claude-code-orchestrator-kit 1.3.1 → 1.4.0

package/.claude/commands/speckit.analyze.md

@@ -1,5 +1,8 @@
 ---
 description: Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
+scripts:
+  sh: .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
+  ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
 ---
 
 ## User Input

package/.claude/commands/speckit.checklist.md

@@ -1,5 +1,8 @@
 ---
 description: Generate a custom checklist for the current feature based on user requirements.
+scripts:
+  sh: .specify/scripts/bash/check-prerequisites.sh --json
+  ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json
 ---
 
 ## Checklist Purpose: "Unit Tests for English"

package/.claude/commands/speckit.clarify.md

@@ -1,5 +1,12 @@
 ---
 description: Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
+handoffs:
+  - label: Build Technical Plan
+    agent: speckit.plan
+    prompt: Create a plan for the spec. I am building with...
+scripts:
+   sh: .specify/scripts/bash/check-prerequisites.sh --json --paths-only
+   ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json -PathsOnly
 ---
 
 ## User Input
@@ -166,7 +173,7 @@ Execution steps:
 
 Behavior rules:
 
-- If clarifications reveal complex unknowns, flag for research phase
+- If clarifications reveal complex unknowns, flag for research phase (create research prompts in `FEATURE_DIR/research/`)
 - If no meaningful ambiguities found (or all potential questions would be low-impact), respond: "No critical ambiguities detected worth formal clarification." and suggest proceeding.
 - If spec file missing, instruct user to run `/speckit.specify` first (do not create a new spec here).
 - Never exceed 5 total asked questions (clarification retries for a single question do not count as new questions).

package/.claude/commands/speckit.constitution.md

@@ -1,5 +1,9 @@
 ---
 description: Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync
+handoffs:
+  - label: Build Specification
+    agent: speckit.specify
+    prompt: Implement the feature specification based on the updated constitution. I want to build...
 ---
 
 ## User Input

package/.claude/commands/speckit.implement.md

@@ -1,5 +1,8 @@
 ---
 description: Execute the implementation plan by processing and executing all tasks defined in tasks.md
+scripts:
+  sh: .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
+  ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
 ---
 
 > **ORCHESTRATION REMINDER**: You are the orchestrator, not the implementer. Delegate all complex tasks to subagents with complete context. Gather full context before delegation (read code, search patterns, review docs, check commits). Verify results thoroughly (read files, run type-check). Re-delegate with corrections if validation fails. Execute directly only for trivial tasks (1-2 line fixes, imports, single npm install).

package/.claude/commands/speckit.plan.md

@@ -1,5 +1,19 @@
 ---
 description: Execute the implementation planning workflow using the plan template to generate design artifacts.
+handoffs:
+  - label: Create Tasks
+    agent: speckit.tasks
+    prompt: Break the plan into tasks
+    send: true
+  - label: Create Checklist
+    agent: speckit.checklist
+    prompt: Create a checklist for the following domain...
+scripts:
+  sh: .specify/scripts/bash/setup-plan.sh --json
+  ps: .specify/scripts/powershell/setup-plan.ps1 -Json
+agent_scripts:
+  sh: .specify/scripts/bash/update-agent-context.sh __AGENT__
+  ps: .specify/scripts/powershell/update-agent-context.ps1 -AgentType __AGENT__
 ---
 
 ## User Input
@@ -31,18 +45,19 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 ### Phase 0: Outline & Research
 
-**Research Considerations**:
-- If tech decisions unclear, classify as research task
-- Document research questions in plan with classification (simple/complex)
-- Simple research: Agent tools (Grep, Read, WebSearch, Context7, Supabase docs)
-- Complex research: Create prompt → deepresearch → incorporate
-
 1. **Extract unknowns from Technical Context** above:
    - For each NEEDS CLARIFICATION → research task
    - For each dependency → best practices task
    - For each integration → patterns task
 
-2. **Generate and dispatch research agents**:
+2. **Library-First Search** (MANDATORY before research):
+   - For each major component (>20 lines expected), search for existing libraries:
+     - WebSearch: "npm {functionality} library 2024" or "python {functionality} package"
+     - Context7: documentation for candidate libraries
+     - Check: weekly downloads >1000, commits in last 6 months, TypeScript/types support
+   - Document library decisions in research.md
+
+3. **Generate and dispatch research agents**:
 
    ```text
    For each unknown in Technical Context:
@@ -51,17 +66,17 @@ You **MUST** consider the user input before proceeding (if not empty).
      Task: "Find best practices for {tech} in {domain}"
    ```
 
-3. **Consolidate findings** in `research.md` using format:
+4. **Research Considerations**:
+   - **Simple research**: Questions solvable with available tools (Grep, Read, WebSearch, Context7) - resolve immediately
+   - **Complex research**: Requires deep investigation → create research prompt in `FEATURE_DIR/research/` for deepresearch tool
+
+5. **Consolidate findings** in `research.md` using format:
    - Decision: [what was chosen]
    - Rationale: [why chosen]
    - Alternatives considered: [what else evaluated]
+   - Library: [if applicable - name, version, why chosen over alternatives]
 
-4. **Library discovery** for each planned component:
-   - Search npm/pypi for existing solutions (WebSearch + Context7)
-   - Evaluate: maintenance status (commits last 6 months), weekly downloads >1000, TypeScript support
-   - Document in research.md: chosen libraries with rationale, or justification for custom implementation
-
-**Output**: research.md with all NEEDS CLARIFICATION resolved and library decisions documented
+**Output**: research.md with all NEEDS CLARIFICATION resolved, research/ with complex research prompts (if any)
 
 ### Phase 1: Design & Contracts
 
@@ -90,3 +105,4 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 - Use absolute paths
 - ERROR on gate failures or unresolved clarifications
+- Library-first: Always check for existing libraries before planning custom implementations

package/.claude/commands/speckit.specify.md

@@ -1,5 +1,16 @@
 ---
 description: Create or update the feature specification from a natural language feature description.
+handoffs:
+  - label: Build Technical Plan
+    agent: speckit.plan
+    prompt: Create a plan for the spec. I am building with...
+  - label: Clarify Spec Requirements
+    agent: speckit.clarify
+    prompt: Clarify specification requirements
+    send: true
+scripts:
+  sh: .specify/scripts/bash/create-new-feature.sh --json "{ARGS}"
+  ps: .specify/scripts/powershell/create-new-feature.ps1 -Json "{ARGS}"
 ---
 
 ## User Input
@@ -29,27 +40,28 @@ Given that feature description, do this:
      - "Fix payment processing timeout bug" → "fix-payment-timeout"
 
 2. **Check for existing branches before creating new one**:
-   
+
    a. First, fetch all remote branches to ensure we have the latest information:
+
       ```bash
       git fetch --all --prune
       ```
-   
+
    b. Find the highest feature number across all sources for the short-name:
       - Remote branches: `git ls-remote --heads origin | grep -E 'refs/heads/[0-9]+-<short-name>$'`
       - Local branches: `git branch | grep -E '^[* ]*[0-9]+-<short-name>$'`
       - Specs directories: Check for directories matching `specs/[0-9]+-<short-name>`
-   
+
    c. Determine the next available number:
       - Extract all numbers from all three sources
       - Find the highest number N
       - Use N+1 for the new branch number
-   
+
    d. Run the script `.specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS"` with the calculated number and short-name:
       - Pass `--number N+1` and `--short-name "your-short-name"` along with the feature description
-      - Bash example: `.specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS" --json --number 5 --short-name "user-auth" "Add user authentication"`
-      - PowerShell example: `.specify/scripts/bash/create-new-feature.sh --json "$ARGUMENTS" -Json -Number 5 -ShortName "user-auth" "Add user authentication"`
-   
+      - Bash example: `.specify/scripts/bash/create-new-feature.sh --json --number 5 --short-name "user-auth" "Add user authentication"`
+      - PowerShell example: `.specify/scripts/powershell/create-new-feature.ps1 -Json -Number 5 -ShortName "user-auth" "Add user authentication"`
+
    **IMPORTANT**:
    - Check all three sources (remote branches, local branches, specs directories) to find the highest number
    - Only match branches/directories with the exact short-name pattern
@@ -96,20 +108,20 @@ Given that feature description, do this:
 
       ```markdown
       # Specification Quality Checklist: [FEATURE NAME]
-      
+
       **Purpose**: Validate specification completeness and quality before proceeding to planning
       **Created**: [DATE]
       **Feature**: [Link to spec.md]
-      
+
       ## Content Quality
-      
+
       - [ ] No implementation details (languages, frameworks, APIs)
       - [ ] Focused on user value and business needs
       - [ ] Written for non-technical stakeholders
       - [ ] All mandatory sections completed
-      
+
       ## Requirement Completeness
-      
+
       - [ ] No [NEEDS CLARIFICATION] markers remain
       - [ ] Requirements are testable and unambiguous
       - [ ] Success criteria are measurable
@@ -118,16 +130,16 @@ Given that feature description, do this:
       - [ ] Edge cases are identified
       - [ ] Scope is clearly bounded
       - [ ] Dependencies and assumptions identified
-      
+
       ## Feature Readiness
-      
+
       - [ ] All functional requirements have clear acceptance criteria
       - [ ] User scenarios cover primary flows
       - [ ] Feature meets measurable outcomes defined in Success Criteria
       - [ ] No implementation details leak into specification
-      
+
       ## Notes
-      
+
       - Items marked incomplete require spec updates before `/speckit.clarify` or `/speckit.plan`
       ```
 
@@ -152,20 +164,20 @@ Given that feature description, do this:
 
            ```markdown
            ## Question [N]: [Topic]
-           
+
            **Context**: [Quote relevant spec section]
-           
+
            **What we need to know**: [Specific question from NEEDS CLARIFICATION marker]
-           
+
            **Suggested Answers**:
-           
+
            | Option | Answer | Implications |
            |--------|--------|--------------|
            | A      | [First suggested answer] | [What this means for the feature] |
            | B      | [Second suggested answer] | [What this means for the feature] |
            | C      | [Third suggested answer] | [What this means for the feature] |
            | Custom | Provide your own answer | [Explain how to provide custom input] |
-           
+
            **Your choice**: _[Wait for user response]_
            ```
 

package/.claude/commands/speckit.tasks.md

@@ -1,5 +1,17 @@
 ---
 description: Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
+handoffs:
+  - label: Analyze For Consistency
+    agent: speckit.analyze
+    prompt: Run a project analysis for consistency
+    send: true
+  - label: Implement Project
+    agent: speckit.implement
+    prompt: Start the implementation in phases
+    send: true
+scripts:
+  sh: .specify/scripts/bash/check-prerequisites.sh --json
+  ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json
 ---
 
 ## User Input
@@ -16,7 +28,7 @@ You **MUST** consider the user input before proceeding (if not empty).
 
 2. **Load design documents**: Read from FEATURE_DIR:
    - **Required**: plan.md (tech stack, libraries, structure), spec.md (user stories with priorities)
-   - **Optional**: data-model.md (entities), contracts/ (API endpoints), research.md (decisions), quickstart.md (test scenarios)
+   - **Optional**: data-model.md (entities), contracts/ (API endpoints), research.md (decisions), research/ (complex research), quickstart.md (test scenarios)
    - Note: Not all projects have all documents. Generate tasks based on what's available.
 
 3. **Execute task generation workflow**:
@@ -25,13 +37,15 @@ You **MUST** consider the user input before proceeding (if not empty).
    - If data-model.md exists: Extract entities and map to user stories
    - If contracts/ exists: Map endpoints to user stories
    - If research.md exists: Extract decisions for setup tasks
+   - If research/ exists: Identify complex research tasks that need resolution
    - Generate tasks organized by user story (see Task Generation Rules below)
    - Generate dependency graph showing user story completion order
    - Create parallel execution examples per user story
    - Validate task completeness (each user story has all needed tasks, independently testable)
 
-4. **Generate tasks.md**: Use `.specify.specify/templates/tasks-template.md` as structure, fill with:
+4. **Generate tasks.md**: Use `.specify/templates/tasks-template.md` as structure, fill with:
    - Correct feature name from plan.md
+   - Phase 0: Planning (executor assignment) - ALWAYS include
    - Phase 1: Setup tasks (project initialization)
    - Phase 2: Foundational tasks (blocking prerequisites for all user stories)
    - Phase 3+: One phase per user story (in priority order from spec.md)
@@ -94,7 +108,7 @@ Every task MUST strictly follow this format:
 4. **[Story] label**: REQUIRED for user story phase tasks only
    - Format: [US1], [US2], [US3], etc. (maps to user stories from spec.md)
    - Setup phase: NO story label
-   - Foundational phase: NO story label  
+   - Foundational phase: NO story label
    - User Story phases: MUST have story label
    - Polish phase: NO story label
 5. **Description**: Clear action with exact file path
@@ -137,6 +151,7 @@ Every task MUST strictly follow this format:
 
 ### Phase Structure
 
+- **Phase 0**: Planning (executor assignment, agent creation, research resolution)
 - **Phase 1**: Setup (project initialization)
 - **Phase 2**: Foundational (blocking prerequisites - MUST complete before user stories)
 - **Phase 3+**: User Stories in priority order (P1, P2, P3...)

package/.claude/commands/speckit.taskstoissues.md

@@ -0,0 +1,35 @@
+---
+description: Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
+tools: ['github/github-mcp-server/issue_write']
+scripts:
+  sh: .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks
+  ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks
+---
+
+## User Input
+
+```text
+$ARGUMENTS
+```
+
+You **MUST** consider the user input before proceeding (if not empty).
+
+## Outline
+
+1. Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` from repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").
+
+2. From the executed script, extract the path to **tasks**.
+
+3. Get the Git remote by running:
+
+```bash
+git config --get remote.origin.url
+```
+
+> [!CAUTION]
+> ONLY PROCEED TO NEXT STEPS IF THE REMOTE IS A GITHUB URL
+
+4. For each task in the list, use the GitHub MCP server to create a new issue in the repository that is representative of the Git remote.
+
+> [!CAUTION]
+> UNDER NO CIRCUMSTANCES EVER CREATE ISSUES IN REPOSITORIES THAT DO NOT MATCH THE REMOTE URL

package/.gitignore

@@ -108,6 +108,8 @@ $RECYCLE.BIN/
 *.backup
 *.bak
 *.old
+.claude/commands.backup.*/
+.specify.backup.*/
 
 # Archive files
 *.archive
@@ -126,3 +128,9 @@ articles/
 
 # Content agents (temporary/helper agents for writing)
 .claude/agents/content/
+
+# ===================================================================
+# Spec-Kit Temporary
+# ===================================================================
+# Original spec-kit clone (for comparison)
+/tmp/spec-kit-comparison/

package/docs/SPECKIT-GUIDE.md

@@ -0,0 +1,415 @@
+# Spec-Kit: Руководство по использованию
+
+> Версия: v0.0.90 + DeksdenFlow расширения
+
+Spec-Kit — это набор команд для **спецификационно-ориентированной разработки** (Spec-Driven Development). Позволяет структурированно описывать требования, планировать реализацию и выполнять задачи через агентов.
+
+---
+
+## Быстрый старт
+
+```bash
+# 1. Создать спецификацию фичи
+/speckit.specify Добавить систему аутентификации через OAuth2
+
+# 2. Уточнить требования (опционально)
+/speckit.clarify
+
+# 3. Создать технический план
+/speckit.plan
+
+# 4. Сгенерировать задачи
+/speckit.tasks
+
+# 5. Проверить консистентность (опционально)
+/speckit.analyze
+
+# 6. Реализовать
+/speckit.implement
+```
+
+---
+
+## Команды
+
+### `/speckit.specify` — Создание спецификации
+
+**Что делает**: Создаёт ветку, директорию и файл `spec.md` с требованиями.
+
+**Использование**:
+```bash
+/speckit.specify Описание фичи на естественном языке
+```
+
+**Пример**:
+```bash
+/speckit.specify Добавить дашборд аналитики с графиками посещаемости
+```
+
+**Результат**:
+- Создаётся ветка `1-analytics-dashboard`
+- Создаётся `specs/1-analytics-dashboard/spec.md`
+- Создаётся чеклист `specs/1-analytics-dashboard/checklists/requirements.md`
+
+**Особенности**:
+- Автоматически генерирует короткое имя ветки
+- Проверяет существующие ветки для уникального номера
+- Максимум 3 маркера `[NEEDS CLARIFICATION]`
+- Задаёт уточняющие вопросы если нужно
+
+---
+
+### `/speckit.clarify` — Уточнение требований
+
+**Что делает**: Анализирует спецификацию на неясности и задаёт до 5 вопросов.
+
+**Использование**:
+```bash
+/speckit.clarify
+/speckit.clarify область безопасности
+```
+
+**Когда использовать**:
+- Перед `/speckit.plan` если spec.md содержит неясности
+- Для глубокой проработки конкретной области
+
+**Особенности**:
+- Анализирует по 11 категориям (Scope, Data Model, UX, Security и др.)
+- Предлагает рекомендованные ответы
+- Обновляет spec.md после каждого ответа
+- Сложные вопросы помечает для research phase
+
+---
+
+### `/speckit.plan` — Техническое планирование
+
+**Что делает**: Создаёт технический план с архитектурой, моделями данных и контрактами.
+
+**Использование**:
+```bash
+/speckit.plan
+/speckit.plan Next.js 15, Supabase, tRPC
+```
+
+**Результат** (в директории фичи):
+- `plan.md` — основной план
+- `research.md` — результаты исследований
+- `research/` — сложные исследования (если есть)
+- `data-model.md` — модели данных
+- `contracts/` — API контракты
+- `quickstart.md` — быстрый старт
+
+**Особенности**:
+- **Library-First**: Сначала ищет существующие библиотеки
+- Проверяет соответствие Constitution
+- Классифицирует research: simple (решается сразу) / complex (в research/)
+
+---
+
+### `/speckit.tasks` — Генерация задач
+
+**Что делает**: Создаёт `tasks.md` с пошаговым планом реализации.
+
+**Использование**:
+```bash
+/speckit.tasks
+```
+
+**Структура tasks.md**:
+```
+Phase 0: Planning (назначение executor'ов)
+Phase 1: Setup (инициализация проекта)
+Phase 2: Foundational (базовая инфраструктура)
+Phase 3+: User Stories (по приоритетам P1, P2, P3...)
+Phase N: Polish (финальные улучшения)
+```
+
+**Формат задач**:
+```markdown
+- [ ] T001 Create project structure per implementation plan
+- [ ] T005 [P] [US1] Create User model in src/models/user.py
+```
+
+- `T001` — ID задачи
+- `[P]` — можно выполнять параллельно
+- `[US1]` — относится к User Story 1
+
+---
+
+### `/speckit.analyze` — Анализ консистентности
+
+**Что делает**: Проверяет spec.md, plan.md и tasks.md на противоречия.
+
+**Использование**:
+```bash
+/speckit.analyze
+```
+
+**Что проверяет**:
+- Дублирование требований
+- Неясные формулировки
+- Покрытие требований задачами
+- Соответствие Constitution
+- Терминологическую консистентность
+
+**Результат**: Отчёт с severity (CRITICAL/HIGH/MEDIUM/LOW) и рекомендациями.
+
+---
+
+### `/speckit.implement` — Реализация
+
+**Что делает**: Выполняет задачи из tasks.md через агентов.
+
+**Использование**:
+```bash
+/speckit.implement
+/speckit.implement начать с Phase 2
+```
+
+**Workflow**:
+
+```
+┌─────────────────────────────────────────────────────────┐
+│  PLANNING PHASE (один раз в начале)                    │
+├─────────────────────────────────────────────────────────┤
+│  P001: Анализ задач → какие агенты нужны               │
+│  P002: Создание агентов через meta-agent-v3            │
+│  P003: Назначение executor'ов для каждой задачи        │
+│  P004: Решение research задач                          │
+└─────────────────────────────────────────────────────────┘
+                          ↓
+┌─────────────────────────────────────────────────────────┐
+│  EXECUTION (для каждой задачи)                         │
+├─────────────────────────────────────────────────────────┤
+│  1. TodoWrite: in_progress                             │
+│  2. Gather context (код, паттерны, документация)       │
+│  3. Library search (если >20 строк нового кода)        │
+│  4. Context7: получить docs библиотек                  │
+│  5. Execute: делегировать агенту или выполнить         │
+│  6. Verify: прочитать файлы, type-check                │
+│  7. Accept/Reject: повторить если ошибка               │
+│  8. TodoWrite: completed                               │
+│  9. Mark [X] в tasks.md + artifacts                    │
+│  10. /push patch                                       │
+└─────────────────────────────────────────────────────────┘
+```
+
+**Ключевые правила**:
+- **1 Task = 1 Agent** — атомарность
+- **Parallel = N calls in single message** — параллельные задачи запускаются одним сообщением
+- **Library-first** — сначала ищем библиотеку, потом пишем код
+- **Commit after each task** — `/push patch` после каждой задачи
+
+---
+
+### `/speckit.checklist` — Создание чеклиста
+
+**Что делает**: Генерирует чеклист для проверки качества требований.
+
+**Использование**:
+```bash
+/speckit.checklist ux
+/speckit.checklist security
+/speckit.checklist api
+```
+
+**Важно**: Чеклисты проверяют **качество требований**, не реализацию!
+
+```markdown
+# Правильно (проверка требований):
+- [ ] Are error handling requirements defined for all API failure modes?
+
+# Неправильно (проверка реализации):
+- [ ] Verify API returns 200 on success
+```
+
+---
+
+### `/speckit.constitution` — Управление принципами
+
+**Что делает**: Создаёт/обновляет файл принципов проекта.
+
+**Использование**:
+```bash
+/speckit.constitution
+/speckit.constitution добавить принцип "No ORM, raw SQL only"
+```
+
+**Файл**: `.specify/memory/constitution.md`
+
+Constitution определяет:
+- Обязательные технологии
+- Запрещённые подходы
+- Quality gates
+- Архитектурные ограничения
+
+---
+
+### `/speckit.taskstoissues` — Экспорт в GitHub Issues
+
+**Что делает**: Конвертирует tasks.md в GitHub Issues.
+
+**Использование**:
+```bash
+/speckit.taskstoissues
+```
+
+**Требования**:
+- GitHub MCP server должен быть настроен
+- Remote должен быть GitHub URL
+
+---
+
+## Структура проекта
+
+```
+project/
+├── .specify/
+│   ├── memory/
+│   │   └── constitution.md      # Принципы проекта
+│   ├── templates/
+│   │   ├── spec-template.md
+│   │   ├── plan-template.md
+│   │   ├── tasks-template.md
+│   │   └── checklist-template.md
+│   └── scripts/bash/
+│       ├── create-new-feature.sh
+│       ├── check-prerequisites.sh
+│       ├── setup-plan.sh
+│       └── update-agent-context.sh
+├── .claude/commands/
+│   ├── speckit.specify.md
+│   ├── speckit.clarify.md
+│   ├── speckit.plan.md
+│   ├── speckit.tasks.md
+│   ├── speckit.analyze.md
+│   ├── speckit.implement.md
+│   ├── speckit.checklist.md
+│   ├── speckit.constitution.md
+│   └── speckit.taskstoissues.md
+└── specs/
+    └── 1-feature-name/
+        ├── spec.md
+        ├── plan.md
+        ├── research.md
+        ├── research/           # Сложные исследования
+        ├── data-model.md
+        ├── contracts/
+        ├── quickstart.md
+        ├── tasks.md
+        └── checklists/
+            └── requirements.md
+```
+
+---
+
+## Phase 0: Planning — Детали
+
+Phase 0 — критическая фаза перед реализацией:
+
+| Шаг | Действие | Результат |
+|-----|----------|-----------|
+| P001 | Анализ задач | Список необходимых агентов |
+| P002 | Создание агентов | `.claude/agents/` + restart |
+| P003 | Назначение executor'ов | Аннотации `[EXECUTOR: name]` |
+| P004 | Research resolution | Решённые вопросы или prompts |
+
+**Executor'ы**:
+- `MAIN` — только тривиальные задачи (1-2 строки)
+- `existing-agent` — если 100% совпадение возможностей
+- `new-agent` — создаётся через meta-agent-v3
+
+**Пример аннотированной задачи**:
+```markdown
+- [ ] T012 [P] [US1] [EXECUTOR: fullstack-nextjs-specialist] [PARALLEL-GROUP-1]
+      Create User model in src/models/user.ts
+```
+
+---
+
+## Интеграция с библиотеками
+
+Перед написанием кода >20 строк:
+
+1. **WebSearch**: `npm {functionality} library 2025`
+2. **Context7**: Получить документацию
+3. **Проверить**: downloads >1000/week, commits <6 months, TypeScript support
+4. **Решить**: использовать библиотеку или писать своё
+
+```bash
+# В implement фазе автоматически:
+mcp__context7__resolve-library-id → получить ID
+mcp__context7__get-library-docs → получить docs по теме
+```
+
+---
+
+## DeksdenFlow (Session Management)
+
+При длинных сессиях `/speckit.implement`:
+
+- **resume-session** — проверка существующей сессии
+- **save-session-context** — сохранение после каждой фазы
+- **load-project-context** — загрузка структуры проекта
+
+Позволяет:
+- Возобновить работу после перезапуска
+- Не терять контекст при ошибках
+- Логировать решения в session-log.md
+
+---
+
+## Типичные сценарии
+
+### Новая фича с нуля
+```bash
+/speckit.specify Добавить систему уведомлений
+/speckit.clarify
+/speckit.plan Next.js, Supabase
+/speckit.tasks
+/speckit.implement
+```
+
+### Быстрый прототип (skip clarify)
+```bash
+/speckit.specify Простая форма обратной связи
+/speckit.plan
+/speckit.tasks
+/speckit.implement
+```
+
+### Только планирование (без реализации)
+```bash
+/speckit.specify Миграция на новую архитектуру
+/speckit.clarify
+/speckit.plan
+/speckit.tasks
+/speckit.analyze
+# Передать tasks.md команде
+```
+
+### Проверка существующей спеки
+```bash
+/speckit.analyze
+/speckit.checklist security
+/speckit.checklist ux
+```
+
+---
+
+## Troubleshooting
+
+| Проблема | Решение |
+|----------|---------|
+| `No feature branch` | Сначала запустите `/speckit.specify` |
+| `spec.md not found` | Переключитесь на feature ветку |
+| `tasks.md missing` | Запустите `/speckit.tasks` |
+| Агент не найден | После P002 перезапустите Claude Code |
+| Library not found | Проверьте Context7 MCP connection |
+
+---
+
+## Ссылки
+
+- [GitHub Spec-Kit](https://github.com/github/spec-kit)
+- [Spec-Driven Development Guide](https://github.blog/ai-and-ml/generative-ai/spec-driven-development-with-ai-get-started-with-a-new-open-source-toolkit/)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-code-orchestrator-kit",
-  "version": "1.3.1",
+  "version": "1.4.0",
   "description": "Complete automation and orchestration system for Claude Code with 33+ AI agents, quality gates, health monitoring, and workflow automation",
   "main": "index.js",
   "type": "module",