cc-viewer 1.6.232 → 1.6.233

package/concepts/no/CustomUltraplanExpert.md

@@ -0,0 +1,165 @@
+# Custom UltraPlan Expert — Forfatterveiledning
+
+## 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.
+
+---
+
+## Hvordan ser ekspertmalen ut?
+
+Hver innebygde ekspert (Code Expert / Research Expert) er i bunn og grunn en `<system-reminder>`-blokk som injiseres inn i Claude Codes kontekst. Din custom-ekspert går gjennom nøyaktig samme pipeline. Her er **Research Expert**-malen brutt ned:
+
+```xml
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3
+interactions. Once the task is complete, these instructions should be gradually
+deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target
+audience, and deliverable format whenever the user's intent is ambiguous. Skip
+only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally
+detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore
+   various facets of the requirements:
+   - If necessary, deploy a preliminary investigator to conduct an initial
+     survey of industry-specific solutions using `webSearch`;
+   - If necessary, deploy a specialized investigator to research authoritative
+     sources—such as academic papers, news articles, and research reports—
+     using `webSearch`;
+   - Assign an agent to synthesize the target solution, while simultaneously
+     verifying the rigor and credibility of the gathered papers, news, and
+     research reports;
+   - If necessary, assign an agent to analyze competitor data to provide
+     supplementary analytical perspectives;
+   - If necessary, assign an agent to handle the implementation of a product
+     demo (generating outputs such as HTML, Markdown, etc.);
+   - If the task is sufficiently complex, you may assign additional teammates
+     to the roles defined above, or introduce other specialized roles; you are
+     permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive,
+   step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these
+   agents shall scrutinize the plan from multiple roles and perspectives to
+   identify any omitted steps and to propose reasonable additions or
+   optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke
+   `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+   - If Approved: Proceed to execute the plan within this current session.
+   - If Rejected: Revise the plan based on the provided feedback, and then
+     invoke `ExitPlanMode` once again.
+   - If an Error Occurs: Do *not* follow the suggestions; prompt the user for
+     further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact
+  changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an
+  appropriate location and notify the user.
+</system-reminder>
+```
+
+---
+
+## Seksjon-for-seksjon gjennomgang
+
+### 1. `[SCOPED INSTRUCTION]`-scope-header (wrapper — auto-generert)
+> 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.**
+
+### 2. Innledende oppgavedefinisjon (**dette er det du skal skrive om**)
+> Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+Dette er hele malens "subjekt-verb-objekt": **det forteller Claude Code holdningen og målet**. Standarden "multi-agent exploration + implementation plan" passer godt til **programvareutvikling / planlegging**, men føles klosset for mange andre domener (innholdsgjennomgang, dataanalyse, copywriting, markedsundersøkelse, compliance-revisjon…).
+
+**Vi anbefaler sterkt å skrive om denne linjen for målet ditt**, for eksempel:
+
+- **Innholdsanmelder**: "You are a senior content reviewer specializing in {domain}. Your goal is to identify factual inaccuracies, tone inconsistencies, and structural weaknesses in the provided material."
+- **Konkurranseanalytiker**: "Conduct a rigorous competitive analysis for {product category}. Produce a comparison matrix, positioning insights, and strategic recommendations."
+- **Copywriter**: "Generate multiple creative copy variants for {scenario}, each with distinct positioning, tone, and call-to-action strategy."
+
+### 3. Arbeidsflyttrinn (1–5 punkter — **trim eller utvid basert på kompleksitet**)
+
+Research Expert har 5 trinn: **utforsk → syntetiser → review → send inn plan → utfør**. Dette håndhever "parallell multi-agent + kryssreview + plangodkjenning" — tre lag av strenghet, passende for høyrisiko-/breddeomfangsoppgaver, men **overdrevent for lette oppgaver**.
+
+- **Enkel oppgave** (enkelt oppslag / liten fiks): dropp multi-agent-utsendelsen og review; bare "produser svaret" i ett trinn.
+- **Middels kompleks oppgave**: behold "utforsk → syntetiser → review"; dropp ExitPlanMode-dansen; lever resultatet direkte.
+- **Kompleks, dyr oppgave** (stor refaktorering, multi-option-sammenligning, tverrfaglig forskning): behold alle 5 trinn, og legg eventuelt til et "risikomodell"- eller "alternativ-sammenligningsmatrise"-trinn.
+
+### 4. Underroller i Trinn 1 (**tilpass til ditt domene**)
+
+Research Expert lister 6 potensielle roller (bransjespeider, akademisk forsker, syntetiserer + faktasjekker, konkurranseanalytiker, demo-produsent, utvidelsesplass). **Skriv om denne listen for ditt scenario**:
+
+- **Skriving**: "kildesamler + stilanalytiker + faktasjekker"
+- **Dataanalyse**: "datavaskingsagent + statistisk modelleringsagent + visualiseringsagent"
+- **Kodeaudit**: "statisk-analyse-agent + avhengighetskjederevisor + threat modeler"
+
+### 5. Endelig leveranse-sjekkliste (**tilpass til ditt reelle behov**)
+
+> Your final plan must include the following elements: ...
+
+Den opprinnelige malen lister 6 elementer i en "implementeringsplan". Din leveranse kan være noe helt annet:
+
+- En **forskningsrapport** → "Executive summary / Methodology / Key findings / Limitations / Action recommendations"
+- En **review-rapport** → "Issue list / Severity rating / Fix suggestions / Before-after examples"
+- En **sammenligningsmatrise** → "Dimension definitions / Scoring rubric / Conclusions / Recommendation rationale"
+
+---
+
+## 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.
+
+---
+
+## Et omarbeidet eksempel: Competitive Analyst
+
+```
+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}".
+
+Instructions:
+1. Use the Agent tool to dispatch 3 parallel investigators:
+   - Market landscape agent: map the top 5–8 competitors with core positioning
+   - Feature matrix agent: compile a feature-by-feature comparison using
+     publicly available sources (webSearch)
+   - Pricing & GTM agent: analyze pricing models, distribution channels, and
+     go-to-market motions
+
+2. Synthesize the three streams into a unified competitive report.
+
+3. Dispatch one review agent to stress-test the report: challenge any
+   assumption lacking a cited source, flag outdated data (>12 months), and
+   propose one "non-obvious" insight.
+
+4. Deliver the final report with the following sections:
+   - TL;DR (3 bullets)
+   - Competitor positioning map
+   - Feature matrix (markdown table)
+   - Pricing & GTM table
+   - Top 3 strategic implications for our product
+   - Caveats & data gaps
+```
+
+Sammenlignet med den originale Research Expert: trimmet til 4 trinn, underroller redusert fra 6 til 3, leveranseliste fullstendig omskrevet som "rapportseksjoner".

package/concepts/no/UltraPlan.md

@@ -53,3 +53,104 @@ En multi-agent samarbeidsarbeidsflyt designet for forsknings- og analyseoppgaver
 4. Syntetiser alle funn til en omfattende implementeringsplan
 5. Utplasser flere gjennomgangsagenter for å granske planen fra ulike roller og perspektiver
 6. Utfør planen etter godkjenning
+
+---
+
+## Raw Templates
+
+Below are the two raw prompt templates UltraPlan actually sends to Claude Code (see `src/utils/ultraplanTemplates.js`):
+
+### Code Expert (codeExpert)
+
+<textarea readonly><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.
+
+Pre-requisite: Use `AskUserQuestion` to clarify user intent whenever the request is ambiguous (target element, interaction style, scope of platforms, etc.). Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate a highly detailed implementation plan.
+
+Instructions:
+1. Use the `Agent` tool to spawn parallel agents that simultaneously explore different aspects of the codebase:
+- If necessary, assign a preliminary researcher to use the `webSearch` tool to first investigate cutting-edge solutions in the relevant industry domain;
+- One agent responsible for understanding the relevant existing code and architecture;
+- One agent responsible for identifying all files that need to be modified;
+- One agent responsible for identifying potential risks, edge cases, and dependencies;
+- You may add other roles or deploy additional agents beyond the three listed above; the maximum number of concurrently dispatched agents is 5.
+
+2. Synthesize the findings from all agents into a detailed, step-by-step implementation plan.
+
+3. Use the `Agent` tool to spawn 2-3 review agents that examine the plan from different perspectives, checking for missing steps, potential risks, or corresponding mitigation strategies.
+
+4. Integrate the feedback gathered during the review process, then call `ExitPlanMode` to submit your final plan.
+
+5. Once `ExitPlanMode` returns a result:
+- If approved: proceed to execute the plan within this session.
+- If rejected: revise the plan based on the feedback provided and call `ExitPlanMode` again.
+- If an error occurs (including receiving a "Not in Plan Mode" message): do **not** follow the suggestions provided in the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the implementation strategy;
+- An ordered list of files to be created or modified, with precise details of the required changes for each file;
+- A step-by-step execution sequence;
+- Testing and validation procedures;
+- Potential risks and their corresponding mitigation strategies;
+
+6. After the final plan has been successfully executed:
+First run `git diff --quiet && git diff --cached --quiet` (or equivalent) to detect whether the working tree actually has non-trivial changes; if there are no real changes (or only whitespace/comment-only edits), skip the UltraReview step.
+Otherwise, if the project is managed with Git:
+Initiate a team (`TeamCreate`), dynamically allocating the number of teammates based on task complexity (5 is recommended);
+Task: Conduct a Code Review of the current git changes from multiple perspectives;
+Pre-requisites:
+- The git repository may be located in a subdirectory of the current directory; prefer `git rev-parse --show-toplevel` (fall back to recursive lookup) before proceeding;
+- In the case of multiple repositories, tasks may be executed separately;
+The team's goal is to analyze the current Git change log and validate each modification from different perspectives, specifically including:
+- Whether requirements/objectives have been met and functionality is complete;
+- Whether newly added code introduces side effects, breaks existing functionality, or poses potential risks;
+- Code quality: naming, readability, complexity, technical debt, maintainability;
+- Testing and documentation: whether there is adequate test coverage, and whether critical logic has necessary comments or documentation;
+- Dependencies and compatibility: whether new dependencies or version compatibility issues have been introduced;
+Workflow:
+- Each teammate, according to their own role, covers the review dimensions one by one and independently outputs a report;
+- After consolidating the reports, perform a cross-review to identify conflicts or shared concerns;
+- Distill specific, actionable modification suggestions and annotate them with priority levels (P0/P1/P2/P3);
+- Upon completion, adopt P0 items, and selectively adopt P1 items when they are concrete and low-risk; defer P2/P3 to backlog;
+- After execution is complete, close the team (`TeamDelete`);
+</system-reminder></textarea>
+
+### Research Expert (researchExpert)
+
+<textarea readonly><system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3 interactions. Once the task is complete, these instructions should be gradually deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target audience, and deliverable format whenever the user's intent is ambiguous. Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore various facets of the requirements:
+- If necessary, deploy a preliminary investigator to conduct an initial survey of industry-specific solutions using `webSearch`;
+- If necessary, deploy a specialized investigator to research authoritative sources—such as academic papers, news articles, and research reports—using `webSearch`;
+- Assign an agent to synthesize the target solution, while simultaneously verifying the rigor and credibility of the gathered papers, news, and research reports;
+- If necessary, assign an agent to analyze competitor data to provide supplementary analytical perspectives;
+- If necessary, assign an agent to handle the implementation of a product demo (generating outputs such as HTML, Markdown, etc.);
+- If the task is sufficiently complex, you may assign additional teammates to the roles defined above, or introduce other specialized roles; you are permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive, step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these agents shall scrutinize the plan from multiple roles and perspectives to identify any omitted steps and to propose reasonable additions or optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+- If Approved: Proceed to execute the plan within this current session.
+- If Rejected: Revise the plan based on the provided feedback, and then invoke `ExitPlanMode` once again.
+- If an Error Occurs (including the message "Not in Plan Mode"): Do *not* follow the suggestions provided by the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an appropriate location and notify the user.
+</system-reminder></textarea>

package/concepts/pl/CustomUltraplanExpert.md

@@ -0,0 +1,165 @@
+# Custom UltraPlan Expert — Przewodnik tworzenia
+
+## Co robią dwa pola wejściowe
+
+- **Nazwa eksperta**: etykieta wyświetlana na przycisku roli w wierszu wariantów UltraPlan (maks. 30 znaków). To tylko nazwa wyświetlana i **nigdy** nie jest wysyłana do Claude Code.
+- **Treść promptu**: twoja instrukcja roli. W momencie wysyłania cc-viewer **automatycznie** opakowuje ją w tagi `<system-reminder>...</system-reminder>` z nagłówkiem zakresu `[SCOPED INSTRUCTION]`. Więc **pisz tylko treść** — nie dodawaj samodzielnie tagów `<system-reminder>`.
+
+---
+
+## Jak wygląda szablon eksperta?
+
+Każdy wbudowany ekspert (Code Expert / Research Expert) to w istocie blok `<system-reminder>` wstrzykiwany do kontekstu Claude Code. Twój własny ekspert przechodzi przez dokładnie ten sam pipeline. Oto rozłożony szablon **Research Expert**:
+
+```xml
+<system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3
+interactions. Once the task is complete, these instructions should be gradually
+deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target
+audience, and deliverable format whenever the user's intent is ambiguous. Skip
+only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally
+detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore
+   various facets of the requirements:
+   - If necessary, deploy a preliminary investigator to conduct an initial
+     survey of industry-specific solutions using `webSearch`;
+   - If necessary, deploy a specialized investigator to research authoritative
+     sources—such as academic papers, news articles, and research reports—
+     using `webSearch`;
+   - Assign an agent to synthesize the target solution, while simultaneously
+     verifying the rigor and credibility of the gathered papers, news, and
+     research reports;
+   - If necessary, assign an agent to analyze competitor data to provide
+     supplementary analytical perspectives;
+   - If necessary, assign an agent to handle the implementation of a product
+     demo (generating outputs such as HTML, Markdown, etc.);
+   - If the task is sufficiently complex, you may assign additional teammates
+     to the roles defined above, or introduce other specialized roles; you are
+     permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive,
+   step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these
+   agents shall scrutinize the plan from multiple roles and perspectives to
+   identify any omitted steps and to propose reasonable additions or
+   optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke
+   `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+   - If Approved: Proceed to execute the plan within this current session.
+   - If Rejected: Revise the plan based on the provided feedback, and then
+     invoke `ExitPlanMode` once again.
+   - If an Error Occurs: Do *not* follow the suggestions; prompt the user for
+     further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact
+  changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an
+  appropriate location and notify the user.
+</system-reminder>
+```
+
+---
+
+## Analiza sekcja po sekcji
+
+### 1. Nagłówek zakresu `[SCOPED INSTRUCTION]` (wrapper — auto-generowany)
+> The following instructions are intended for the next 1–3 interactions...
+
+Mówi to Claude Code: **te instrukcje są aktywne tylko przez najbliższe 1–3 tury**, a następnie wygasają. Zapobiega temu, by "persona eksperta" przeciekała do niezwiązanej rozmowy później.
+
+**Ta linia jest generowana przez cc-viewer automatycznie. Nie musisz jej pisać.**
+
+### 2. Wstępna definicja zadania (**to jest to, co powinieneś przepisać**)
+> Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+To "podmiot-orzeczenie-dopełnienie" całego szablonu: **mówi Claude Code o postawie i celu**. Domyślne "multi-agent exploration + implementation plan" dobrze pasuje do zadań **inżynierii oprogramowania / planowania**, ale wydaje się niezręczne w wielu innych dziedzinach (recenzja treści, analiza danych, copywriting, badania rynku, audyt zgodności…).
+
+**Zdecydowanie zalecamy przepisanie tej linii pod twój cel**, na przykład:
+
+- **Recenzent treści**: "You are a senior content reviewer specializing in {domain}. Your goal is to identify factual inaccuracies, tone inconsistencies, and structural weaknesses in the provided material."
+- **Analityk konkurencji**: "Conduct a rigorous competitive analysis for {product category}. Produce a comparison matrix, positioning insights, and strategic recommendations."
+- **Copywriter**: "Generate multiple creative copy variants for {scenario}, each with distinct positioning, tone, and call-to-action strategy."
+
+### 3. Kroki workflow (1–5 elementów — **przytnij lub rozszerz w zależności od złożoności**)
+
+Research Expert ma 5 kroków: **eksploruj → syntetyzuj → review → złóż plan → wykonaj**. Wymusza to "równoległy multi-agent + krzyżowy review + zatwierdzenie planu" — trzy warstwy rygoru, odpowiednie dla zadań wysokiego ryzyka/szerokiego zakresu, ale **przesadne dla lekkich**.
+
+- **Proste zadanie** (pojedyncze wyszukanie / mała poprawka): porzuć rozsyłanie multi-agent i review; po prostu "wyprodukuj odpowiedź" w jednym kroku.
+- **Zadanie średnio złożone**: zachowaj "eksploruj → syntetyzuj → review"; porzuć taniec ExitPlanMode; dostarcz wynik bezpośrednio.
+- **Zadanie złożone, kosztowne** (duża refaktoryzacja, porównanie wielu opcji, badania międzydziedzinowe): zachowaj wszystkie 5 kroków, ewentualnie dodaj krok "modelu ryzyka" lub "macierzy porównania opcji".
+
+### 4. Podrole w Kroku 1 (**dostosuj do swojej dziedziny**)
+
+Research Expert wymienia 6 potencjalnych ról (zwiadowca branżowy, badacz akademicki, syntetyzator + fact-checker, analityk konkurencji, producent demo, slot rozszerzalności). **Przepisz tę listę pod swój scenariusz**:
+
+- **Pisanie**: "zbieracz źródeł + analityk stylu + fact-checker"
+- **Analiza danych**: "agent czyszczenia danych + agent modelowania statystycznego + agent wizualizacji"
+- **Audyt kodu**: "agent analizy statycznej + audytor łańcucha zależności + threat modeler"
+
+### 5. Lista końcowych deliverables (**dostosuj do realnych potrzeb**)
+
+> Your final plan must include the following elements: ...
+
+Oryginalny szablon wymienia 6 elementów "planu wdrożenia". Twój deliverable może być czymś zupełnie innym:
+
+- **Raport badawczy** → "Executive summary / Methodology / Key findings / Limitations / Action recommendations"
+- **Raport z review** → "Issue list / Severity rating / Fix suggestions / Before-after examples"
+- **Macierz porównawcza** → "Dimension definitions / Scoring rubric / Conclusions / Recommendation rationale"
+
+---
+
+## Wskazówki dla autorów (TL;DR)
+
+1. **Zachowaj wrapper**: linia `<system-reminder>` + `[SCOPED INSTRUCTION]` jest dodawana przez cc-viewer — nie powtarzaj.
+2. **Przepisz zdanie otwierające**: określ rolę, cel i format wyjścia w jednej linii.
+3. **Elastycznie kształtuj workflow**: 1–2 kroki dla lekkich zadań, pełna pętla 5-krokowa tylko dla złożonych.
+4. **Przepisz podrole z Kroku 1**: domyślne (artykuły akademickie / konkurenci / demo) prawdopodobnie nie są tym, czego chcesz.
+5. **Końcowa "lista deliverables" to twój próg jakości**: rozpisz strukturę wyjścia — Claude Code będzie ją ściśle przestrzegać.
+
+---
+
+## Przerobiony przykład: Competitive Analyst
+
+```
+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}".
+
+Instructions:
+1. Use the Agent tool to dispatch 3 parallel investigators:
+   - Market landscape agent: map the top 5–8 competitors with core positioning
+   - Feature matrix agent: compile a feature-by-feature comparison using
+     publicly available sources (webSearch)
+   - Pricing & GTM agent: analyze pricing models, distribution channels, and
+     go-to-market motions
+
+2. Synthesize the three streams into a unified competitive report.
+
+3. Dispatch one review agent to stress-test the report: challenge any
+   assumption lacking a cited source, flag outdated data (>12 months), and
+   propose one "non-obvious" insight.
+
+4. Deliver the final report with the following sections:
+   - TL;DR (3 bullets)
+   - Competitor positioning map
+   - Feature matrix (markdown table)
+   - Pricing & GTM table
+   - Top 3 strategic implications for our product
+   - Caveats & data gaps
+```
+
+W porównaniu z oryginalnym Research Expert: przycięte do 4 kroków, podrole zredukowane z 6 do 3, lista deliverables całkowicie przepisana jako "sekcje raportu".

package/concepts/pl/UltraPlan.md

@@ -53,3 +53,104 @@ Wieloagentowy przepływ pracy zaprojektowany dla zadań badawczych i analityczny
 4. Synteza wszystkich odkryć w kompleksowy plan implementacji
 5. Wysłanie wielu agentów recenzentów do zbadania planu z różnych ról i perspektyw
 6. Realizacja planu po zatwierdzeniu
+
+---
+
+## Raw Templates
+
+Below are the two raw prompt templates UltraPlan actually sends to Claude Code (see `src/utils/ultraplanTemplates.js`):
+
+### Code Expert (codeExpert)
+
+<textarea readonly><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.
+
+Pre-requisite: Use `AskUserQuestion` to clarify user intent whenever the request is ambiguous (target element, interaction style, scope of platforms, etc.). Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate a highly detailed implementation plan.
+
+Instructions:
+1. Use the `Agent` tool to spawn parallel agents that simultaneously explore different aspects of the codebase:
+- If necessary, assign a preliminary researcher to use the `webSearch` tool to first investigate cutting-edge solutions in the relevant industry domain;
+- One agent responsible for understanding the relevant existing code and architecture;
+- One agent responsible for identifying all files that need to be modified;
+- One agent responsible for identifying potential risks, edge cases, and dependencies;
+- You may add other roles or deploy additional agents beyond the three listed above; the maximum number of concurrently dispatched agents is 5.
+
+2. Synthesize the findings from all agents into a detailed, step-by-step implementation plan.
+
+3. Use the `Agent` tool to spawn 2-3 review agents that examine the plan from different perspectives, checking for missing steps, potential risks, or corresponding mitigation strategies.
+
+4. Integrate the feedback gathered during the review process, then call `ExitPlanMode` to submit your final plan.
+
+5. Once `ExitPlanMode` returns a result:
+- If approved: proceed to execute the plan within this session.
+- If rejected: revise the plan based on the feedback provided and call `ExitPlanMode` again.
+- If an error occurs (including receiving a "Not in Plan Mode" message): do **not** follow the suggestions provided in the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the implementation strategy;
+- An ordered list of files to be created or modified, with precise details of the required changes for each file;
+- A step-by-step execution sequence;
+- Testing and validation procedures;
+- Potential risks and their corresponding mitigation strategies;
+
+6. After the final plan has been successfully executed:
+First run `git diff --quiet && git diff --cached --quiet` (or equivalent) to detect whether the working tree actually has non-trivial changes; if there are no real changes (or only whitespace/comment-only edits), skip the UltraReview step.
+Otherwise, if the project is managed with Git:
+Initiate a team (`TeamCreate`), dynamically allocating the number of teammates based on task complexity (5 is recommended);
+Task: Conduct a Code Review of the current git changes from multiple perspectives;
+Pre-requisites:
+- The git repository may be located in a subdirectory of the current directory; prefer `git rev-parse --show-toplevel` (fall back to recursive lookup) before proceeding;
+- In the case of multiple repositories, tasks may be executed separately;
+The team's goal is to analyze the current Git change log and validate each modification from different perspectives, specifically including:
+- Whether requirements/objectives have been met and functionality is complete;
+- Whether newly added code introduces side effects, breaks existing functionality, or poses potential risks;
+- Code quality: naming, readability, complexity, technical debt, maintainability;
+- Testing and documentation: whether there is adequate test coverage, and whether critical logic has necessary comments or documentation;
+- Dependencies and compatibility: whether new dependencies or version compatibility issues have been introduced;
+Workflow:
+- Each teammate, according to their own role, covers the review dimensions one by one and independently outputs a report;
+- After consolidating the reports, perform a cross-review to identify conflicts or shared concerns;
+- Distill specific, actionable modification suggestions and annotate them with priority levels (P0/P1/P2/P3);
+- Upon completion, adopt P0 items, and selectively adopt P1 items when they are concrete and low-risk; defer P2/P3 to backlog;
+- After execution is complete, close the team (`TeamDelete`);
+</system-reminder></textarea>
+
+### Research Expert (researchExpert)
+
+<textarea readonly><system-reminder>
+[SCOPED INSTRUCTION] The following instructions are intended for the next 1–3 interactions. Once the task is complete, these instructions should be gradually deprioritized and no longer influence subsequent interactions.
+
+Pre-requisite: Use `AskUserQuestion` to clarify the research scope, target audience, and deliverable format whenever the user's intent is ambiguous. Skip only if the intent is unambiguous.
+
+Leverage a multi-agent exploration mechanism to formulate an exceptionally detailed implementation plan.
+
+Instructions:
+1. Utilize the Agent tool to spawn parallel agents that simultaneously explore various facets of the requirements:
+- If necessary, deploy a preliminary investigator to conduct an initial survey of industry-specific solutions using `webSearch`;
+- If necessary, deploy a specialized investigator to research authoritative sources—such as academic papers, news articles, and research reports—using `webSearch`;
+- Assign an agent to synthesize the target solution, while simultaneously verifying the rigor and credibility of the gathered papers, news, and research reports;
+- If necessary, assign an agent to analyze competitor data to provide supplementary analytical perspectives;
+- If necessary, assign an agent to handle the implementation of a product demo (generating outputs such as HTML, Markdown, etc.);
+- If the task is sufficiently complex, you may assign additional teammates to the roles defined above, or introduce other specialized roles; you are permitted to schedule up to 5 teammates concurrently.
+
+2. Synthesize the findings from the aforementioned agents into a comprehensive, step-by-step implementation plan.
+
+3. Utilize the Agent tool to spawn a set of parallel review agents; these agents shall scrutinize the plan from multiple roles and perspectives to identify any omitted steps and to propose reasonable additions or optimizations.
+
+4. Consolidate the feedback received from the review agents, then invoke `ExitPlanMode` to submit your final plan.
+
+5. Upon receiving the result from `ExitPlanMode`:
+- If Approved: Proceed to execute the plan within this current session.
+- If Rejected: Revise the plan based on the provided feedback, and then invoke `ExitPlanMode` once again.
+- If an Error Occurs (including the message "Not in Plan Mode"): Do *not* follow the suggestions provided by the error message; instead, prompt the user for further instructions.
+
+Your final plan must include the following elements:
+- A clear summary of the proposed implementation strategy;
+- An ordered list of files to be created or modified, specifying the exact changes required for each;
+- A step-by-step sequence for executing the implementation;
+- Identification of potential risks and corresponding mitigation strategies;
+- Creative ideation and suggestions for advanced enhancements;
+- If a product demo was generated, place the corresponding demo output in an appropriate location and notify the user.
+</system-reminder></textarea>