cc-viewer 1.6.278 → 1.6.279

package/concepts/ar/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## ما الذي يفعله حقلا الإدخال
 
 - **اسم الخبير**: التسمية المعروضة على زر الدور في صف خيارات UltraPlan (بحد أقصى 30 حرفًا). إنه مجرد اسم عرض ولا يُرسل **أبدًا** إلى Claude Code.
-- **نص الموجّه (Prompt body)**: تعليمات الدور الخاصة بك. عند الإرسال، يقوم cc-viewer **تلقائيًا** بتغليفه بوسوم `<system-reminder>...</system-reminder>` مع ترويسة نطاق `[SCOPED INSTRUCTION]`. لذا **اكتب النص فقط** — لا تضف وسوم `<system-reminder>` بنفسك.
+- **نص الموجّه (Prompt body)**: تعليمات الدور الخاصة بك. عند إنشاء خبير جديد، يأتي المحرر **مُعبّأً مسبقًا** بغلاف `<system-reminder>...</system-reminder>` وترويسة النطاق `[SCOPED INSTRUCTION]` الخاصة به — **اكتب تعليمات الدور داخل الغلاف**. لن يقوم cc-viewer بالتغليف مرتين: إن كان الغلاف موجودًا يُرسل كما هو؛ وإن أزلته، يضيف cc-viewer واحدًا عند الإرسال.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## التحليل قسمًا بقسم
 
-### 1. ترويسة نطاق `[SCOPED INSTRUCTION]` (الغلاف — يُولَّد تلقائيًا)
+### 1. ترويسة نطاق `[SCOPED INSTRUCTION]` (الغلاف — مُعبّأ مسبقًا لك)
 > The following instructions are intended for the next 1–3 interactions...
 
 يُخبر هذا Claude Code: **هذه التعليمات نشطة فقط للأدوار الـ 1–3 التالية**، ثم تتلاشى. يمنع تسرب «شخصية الخبير» إلى محادثات لاحقة غير ذات صلة.
 
-**يتم توليد هذا السطر بواسطة cc-viewer تلقائيًا. لست بحاجة لكتابته.**
+**يأتي هذا السطر مُعبّأً مسبقًا في المحرر — اتركه كما هو؛ لست بحاجة لإعادة كتابته.**
 
 ### 2. تعريف المهمة الافتتاحي (**هذا ما يجب عليك إعادة كتابته**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Your final plan must include the following elements:
 
 ## نصائح التأليف (TL;DR)
 
-1. **احتفظ بالغلاف**: سطر `<system-reminder>` + `[SCOPED INSTRUCTION]` يُضاف بواسطة cc-viewer — لا تكرره.
-2. **أعد كتابة الجملة الافتتاحية**: اذكر الدور والهدف وصيغة المخرجات في سطر واحد.
-3. **مرّن سير العمل**: 1–2 خطوة للمهام الخفيفة، الحلقة الكاملة المكونة من 5 خطوات للمعقدة فقط.
-4. **أعد كتابة الأدوار الفرعية للخطوة 1**: الافتراضات (الأوراق الأكاديمية / المنافسون / demo) ربما ليست ما تريد.
-5. **«قائمة فحص المخرجات» النهائية هي معيار الجودة لديك**: حدد بنية المخرجات — سيتبعها Claude Code بصرامة.
+1. **أعد كتابة الجملة الافتتاحية**: اذكر الدور والهدف وصيغة المخرجات في سطر واحد.
+2. **مرّن سير العمل**: 1–2 خطوة للمهام الخفيفة، الحلقة الكاملة المكونة من 5 خطوات للمعقدة فقط.
+3. **أعد كتابة الأدوار الفرعية للخطوة 1**: الافتراضات (الأوراق الأكاديمية / المنافسون / demo) ربما ليست ما تريد.
+4. **«قائمة فحص المخرجات» النهائية هي معيار الجودة لديك**: حدد بنية المخرجات — سيتبعها Claude Code بصرامة.
 
 ---
 
 ## مثال معاد هيكلته: Competitive Analyst
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 مقارنة بـ Research Expert الأصلي: تم اختصاره إلى 4 خطوات، خُفِّضت الأدوار الفرعية من 6 إلى 3، وأُعيدت كتابة قائمة المخرجات بالكامل كـ «أقسام تقرير».

package/concepts/da/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## Hvad gør de to inputfelter
 
 - **Ekspertnavn**: etiketten der vises på rolleknappen i UltraPlan-variantrækken (max 30 tegn). Det er kun et visningsnavn og sendes **aldrig** til Claude Code.
-- **Promptindhold**: din rolleinstruktion. Ved afsendelse pakker cc-viewer det **automatisk** ind i `<system-reminder>...</system-reminder>`-tags med en `[SCOPED INSTRUCTION]`-scope-header. Så **skriv kun selve indholdet** — tilføj ikke `<system-reminder>`-tags selv.
+- **Promptindhold**: din rolleinstruktion. Når du opretter en ny ekspert, **kommer editoren forudfyldt** med `<system-reminder>...</system-reminder>`-wrapperen og dens `[SCOPED INSTRUCTION]`-scope-header — **skriv din rolleinstruktion inde i wrapperen**. cc-viewer pakker ikke dobbelt: hvis wrapperen er til stede, sendes den som den er; hvis du fjerner den, tilføjer cc-viewer en igen ved afsendelse.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## Sektion-for-sektion gennemgang
 
-### 1. `[SCOPED INSTRUCTION]`-scope-header (wrapper — auto-genereret)
+### 1. `[SCOPED INSTRUCTION]`-scope-header (wrapper — forudfyldt for dig)
 > The following instructions are intended for the next 1–3 interactions...
 
 Dette fortæller Claude Code: **disse instruktioner er kun aktive de næste 1–3 turneringer**, derefter aftager de. Forhindrer "ekspertpersonaen" i at lække ind i ikke-relaterede samtaler bagefter.
 
-**Denne linje genereres af cc-viewer automatisk. Du behøver ikke skrive den.**
+**Denne linje kommer forudfyldt i editoren — behold den som den er; du behøver ikke at omskrive den.**
 
 ### 2. Indledende opgavedefinition (**dette er det, du skal omskrive**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Den oprindelige skabelon lister 6 elementer i en "implementeringsplan". Din leve
 
 ## Forfattertips (TL;DR)
 
-1. **Behold wrapperen**: `<system-reminder>` + `[SCOPED INSTRUCTION]`-linjen tilføjes af cc-viewer — gentag ikke.
-2. **Omskriv åbningssætningen**: angiv rolle, mål og outputformat på én linje.
-3. **Flex workflowet**: 1–2 trin for lette opgaver, det fulde 5-trin loop kun for komplekse.
-4. **Omskriv Trin 1's underroller**: standardrollerne (akademiske artikler / konkurrenter / demo) er sandsynligvis ikke det, du vil have.
-5. **Den endelige "leverance-tjekliste" er din kvalitetsbarrer**: stav outputstrukturen ud — Claude Code følger den strikt.
+1. **Omskriv åbningssætningen**: angiv rolle, mål og outputformat på én linje.
+2. **Flex workflowet**: 1–2 trin for lette opgaver, det fulde 5-trin loop kun for komplekse.
+3. **Omskriv Trin 1's underroller**: standardrollerne (akademiske artikler / konkurrenter / demo) er sandsynligvis ikke det, du vil have.
+4. **Den endelige "leverance-tjekliste" er din kvalitetsbarrer**: stav outputstrukturen ud — Claude Code følger den strikt.
 
 ---
 
 ## Et omarbejdet eksempel: Competitive Analyst
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 Sammenlignet med den originale Research Expert: trimmet til 4 trin, underroller reduceret fra 6 til 3, leveranceliste fuldt omskrevet som "rapportsektioner".

package/concepts/de/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## Was die beiden Eingabefelder tun
 
 - **Expertenname**: das Label, das auf der Rollenschaltfläche in der UltraPlan-Variantenzeile angezeigt wird (max. 30 Zeichen). Es ist nur ein Anzeigename und wird **niemals** an Claude Code gesendet.
-- **Prompt-Inhalt**: Ihre Rollenanweisung. Beim Senden umschließt cc-viewer ihn **automatisch** mit `<system-reminder>...</system-reminder>`-Tags und einem `[SCOPED INSTRUCTION]`-Scope-Header. Schreiben Sie also **nur den Inhalt** — fügen Sie keine `<system-reminder>`-Tags selbst hinzu.
+- **Prompt-Inhalt**: Ihre Rollenanweisung. Beim Anlegen eines neuen Experten **ist der Editor vorausgefüllt** mit dem `<system-reminder>...</system-reminder>`-Wrapper und seinem `[SCOPED INSTRUCTION]`-Scope-Header — **schreiben Sie Ihre Rollenanweisung innerhalb des Wrappers**. cc-viewer umschließt nicht doppelt: Ist der Wrapper vorhanden, wird er unverändert gesendet; entfernen Sie ihn, fügt cc-viewer beim Senden wieder einen hinzu.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## Aufschlüsselung Abschnitt für Abschnitt
 
-### 1. `[SCOPED INSTRUCTION]`-Scope-Header (Wrapper — automatisch generiert)
+### 1. `[SCOPED INSTRUCTION]`-Scope-Header (Wrapper — für Sie vorausgefüllt)
 > The following instructions are intended for the next 1–3 interactions...
 
 Dies teilt Claude Code mit: **diese Anweisungen sind nur für die nächsten 1–3 Runden aktiv**, danach werden sie ausgeblendet. Verhindert, dass die „Expertenpersona" anschließend in unzusammenhängende Konversationen einsickert.
 
-**Diese Zeile wird automatisch von cc-viewer generiert. Sie müssen sie nicht schreiben.**
+**Diese Zeile ist im Editor vorausgefüllt — lassen Sie sie unverändert; Sie müssen sie nicht neu schreiben.**
 
 ### 2. Einführende Aufgabendefinition (**das ist es, was Sie umschreiben sollten**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Die ursprüngliche Vorlage listet 6 Elemente eines „Implementierungsplans" auf
 
 ## Tipps zur Erstellung (TL;DR)
 
-1. **Behalten Sie den Wrapper**: `<system-reminder>` + `[SCOPED INSTRUCTION]`-Zeile wird von cc-viewer hinzugefügt — nicht wiederholen.
-2. **Schreiben Sie den Eröffnungssatz um**: nennen Sie Rolle, Ziel und Ausgabeformat in einer Zeile.
-3. **Flexibler Workflow**: 1–2 Schritte für leichte Aufgaben, die volle 5-Schritte-Schleife nur für komplexe.
-4. **Schreiben Sie die Unterrollen aus Schritt 1 um**: die Standardwerte (akademische Arbeiten / Wettbewerber / Demo) sind wahrscheinlich nicht das, was Sie wollen.
-5. **Die finale „Liefer-Checkliste" ist Ihre Qualitätsschwelle**: spezifizieren Sie die Ausgabestruktur — Claude Code wird sie strikt befolgen.
+1. **Schreiben Sie den Eröffnungssatz um**: nennen Sie Rolle, Ziel und Ausgabeformat in einer Zeile.
+2. **Flexibler Workflow**: 1–2 Schritte für leichte Aufgaben, die volle 5-Schritte-Schleife nur für komplexe.
+3. **Schreiben Sie die Unterrollen aus Schritt 1 um**: die Standardwerte (akademische Arbeiten / Wettbewerber / Demo) sind wahrscheinlich nicht das, was Sie wollen.
+4. **Die finale „Liefer-Checkliste" ist Ihre Qualitätsschwelle**: spezifizieren Sie die Ausgabestruktur — Claude Code wird sie strikt befolgen.
 
 ---
 
 ## Ein überarbeitetes Beispiel: Wettbewerbsanalyst
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 Im Vergleich zum ursprünglichen Research Expert: auf 4 Schritte gekürzt, Unterrollen von 6 auf 3 reduziert, Liefer-Liste vollständig als „Berichtsabschnitte" umgeschrieben.

package/concepts/en/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## What the two input fields do
 
 - **Expert name**: the label shown on the role button in the UltraPlan variant row (30-char max). It's just a display name and is **never** sent to Claude Code.
-- **Prompt body**: your role instruction. At send time cc-viewer **automatically** wraps it in `<system-reminder>...</system-reminder>` tags with a `[SCOPED INSTRUCTION]` scope header. So **write the body only** — do not add `<system-reminder>` tags yourself.
+- **Prompt body**: your role instruction. When you create a new expert, the editor **comes prefilled** with the `<system-reminder>...</system-reminder>` wrapper and its `[SCOPED INSTRUCTION]` scope header — **write your role instruction inside the wrapper**. cc-viewer won't double-wrap: if the wrapper is present it is sent as-is; if you remove it, cc-viewer adds one back at send time.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## Section-by-section breakdown
 
-### 1. `[SCOPED INSTRUCTION]` scope header (wrapper — auto-generated)
+### 1. `[SCOPED INSTRUCTION]` scope header (wrapper — prefilled for you)
 > The following instructions are intended for the next 1–3 interactions...
 
 This tells Claude Code: **these instructions are only active for the next 1–3 turns**, then fade out. Prevents the "expert persona" from leaking into unrelated conversation afterwards.
 
-**This line is generated by cc-viewer automatically. You don't need to write it.**
+**This line comes prefilled in the editor — keep it as-is; you don't need to rewrite it.**
 
 ### 2. Opening task definition (**this is what you should rewrite**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ The original template lists 6 elements of an "implementation plan". Your deliver
 
 ## Authoring tips (TL;DR)
 
-1. **Keep the wrapper**: `<system-reminder>` + `[SCOPED INSTRUCTION]` line is added by cc-viewer — don't repeat.
-2. **Rewrite the opening sentence**: state the role, goal, and output format in one line.
-3. **Flex the workflow**: 1–2 steps for light tasks, the full 5-step loop only for complex ones.
-4. **Rewrite Step 1 sub-roles**: the defaults (academic papers / competitors / demo) are probably not what you want.
-5. **The final "deliverable checklist" is your quality bar**: spell out the output structure — Claude Code will follow it strictly.
+1. **Rewrite the opening sentence**: state the role, goal, and output format in one line.
+2. **Flex the workflow**: 1–2 steps for light tasks, the full 5-step loop only for complex ones.
+3. **Rewrite Step 1 sub-roles**: the defaults (academic papers / competitors / demo) are probably not what you want.
+4. **The final "deliverable checklist" is your quality bar**: spell out the output structure — Claude Code will follow it strictly.
 
 ---
 
 ## A refactored example: Competitive Analyst
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 Compared to the original Research Expert: trimmed to 4 steps, sub-roles reduced from 6 to 3, deliverable list fully rewritten as "report sections".

package/concepts/es/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## Qué hacen los dos campos de entrada
 
 - **Nombre del experto**: la etiqueta mostrada en el botón de rol en la fila de variantes UltraPlan (máx. 30 caracteres). Es solo un nombre de visualización y **nunca** se envía a Claude Code.
-- **Cuerpo del prompt**: tu instrucción de rol. En el momento del envío, cc-viewer lo envuelve **automáticamente** en etiquetas `<system-reminder>...</system-reminder>` con un encabezado de alcance `[SCOPED INSTRUCTION]`. Por lo tanto, **escribe solo el cuerpo** — no añadas tú mismo las etiquetas `<system-reminder>`.
+- **Cuerpo del prompt**: tu instrucción de rol. Al crear un nuevo experto, el editor **viene precargado** con el envoltorio `<system-reminder>...</system-reminder>` y su encabezado de alcance `[SCOPED INSTRUCTION]` — **escribe tu instrucción de rol dentro del envoltorio**. cc-viewer no envuelve dos veces: si el envoltorio está presente, se envía tal cual; si lo quitas, cc-viewer añade uno de nuevo en el momento del envío.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## Desglose sección por sección
 
-### 1. Encabezado de alcance `[SCOPED INSTRUCTION]` (envoltorio — generado automáticamente)
+### 1. Encabezado de alcance `[SCOPED INSTRUCTION]` (envoltorio — precargado para ti)
 > The following instructions are intended for the next 1–3 interactions...
 
 Esto le dice a Claude Code: **estas instrucciones solo están activas durante los próximos 1–3 turnos**, luego se desvanecen. Evita que la «persona experta» se filtre posteriormente a una conversación no relacionada.
 
-**Esta línea es generada automáticamente por cc-viewer. No necesitas escribirla.**
+**Esta línea viene precargada en el editor — déjala tal cual; no necesitas reescribirla.**
 
 ### 2. Definición de tarea inicial (**esto es lo que deberías reescribir**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ La plantilla original enumera 6 elementos de un «plan de implementación». Tu
 
 ## Consejos de creación (TL;DR)
 
-1. **Mantén el envoltorio**: la línea `<system-reminder>` + `[SCOPED INSTRUCTION]` la añade cc-viewer — no la repitas.
-2. **Reescribe la oración inicial**: indica el rol, el objetivo y el formato de salida en una sola línea.
-3. **Flexibiliza el flujo de trabajo**: 1–2 pasos para tareas ligeras, el ciclo completo de 5 pasos solo para las complejas.
-4. **Reescribe los subroles del Paso 1**: los valores predeterminados (artículos académicos / competidores / demo) probablemente no son lo que quieres.
-5. **La «lista de verificación de entregables» final es tu estándar de calidad**: especifica la estructura de salida — Claude Code la seguirá estrictamente.
+1. **Reescribe la oración inicial**: indica el rol, el objetivo y el formato de salida en una sola línea.
+2. **Flexibiliza el flujo de trabajo**: 1–2 pasos para tareas ligeras, el ciclo completo de 5 pasos solo para las complejas.
+3. **Reescribe los subroles del Paso 1**: los valores predeterminados (artículos académicos / competidores / demo) probablemente no son lo que quieres.
+4. **La «lista de verificación de entregables» final es tu estándar de calidad**: especifica la estructura de salida — Claude Code la seguirá estrictamente.
 
 ---
 
 ## Un ejemplo refactorizado: Analista competitivo
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 En comparación con el Research Expert original: recortado a 4 pasos, subroles reducidos de 6 a 3, lista de entregables completamente reescrita como «secciones del informe».

package/concepts/fr/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## Ce que font les deux champs de saisie
 
 - **Nom de l'expert** : l'étiquette affichée sur le bouton de rôle dans la rangée des variantes UltraPlan (30 caractères max.). Ce n'est qu'un nom d'affichage et il n'est **jamais** envoyé à Claude Code.
-- **Corps du prompt** : votre instruction de rôle. Au moment de l'envoi, cc-viewer l'enveloppe **automatiquement** dans des balises `<system-reminder>...</system-reminder>` avec un en-tête de portée `[SCOPED INSTRUCTION]`. Donc **n'écrivez que le corps** — n'ajoutez pas vous-même de balises `<system-reminder>`.
+- **Corps du prompt** : votre instruction de rôle. Lorsque vous créez un nouvel expert, l'éditeur **est prérempli** avec le wrapper `<system-reminder>...</system-reminder>` et son en-tête de portée `[SCOPED INSTRUCTION]` — **écrivez votre instruction de rôle à l'intérieur du wrapper**. cc-viewer n'enveloppe pas deux fois : si le wrapper est présent, il est envoyé tel quel ; si vous le supprimez, cc-viewer en rajoute un au moment de l'envoi.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## Décomposition section par section
 
-### 1. En-tête de portée `[SCOPED INSTRUCTION]` (wrapper — généré automatiquement)
+### 1. En-tête de portée `[SCOPED INSTRUCTION]` (wrapper — prérempli pour vous)
 > The following instructions are intended for the next 1–3 interactions...
 
 Cela indique à Claude Code : **ces instructions ne sont actives que pour les 1 à 3 prochains tours**, puis s'estompent. Empêche la « persona d'expert » de déborder par la suite dans une conversation sans rapport.
 
-**Cette ligne est générée automatiquement par cc-viewer. Vous n'avez pas besoin de l'écrire.**
+**Cette ligne est préremplie dans l'éditeur — laissez-la telle quelle ; vous n'avez pas besoin de la réécrire.**
 
 ### 2. Définition de tâche d'ouverture (**c'est ce que vous devriez réécrire**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Le modèle d'origine répertorie 6 éléments d'un « plan d'implémentation ».
 
 ## Conseils de création (TL;DR)
 
-1. **Conservez le wrapper** : la ligne `<system-reminder>` + `[SCOPED INSTRUCTION]` est ajoutée par cc-viewer — ne la répétez pas.
-2. **Réécrivez la phrase d'ouverture** : énoncez le rôle, l'objectif et le format de sortie en une seule ligne.
-3. **Adaptez le workflow** : 1–2 étapes pour les tâches légères, la boucle complète à 5 étapes uniquement pour les tâches complexes.
-4. **Réécrivez les sous-rôles de l'étape 1** : les valeurs par défaut (articles académiques / concurrents / démo) ne sont probablement pas ce que vous voulez.
-5. **La « liste de contrôle des livrables » finale est votre exigence de qualité** : précisez la structure de sortie — Claude Code la suivra strictement.
+1. **Réécrivez la phrase d'ouverture** : énoncez le rôle, l'objectif et le format de sortie en une seule ligne.
+2. **Adaptez le workflow** : 1–2 étapes pour les tâches légères, la boucle complète à 5 étapes uniquement pour les tâches complexes.
+3. **Réécrivez les sous-rôles de l'étape 1** : les valeurs par défaut (articles académiques / concurrents / démo) ne sont probablement pas ce que vous voulez.
+4. **La « liste de contrôle des livrables » finale est votre exigence de qualité** : précisez la structure de sortie — Claude Code la suivra strictement.
 
 ---
 
 ## Un exemple refactoré : Analyste concurrentiel
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 Comparé au Research Expert d'origine : réduit à 4 étapes, sous-rôles passés de 6 à 3, liste des livrables entièrement réécrite en « sections de rapport ».

package/concepts/it/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## Cosa fanno i due campi di input
 
 - **Nome esperto**: l'etichetta mostrata sul pulsante del ruolo nella riga delle varianti UltraPlan (max 30 caratteri). È solo un nome visualizzato e **non viene mai** inviato a Claude Code.
-- **Corpo del prompt**: la tua istruzione di ruolo. Al momento dell'invio, cc-viewer lo avvolge **automaticamente** in tag `<system-reminder>...</system-reminder>` con un'intestazione di scope `[SCOPED INSTRUCTION]`. Quindi **scrivi solo il corpo** — non aggiungere tu stesso i tag `<system-reminder>`.
+- **Corpo del prompt**: la tua istruzione di ruolo. Quando crei un nuovo esperto, l'editor **è precompilato** con il wrapper `<system-reminder>...</system-reminder>` e la sua intestazione di scope `[SCOPED INSTRUCTION]` — **scrivi la tua istruzione di ruolo all'interno del wrapper**. cc-viewer non avvolge due volte: se il wrapper è presente viene inviato così com'è; se lo rimuovi, cc-viewer ne aggiunge uno al momento dell'invio.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## Analisi sezione per sezione
 
-### 1. Intestazione di scope `[SCOPED INSTRUCTION]` (wrapper — generato automaticamente)
+### 1. Intestazione di scope `[SCOPED INSTRUCTION]` (wrapper — precompilato per te)
 > The following instructions are intended for the next 1–3 interactions...
 
 Questo dice a Claude Code: **queste istruzioni sono attive solo per i prossimi 1–3 turni**, poi svaniscono. Impedisce alla "persona dell'esperto" di trasferirsi in conversazioni non correlate successive.
 
-**Questa riga viene generata automaticamente da cc-viewer. Non è necessario scriverla.**
+**Questa riga è precompilata nell'editor — lasciala così com'è; non è necessario riscriverla.**
 
 ### 2. Definizione del compito iniziale (**questo è ciò che dovresti riscrivere**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Il modello originale elenca 6 elementi di un "piano di implementazione". Il tuo
 
 ## Suggerimenti per la creazione (TL;DR)
 
-1. **Mantieni il wrapper**: la riga `<system-reminder>` + `[SCOPED INSTRUCTION]` viene aggiunta da cc-viewer — non ripeterla.
-2. **Riscrivi la frase di apertura**: dichiara ruolo, obiettivo e formato di output in una sola riga.
-3. **Flessibilizza il workflow**: 1–2 passaggi per attività leggere, l'intero ciclo a 5 passaggi solo per quelle complesse.
-4. **Riscrivi i sotto-ruoli del passaggio 1**: i valori predefiniti (articoli accademici / concorrenti / demo) probabilmente non sono ciò che vuoi.
-5. **La "checklist dei deliverable" finale è il tuo standard di qualità**: specifica la struttura di output — Claude Code la seguirà rigorosamente.
+1. **Riscrivi la frase di apertura**: dichiara ruolo, obiettivo e formato di output in una sola riga.
+2. **Flessibilizza il workflow**: 1–2 passaggi per attività leggere, l'intero ciclo a 5 passaggi solo per quelle complesse.
+3. **Riscrivi i sotto-ruoli del passaggio 1**: i valori predefiniti (articoli accademici / concorrenti / demo) probabilmente non sono ciò che vuoi.
+4. **La "checklist dei deliverable" finale è il tuo standard di qualità**: specifica la struttura di output — Claude Code la seguirà rigorosamente.
 
 ---
 
 ## Un esempio rifattorizzato: Analista competitivo
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 Rispetto al Research Expert originale: ridotto a 4 passaggi, sotto-ruoli ridotti da 6 a 3, elenco dei deliverable completamente riscritto come "sezioni del rapporto".

package/concepts/ja/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## 2 つの入力欄の役割
 
 - **エキスパート名**：UltraPlan のバリアント行に表示されるロールボタンのラベルです（最大 30 文字）。単なる表示名であり、Claude Code に送信されることは**ありません**。
-- **プロンプト本文**：あなたが書くロール指示です。送信時に cc-viewer が**自動的に** `<system-reminder>...</system-reminder>` タグで囲み、`[SCOPED INSTRUCTION]` のスコープヘッダーを先頭に付加します。したがって**本文だけを書いてください** — `<system-reminder>` タグを自分で追加する必要はありません。
+- **プロンプト本文**：あなたが書くロール指示です。新しいエキスパートを作成すると、エディタには `<system-reminder>...</system-reminder>` ラッパーと `[SCOPED INSTRUCTION]` スコープヘッダーが**あらかじめ入力された状態**で表示されます — **ロール指示はラッパーの内側に書いてください**。cc-viewer は二重に包むことはありません：ラッパーがあればそのまま送信し、削除した場合は送信時に cc-viewer が改めて 1 つ付け直します。
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## セクション別の解説
 
-### 1. `[SCOPED INSTRUCTION]` スコープヘッダー（ラッパー — 自動生成）
+### 1. `[SCOPED INSTRUCTION]` スコープヘッダー（ラッパー — あらかじめ入力済み）
 > The following instructions are intended for the next 1–3 interactions...
 
 この行は Claude Code に対して、**この指示は次の 1〜3 ターンの対話でのみ有効**であり、その後はフェードアウトすると伝えます。「エキスパートペルソナ」がタスク以外の会話に染み出すのを防ぎます。
 
-**この行は cc-viewer が自動的に生成しますので、自分で書く必要はありません。**
+**この行はエディタにあらかじめ入力されています — そのまま残してください。自分で書き直す必要はありません。**
 
 ### 2. 冒頭のタスク定義（**ここが最も書き換える価値のある部分です**）
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Research Expert は 6 つの潜在的なロール（業界スカウト、学術
 
 ## 作成のヒント（TL;DR）
 
-1. **ラッパーは保持してください**：`<system-reminder>` + `[SCOPED INSTRUCTION]` の行は cc-viewer が自動的に追加します — 重複して書かないでください。
-2. **冒頭の一文を書き換えてください**：ロール、目的、出力形式を一行で明示します。
-3. **ワークフローを柔軟に**：軽量タスクには 1〜2 ステップ、複雑なタスクの場合のみ 5 ステップの完全ループを使います。
-4. **ステップ 1 のサブロールを書き換えてください**：デフォルト（学術論文 / 競合 / デモ）はおそらくあなたが望むものではありません。
-5. **最後の「成果物チェックリスト」が品質基準です**：出力構造を明確に書き出してください — Claude Code はそれを厳密に守ります。
+1. **冒頭の一文を書き換えてください**：ロール、目的、出力形式を一行で明示します。
+2. **ワークフローを柔軟に**：軽量タスクには 1〜2 ステップ、複雑なタスクの場合のみ 5 ステップの完全ループを使います。
+3. **ステップ 1 のサブロールを書き換えてください**：デフォルト（学術論文 / 競合 / デモ）はおそらくあなたが望むものではありません。
+4. **最後の「成果物チェックリスト」が品質基準です**：出力構造を明確に書き出してください — Claude Code はそれを厳密に守ります。
 
 ---
 
 ## リファクタリング例：Competitive Analyst
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 オリジナルの Research Expert と比較すると：4 ステップに削減され、サブロールは 6 個から 3 個に減り、成果物リストは「レポートのセクション」として完全に書き換えられています。

package/concepts/ko/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## 두 입력 필드의 역할
 
 - **Expert 이름**: UltraPlan 변형 행의 역할 버튼에 표시되는 라벨입니다 (최대 30자). 단순한 표시 이름이며 Claude Code로 **절대** 전송되지 않습니다.
-- **프롬프트 본문**: 작성하시는 역할 지침입니다. 전송 시 cc-viewer가 **자동으로** `<system-reminder>...</system-reminder>` 태그로 감싸고 `[SCOPED INSTRUCTION]` 스코프 헤더를 맨 앞에 추가합니다. 따라서 **본문만 작성**하시면 되며, 직접 `<system-reminder>` 태그를 추가하지 마십시오.
+- **프롬프트 본문**: 작성하시는 역할 지침입니다. 새 expert를 만들면 에디터에 `<system-reminder>...</system-reminder>` 래퍼와 `[SCOPED INSTRUCTION]` 스코프 헤더가 **미리 채워진** 상태로 표시됩니다 — **역할 지침은 래퍼 안에 작성**하십시오. cc-viewer는 이중으로 감싸지 않습니다: 래퍼가 있으면 그대로 전송하고, 제거하면 전송 시 cc-viewer가 다시 하나를 추가합니다.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## 섹션별 분석
 
-### 1. `[SCOPED INSTRUCTION]` 스코프 헤더 (래퍼 — 자동 생성)
+### 1. `[SCOPED INSTRUCTION]` 스코프 헤더 (래퍼 — 미리 채워짐)
 > The following instructions are intended for the next 1–3 interactions...
 
 이 줄은 Claude Code에게 **이 지침이 다음 1~3턴의 대화에서만 활성화된다**고 알려주며, 그 이후에는 점차 비활성화됩니다. "expert 페르소나"가 무관한 후속 대화로 새어 나가는 것을 방지합니다.
 
-**이 줄은 cc-viewer가 자동으로 생성하므로 직접 작성할 필요가 없습니다.**
+**이 줄은 에디터에 미리 채워져 있습니다 — 그대로 두십시오. 직접 다시 작성할 필요가 없습니다.**
 
 ### 2. 첫머리 작업 정의 (**가장 다시 작성할 가치가 있는 부분입니다**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Research Expert는 6개의 잠재적 역할을 나열합니다 (산업 스카우
 
 ## 작성 팁 (TL;DR)
 
-1. **래퍼는 유지하십시오**: `<system-reminder>` 와 `[SCOPED INSTRUCTION]` 줄은 cc-viewer가 자동으로 추가합니다 — 중복해서 작성하지 마십시오.
-2. **첫 문장을 다시 작성하십시오**: 한 줄로 역할, 목표, 출력 형식을 명시합니다.
-3. **워크플로를 유연하게**: 가벼운 작업에는 1~2단계로 충분하고, 복잡한 작업에서만 5단계 풀 루프를 사용합니다.
-4. **Step 1의 서브 역할을 다시 작성하십시오**: 기본값 (학술 논문 / 경쟁사 / 데모) 은 대개 원하는 것이 아닙니다.
-5. **최종 "산출물 체크리스트"는 품질 기준입니다**: 출력 구조를 명확히 적어 두십시오 — Claude Code는 이를 엄격히 따를 것입니다.
+1. **첫 문장을 다시 작성하십시오**: 한 줄로 역할, 목표, 출력 형식을 명시합니다.
+2. **워크플로를 유연하게**: 가벼운 작업에는 1~2단계로 충분하고, 복잡한 작업에서만 5단계 풀 루프를 사용합니다.
+3. **Step 1의 서브 역할을 다시 작성하십시오**: 기본값 (학술 논문 / 경쟁사 / 데모) 은 대개 원하는 것이 아닙니다.
+4. **최종 "산출물 체크리스트"는 품질 기준입니다**: 출력 구조를 명확히 적어 두십시오 — Claude Code는 이를 엄격히 따를 것입니다.
 
 ---
 
 ## 리팩터링된 예시: Competitive Analyst
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 원본 Research Expert와 비교하면: 4단계로 축소되었고, 서브 역할은 6개에서 3개로 줄었으며, 산출물 목록은 "보고서 섹션"으로 완전히 다시 작성되었습니다.

package/concepts/no/CustomUltraplanExpert.md

@@ -3,7 +3,7 @@
 ## Hva de to inndatafeltene gjør
 
 - **Ekspertnavn**: etiketten som vises på rolleknappen i UltraPlan-variantraden (maks 30 tegn). Det er bare et visningsnavn og sendes **aldri** til Claude Code.
-- **Promptinnhold**: din rolleinstruksjon. Ved sending pakker cc-viewer det **automatisk** inn i `<system-reminder>...</system-reminder>`-tagger med en `[SCOPED INSTRUCTION]`-scope-header. Så **skriv kun selve innholdet** — ikke legg til `<system-reminder>`-tagger selv.
+- **Promptinnhold**: din rolleinstruksjon. Når du oppretter en ny ekspert, kommer editoren **ferdig utfylt** med `<system-reminder>...</system-reminder>`-wrapperen og dens `[SCOPED INSTRUCTION]`-scope-header — **skriv rolleinstruksjonen din inni wrapperen**. cc-viewer pakker ikke dobbelt: hvis wrapperen er til stede sendes den som den er; hvis du fjerner den, legger cc-viewer til en ny ved sending.
 
 ---
 
@@ -77,12 +77,12 @@ Your final plan must include the following elements:
 
 ## Seksjon-for-seksjon gjennomgang
 
-### 1. `[SCOPED INSTRUCTION]`-scope-header (wrapper — auto-generert)
+### 1. `[SCOPED INSTRUCTION]`-scope-header (wrapper — ferdig utfylt for deg)
 > The following instructions are intended for the next 1–3 interactions...
 
 Dette forteller Claude Code: **disse instruksjonene er kun aktive de neste 1–3 turene**, deretter avtar de. Hindrer at "ekspertpersonaen" lekker inn i urelaterte samtaler etterpå.
 
-**Denne linjen genereres av cc-viewer automatisk. Du trenger ikke å skrive den.**
+**Denne linjen kommer ferdig utfylt i editoren — la den stå som den er; du trenger ikke å skrive den om.**
 
 ### 2. Innledende oppgavedefinisjon (**dette er det du skal skrive om**)
 > Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
@@ -125,17 +125,19 @@ Den opprinnelige malen lister 6 elementer i en "implementeringsplan". Din levera
 
 ## Forfattertips (TL;DR)
 
-1. **Behold wrapperen**: `<system-reminder>` + `[SCOPED INSTRUCTION]`-linjen legges til av cc-viewer — ikke gjenta.
-2. **Skriv om åpningssetningen**: oppgi rolle, mål og utdataformat på én linje.
-3. **Flex arbeidsflyten**: 1–2 trinn for lette oppgaver, den fulle 5-trinns sløyfen kun for komplekse.
-4. **Skriv om Trinn 1s underroller**: standardene (akademiske artikler / konkurrenter / demo) er sannsynligvis ikke det du vil ha.
-5. **Den endelige "leveranse-sjekklisten" er din kvalitetslinje**: stav ut utdatastrukturen — Claude Code følger den strengt.
+1. **Skriv om åpningssetningen**: oppgi rolle, mål og utdataformat på én linje.
+2. **Flex arbeidsflyten**: 1–2 trinn for lette oppgaver, den fulle 5-trinns sløyfen kun for komplekse.
+3. **Skriv om Trinn 1s underroller**: standardene (akademiske artikler / konkurrenter / demo) er sannsynligvis ikke det du vil ha.
+4. **Den endelige "leveranse-sjekklisten" er din kvalitetslinje**: stav ut utdatastrukturen — Claude Code følger den strengt.
 
 ---
 
 ## Et omarbeidet eksempel: Competitive Analyst
 
 ```
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions apply only to the next 1–3 interactions. Once the task is complete, these instructions should gradually decrease in priority and no longer affect subsequent interactions. You should be adept at utilizing tools such as `AskUserQuestion`, `EnterPlanMode`, and `TeamCreate`, rather than relying solely on plain text processing.
+
 You are a senior competitive intelligence analyst for {industry}. Your goal is to
 produce a decision-grade competitive landscape report for the product "{our product}".
 
@@ -160,6 +162,7 @@ Instructions:
    - Pricing & GTM table
    - Top 3 strategic implications for our product
    - Caveats & data gaps
+</system-reminder>
 ```
 
 Sammenlignet med den originale Research Expert: trimmet til 4 trinn, underroller redusert fra 6 til 3, leveranseliste fullstendig omskrevet som "rapportseksjoner".