrade my second brain') untuk melihat apa yang baru." Kalau belum: "Ada versi baru Phygital Brain. Perbarui dulu di agenmu, lalu bilang 'perbarui otak keduaku'."
+
 ## 3. Perbaiki hanya yang disetujui
 
 Sebelum perbaikan pertama, cadangkan setiap file yang akan diubah (Cadangan dan Pembatalan di `CLAUDE.md` utama).

package/skills/brain-setup/i18n/id/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # Otak Kedua {Name}
 

package/skills/brain-setup/i18n/ja/keeper/check-up.md

@@ -28,11 +28,14 @@ tags: [brain-keeper, check-up]
 - **ルールの矛盾**：ルートの `CLAUDE.md` の中で、たがいに矛盾するルール。
 - **プライバシー**：普通のノートに書かれたパスワード、キー、非公開の番号（ルートのルール25と26）。報告するのはノートの名前だけで、値は絶対に書きません。
 - **文章**：ノートの中の長いダッシュと、文章チェックのパターン。
+- **新しいバージョン**：このブレインのバージョン（ルートの `CLAUDE.md` の1行目）と、Phygital Brain の最新バージョンを比べます。Web を見られるなら、最新は https://github.com/Phygital-Brain/phygital-brain/releases/latest にある最新リリースです。見られないなら、あなたのエージェントに入っている Phygital Brain のバージョンを使います（見える場合）。わからないときは、この項目は飛ばします。
 
 ## 2. 報告する
 
 上のグループごとに、わかりやすい言葉で短く一覧にします。問題ごとに：ノート、何がおかしいか、提案する修正。簡単で安全な修正（長いダッシュ、足りないタグ、振り分けの表の行）を先に並べます。
 
+新しいバージョンが出ていたら、報告の最初に1行入れます。エージェントにもう入っている場合：「Phygital Brain の新しいバージョンが出ています。「セカンドブレインをアップグレードして」（"Upgrade my second brain"）と言うと、新しい内容を確認できます。」まだの場合：「Phygital Brain の新しいバージョンが出ています。先にエージェントで更新してから、「セカンドブレインをアップグレードして」と言ってください。」
+
 ## 3. 承認されたものだけ直す
 
 最初の修正の前に、変更するファイルをすべてバックアップします（ルートの `CLAUDE.md` の「バックアップと元に戻す」）。

package/skills/brain-setup/i18n/ja/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # {Name}さんのセカンドブレイン
 

package/skills/brain-setup/i18n/pt-BR/keeper/check-up.md

@@ -28,11 +28,14 @@ Procure na pasta inteira e liste os problemas nestes grupos:
 - **Regras em conflito**: regras do `CLAUDE.md` da raiz que se contradizem.
 - **Privacidade**: senhas, chaves ou números privados em notas comuns (regras 25 e 26 da raiz). Diga qual é a nota, nunca o valor.
 - **Escrita**: travessões longos e padrões da Revisão de Texto nas notas.
+- **Versão nova**: compare a versão deste cérebro (a primeira linha do `CLAUDE.md` da raiz) com a versão mais nova do Phygital Brain. Se você puder navegar na web, a mais nova é a última versão publicada em https://github.com/Phygital-Brain/phygital-brain/releases/latest. Se não puder, use a versão do Phygital Brain instalada no seu agente, se der para ver. Se não der para saber, pule esta parte.
 
 ## 2. Relatório
 
 Uma lista curta em palavras simples, agrupada como acima. Para cada problema: a nota, o que está errado, a correção que você sugere. Coloque primeiro as correções simples e seguras (travessões, tags faltando, linhas das tabelas de onde guardar).
 
+Se tiver uma versão mais nova, comece o relatório com uma linha. Se o seu agente já tem essa versão: "Saiu uma versão nova do Phygital Brain. Diga 'atualize meu segundo cérebro' ('Upgrade my second brain') para ver o que mudou." Se não tem: "Saiu uma versão nova do Phygital Brain. Atualize primeiro no seu agente, depois diga 'atualize meu segundo cérebro'."
+
 ## 3. Corrija só o que for aprovado
 
 Antes da primeira correção, faça backup de cada arquivo que vai mudar (Backup e desfazer no `CLAUDE.md` da raiz).

package/skills/brain-setup/i18n/pt-BR/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # Segundo Cérebro de {Name}
 

package/skills/brain-setup/i18n/ru/keeper/check-up.md

@@ -28,11 +28,14 @@ tags: [brain-keeper, check-up]
 - **Конфликты правил**: правила в корневом `CLAUDE.md`, которые противоречат друг другу.
 - **Приватность**: пароли, ключи или личные номера в обычных заметках (корневые правила 25 и 26). Называй заметку, но никогда не значение.
 - **Тексты**: длинные тире и шаблоны из «Проверки текста» в заметках.
+- **Новая версия**: сравни версию этого мозга (первая строка корневого `CLAUDE.md`) с самой новой версией Phygital Brain. Если ты можешь заходить в интернет, самая новая версия: последний выпуск на https://github.com/Phygital-Brain/phygital-brain/releases/latest. Если нет, возьми версию Phygital Brain, установленную в агенте, если ты её видишь. Если узнать не получается, пропусти этот пункт.
 
 ## 2. Отчет
 
 Короткий список простыми словами, по тем же группам. Для каждой проблемы: заметка, что не так, какое исправление ты предлагаешь. Простые и безопасные исправления ставь первыми (длинные тире, недостающие теги, строки в таблицах «Куда что класть»).
 
+Если вышла более новая версия, начни отчет с одной строки. Если в агенте она уже есть: «Вышла новая версия Phygital Brain. Скажите "обнови мой второй мозг" ("Upgrade my second brain"), чтобы увидеть, что нового». Если нет: «Вышла новая версия Phygital Brain. Сначала обновите ее в своем агенте, потом скажите "обнови мой второй мозг"».
+
 ## 3. Исправляй только одобренное
 
 Перед первым исправлением сделай резервную копию каждого файла, который будешь менять («Резервные копии и отмена» в корневом `CLAUDE.md`).

package/skills/brain-setup/i18n/ru/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # Второй мозг: {Name}
 

package/skills/brain-setup/i18n/zh-CN/keeper/check-up.md

@@ -28,11 +28,14 @@ tags: [brain-keeper, check-up]
 - **规则冲突**：根目录 `CLAUDE.md` 里互相矛盾的规则。
 - **隐私**：普通笔记里出现了密码、密钥或私密号码（总规则第 25 和 26 条）。只报告是哪篇笔记，绝不报告具体内容。
 - **写作**：笔记里的破折号，以及“写作检查”列出的写法。
+- **新版本**：把这个大脑的版本（根目录 `CLAUDE.md` 的第一行）和 Phygital Brain 的最新版本比一比。如果你能上网，最新版本就是 https://github.com/Phygital-Brain/phygital-brain/releases/latest 上的最新发布。如果不能上网，就看你的 AI 助手里装的 Phygital Brain 版本，前提是你看得到。如果没法知道，就跳过这一项。
 
 ## 2. 报告
 
 用大白话写一个简短的清单，按上面的分组。每个问题写：哪篇笔记、哪里不对、你建议怎么改。简单、安全的修复放在最前面（破折号、缺少的标签、归类表里的行）。
 
+如果有更新的版本，报告的第一行先写一句。如果 AI 助手里已经是新版本：“Phygital Brain 出了新版本。说「升级我的第二大脑」（“Upgrade my second brain”）就能看到有什么新内容。”如果还不是：“Phygital Brain 出了新版本。先在你的 AI 助手里更新它，然后说「升级我的第二大脑」。”
+
 ## 3. 只改同意过的
 
 第一次修改之前，先备份每个要改的文件（见根目录 `CLAUDE.md` 里的“备份和撤销”）。

package/skills/brain-setup/i18n/zh-CN/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # {Name} 的第二大脑
 

package/skills/brain-setup/templates/root-CLAUDE.md

@@ -6,7 +6,7 @@
 - Rule 12: write their style choice from form 1 into it (for example, "By default: detailed explanations" if they picked `Detailed`).
 -->
 
-<!-- Phygital Brain, version 0.1.1, language: {lang} -->
+<!-- Phygital Brain, version 0.1.3, language: {lang} -->
 
 # {Name}'s Second Brain
 

package/skills/brain-setup/translating.md

@@ -0,0 +1,62 @@
+# Translating during the setup
+
+For a language with no ready set in `i18n/`. You translate the whole brain yourself, once, while you build it. Don't ask the person anything about the translation: choose every word yourself, following these rules. The brain then reads only its own files, already in their language.
+
+## 1. Choose the names first
+
+Before the first form, choose a name in their language for every English name in the list at the end of this file. Write the list down for yourself and use exactly the same spelling in every file you write, so every path and `[[link]]` matches.
+
+- Short, everyday words a person would use for that folder. Not a dictionary translation if people say it differently.
+- Safe as file names on Mac, Windows and phones: no `/ \ : * ? " < > |`, no spaces at the start or end. Letters with accents and non-Latin scripts are fine. Use the NFC form (composed letters).
+- The 7 top folders start with a capital letter where the language has capitals. Subfolders and note names are lowercase where the language has case, with hyphens between words.
+- One name per idea: `research` is the same word in Projects and in Memory.
+- Two names keep their marks: `_Leads` keeps the `_` at the start, and `PAUSED` stays in capitals where the language has them.
+- Every name is different from the others in the same folder.
+
+Choose the feature names too, the same way: Brain Keeper, morning brief, meeting prep, thinking tools, check-up, Writing Check and second brain. Phygital Brain stays in English.
+
+## 2. What you translate
+
+- **Forms:** before you show each form, the text people see: questions, option labels, placeholders, the header and the buttons.
+- **Messages:** everything you say during the setup.
+- **Files:** every file you write from `templates/`, and the Brain Keeper's files from `../brain-keeper/templates/`, as you write them. Swap every English brain path for your names: `About/me.md`, `Skills/brain-keeper/daily.md`, `[[goals]]`, `` `Projects` ``.
+
+## 3. What stays English
+
+- The file names `CLAUDE.md`, `README.md` and `.claudeignore`, and the `.backups/` and `Skills/no-ai-slop/` folders, and everything inside `no-ai-slop/`.
+- Placeholders in curly braces until you fill them in: `{Name}`, `{Time zone}`, `{name}`, `{title}` and the rest.
+- Info blocks (the lines between `---`): keys and values (`type: daily`, `status: active`, `day: Monday`, every tag). Only the `description:` sentence is translated.
+- YAML and other code examples, and every `data-name` and `data-value` in the forms.
+- Names the person gives (their projects, people, companies), exactly as they wrote them.
+
+## 4. Trigger phrases
+
+Sentences a person says to their agent, in quotes, like "check up my brain" or "prep me for {name}". Write what a person would naturally say in their language, then keep the English one after it, so both work: `"{in their language}", "check up my brain", or the same in {Language}`.
+
+## 5. Writing
+
+- Natural, everyday speech. Adapt, don't translate word for word. If a native speaker wouldn't say a sentence that way, rewrite it.
+- About an 8th-grade reading level. Plain and clear, never childish.
+- One register all through: what popular consumer apps in that language use, often the informal "you".
+- "your agent", never a product name, in anything a person sees.
+- No long dashes (the em dash). Use periods, commas, colons or parentheses.
+- Keep every fact, rule, number and step. Don't add or remove rules.
+
+## 6. Folder map
+
+At the end of the root `CLAUDE.md`, add a `## Folder map` section, the same as a ready language gets: a two-column table, English name and the brain's name, for every name in the list below, with one line above it: "For Phygital Brain upgrades and skills only. Daily work uses the names in this brain." Write that line and the heading in their language. This is the only place the English names appear in the brain.
+
+## 7. Check
+
+Before the setup's own checks (3.9):
+
+- No English name from the list is left in a path or `[[link]]`, outside the Folder map and the things that stay English.
+- Every `[[link]]` and path points to a name in your list, spelled the same.
+- Every folder you named in a `CLAUDE.md` exists.
+
+## The names
+
+These are every folder and note name a new brain can have.
+
+- **Top folders:** `About`, `Daily`, `Projects`, `Relationships`, `Memory`, `Library`, `Skills`
+- **Subfolders and notes:** `Clients`, `Collaborators`, `Team`, `Partners`, `decisions`, `research`, `finances`, `archive`, `applications`, `competitors`, `notes`, `briefs`, `drafts`, `ideas`, `feedback`, `assets`, `prompts`, `templates`, `frameworks`, `brain-keeper`, `morning-brief`, `meeting-prep`, `thinking`, `import`, `connected-apps`, `reports`, `me`, `goals`, `business`, `services`, `customers`, `pain-points`, `brand`, `tools`, `cv`, `biography`, `tasks`, `_Leads`, `daily`, `check-up`, `queue`, `PAUSED`