context-first-cli 2.3.1 → 2.3.4

package/dist/templates/commands/en/products/collect.md

@@ -18,59 +18,11 @@ You are a product specialist responsible for collecting and documenting new idea
 
 ---
 
-## 📋 Project Setup
+## Configuration
 
-**⚠️ IMPORTANT: Always read the project configuration files BEFORE running this command!**
+Read `context-manifest.json` and `ai.properties.md` from the orchestrator to get repositories, base_path, and task_management_system.
 
-### Mandatory Files
-
-1. **`context-manifest.json`** (orchestrator root)
-   - List of project repositories
-   - Roles of each repository (metaspecs, application, etc.)
-   - URLs and dependencies between repositories
-
-2. **`ai.properties.md`** (orchestrator root)
-   - Project settings (`project_name`, `base_path`)
-   - Task management system (`task_management_system`)
-   - Credentials and specific configurations
-
-### How to Read
-
-```bash
-# 1. Read context-manifest.json
-cat context-manifest.json
-
-# 2. Read ai.properties.md
-cat ai.properties.md
-```
-
-### Essential Information
-
-After reading the files, you will have:
-- ✅ Complete list of project repositories
-- ✅ Location of the metaspecs repository
-- ✅ Base path to locate repositories
-- ✅ Configured task management system
-- ✅ Project-specific configurations
-
-**🛑 DO NOT proceed without reading these files!** They contain critical information for the correct execution of the command.
-
-## Project Context
-
-Before starting, load the context by consulting:
-
-1. **Automatically locate MetaSpecs**:
-   - Read `context-manifest.json` from the orchestrator
-   - Find the repository with `"role": "metaspecs"`
-   - Read `ai.properties.md` to get the `base_path`
-   - The metaspecs are located at: `{base_path}/{metaspecs-repo-id}/`
-   - Read the `index.md` files as reference
-
-2. **Project structure**:
-   - `context-manifest.json` - List of repositories and their roles
-   - `README.md` of involved repositories
-
-## Your Goal
+## Objective
 
 Understand the user's request and capture it as an issue in the task manager (via MCP).
 
@@ -134,7 +86,7 @@ Just ensure the idea is **adequately understood**.
    - Example split:
      ```
      Original Issue: "Complete payment system"
-     
+
      Suggested Split:
      - FIN-101: Payment gateway integration (backend)
      - FIN-102: Checkout interface (frontend)
@@ -155,22 +107,22 @@ Just ensure the idea is **adequately understood**.
 5. **Issue Saving**
 
    **PRIORITY 1: Use MCP (Model Context Protocol)**
-   
+
    Check if MCP is configured for the task manager:
    - Read `ai.properties.md` from the orchestrator to identify the `task_management_system`
    - If `task_management_system=jira`: Use Jira MCP to create the issue
    - If `task_management_system=linear`: Use Linear MCP to create the issue
    - If `task_management_system=github`: Use GitHub MCP to create the issue
    - If `task_management_system=azure`: Use Azure Boards MCP to create the issue
-   
+
    **When using MCP:**
    - Create the issue directly in the task manager
    - Obtain the created issue ID (e.g., FIN-123, LIN-456)
    - Inform the user: "✅ Issue [ID] created in [task manager]"
    - **DO NOT create a .md file**
-   
+
    **FALLBACK: Create .md file only if MCP fails**
-   
+
    If MCP is not available or fails:
    - Create a file in `./.sessions/<ISSUE-ID>/collect.md`
    - Use manual ID format: `LOCAL-001`, `LOCAL-002`, etc.
@@ -215,4 +167,4 @@ After approval and saving the issue:
 /refine [ISSUE-ID]
 ```
 
-This command will transform the collected issue into refined and validated requirements.
+This command will transform the collected issue into refined and validated requirements.

package/dist/templates/commands/en/products/refine.md

@@ -17,43 +17,9 @@ You are a product expert responsible for helping to refine requirements for the
 
 ---
 
-## 📋 Project Setup
-
-**⚠️ IMPORTANT: Always read the project configuration files BEFORE running this command!**
-
-### Mandatory Files
-
-1. **`context-manifest.json`** (orchestrator root)
-   - List of project repositories
-   - Roles of each repository (metaspecs, application, etc.)
-   - URLs and dependencies between repositories
-
-2. **`ai.properties.md`** (orchestrator root)
-   - Project settings (`project_name`, `base_path`)
-   - Task management system (`task_management_system`)
-   - Credentials and specific configurations
-
-### How to Read
-
-```bash
-# 1. Read context-manifest.json
-cat context-manifest.json
-
-# 2. Read ai.properties.md
-cat ai.properties.md
-```
-
-### Essential Information
-
-After reading the files, you will have:
-- ✅ Complete list of project repositories
-- ✅ Location of the metaspecs repository
-- ✅ Base path to locate repositories
-- ✅ Configured task management system
-- ✅ Project-specific configurations
-
-**🛑 DO NOT proceed without reading these files!** They contain critical information for correct command execution.
+## Configuration
 
+Read `context-manifest.json` and `ai.properties.md` from the orchestrator to get repositories, base_path, and task_management_system.
 
 ## Objective
 
@@ -125,7 +91,7 @@ Once you have gathered sufficient information and validated against metaspecs, p
 - Example split:
   ```
   Original Issue: "Multi-channel notification system"
-  
+
   Suggested Split:
   - FIN-201: Queue and worker infrastructure (backend)
   - FIN-202: Email notifications (backend + templates)
@@ -262,4 +228,4 @@ Once the user approves, save the requirements:
 
 **Example**: `/spec FIN-3`
 
-This command will create a PRD (Product Requirements Document) complete based on the refined requirements, detailing features, user stories, acceptance criteria, and final validations.
+This command will create a PRD (Product Requirements Document) complete based on the refined requirements, detailing features, user stories, acceptance criteria, and final validations.

package/dist/templates/commands/en/products/spec.md

@@ -17,42 +17,9 @@ This command creates the complete specification (Product Requirements Document)
 
 ---
 
-## 📋 Project Configuration
+## Configuration
 
-**⚠️ IMPORTANT: Always read the project configuration files BEFORE running this command!**
-
-### Mandatory Files
-
-1. **`context-manifest.json`** (orchestrator root)
-   - List of project repositories
-   - Roles of each repository (metaspecs, application, etc.)
-   - URLs and dependencies between repositories
-
-2. **`ai.properties.md`** (orchestrator root)
-   - Project settings (`project_name`, `base_path`)
-   - Task management system (`task_management_system`)
-   - Credentials and specific configurations
-
-### How to Read
-
-```bash
-# 1. Read context-manifest.json
-cat context-manifest.json
-
-# 2. Read ai.properties.md
-cat ai.properties.md
-```
-
-### Essential Information
-
-After reading the files, you will have:
-- ✅ Complete list of project repositories
-- ✅ Location of the metaspecs repository
-- ✅ Base path to locate repositories
-- ✅ Configured task management system
-- ✅ Project-specific configurations
-
-**🛑 DO NOT proceed without reading these files!** They contain critical information for correct command execution.
+Read `context-manifest.json` and `ai.properties.md` from the orchestrator to get repositories, base_path, and task_management_system.
 
 ## 📋 Prerequisites
 
@@ -301,4 +268,4 @@ After PRD approval:
 /start
 ```
 
-This command will start feature development.
+This command will start feature development.

package/dist/templates/commands/en/quality/metrics.md

@@ -11,42 +11,9 @@ Measure and document the quality of the implementation through objective metrics
 - Performance
 - Compliance with standards
 
-## 📋 Project Configuration
+## Configuration
 
-**⚠️ IMPORTANT: Always read the project configuration files BEFORE running this command!**
-
-### Required Files
-
-1. **`context-manifest.json`** (orchestrator root)
-   - List of project repositories
-   - Roles of each repository (metaspecs, application, etc.)
-   - URLs and dependencies between repositories
-
-2. **`ai.properties.md`** (orchestrator root)
-   - Project settings (`project_name`, `base_path`)
-   - Task management system (`task_management_system`)
-   - Credentials and specific configurations
-
-### How to Read
-
-```bash
-# 1. Read context-manifest.json
-cat context-manifest.json
-
-# 2. Read ai.properties.md
-cat ai.properties.md
-```
-
-### Essential Information
-
-After reading the files, you will have:
-- ✅ Complete list of project repositories
-- ✅ Location of the metaspecs repository
-- ✅ Base path to locate repositories
-- ✅ Configured task management system
-- ✅ Project-specific configurations
-
-**🛑 DO NOT proceed without reading these files!** They contain critical information for the correct execution of the command.
+Read `context-manifest.json` and `ai.properties.md` from the orchestrator to get repositories, base_path, and task_management_system.
 
 ## 📋 Prerequisites
 
@@ -296,4 +263,4 @@ After running this command, you will have:
 - Comparison with baseline and goals
 - Identification of quality issues
 - Recommendations for actions
-- Objective basis for merge approval
+- Objective basis for merge approval

package/dist/templates/commands/en/quality/observe.md

@@ -12,43 +12,9 @@ Create a structured record of technical and product decisions, ensuring:
 
 **IMPORTANT**: This command DOES NOT generate new decisions. It only RECORDS decisions that have already been made during the development process.
 
-## 📋 Project Configuration
-
-**⚠️ IMPORTANT: Always read the project configuration files BEFORE running this command!**
-
-### Required Files
-
-1. **`context-manifest.json`** (orchestrator root)
-   - List of project repositories
-   - Roles of each repository (metaspecs, application, etc.)
-   - URLs and dependencies between repositories
-
-2. **`ai.properties.md`** (orchestrator root)
-   - Project settings (`project_name`, `base_path`)
-   - Task management system (`task_management_system`)
-   - Credentials and specific configurations
-
-### How to Read
-
-```bash
-# 1. Read context-manifest.json
-cat context-manifest.json
-
-# 2. Read ai.properties.md
-cat ai.properties.md
-```
-
-### Essential Information
-
-After reading the files, you will have:
-- ✅ Complete list of project repositories
-- ✅ Location of the metaspecs repository
-- ✅ Base path to locate repositories
-- ✅ Configured task management system
-- ✅ Project-specific configurations
-
-**🛑 DO NOT proceed without reading these files!** They contain critical information for the correct execution of the command.
+## Configuration
 
+Read `context-manifest.json` and `ai.properties.md` from the orchestrator to get repositories, base_path, and task_management_system.
 
 ## 📋 Prerequisites
 
@@ -203,4 +169,4 @@ After running this command, you will have:
 - Complete decision log in `./.sessions/<ISSUE-ID>/decisions.md`
 - Traceability of every choice made
 - Documentation for future reference
-- Basis for ADRs (if decisions are architectural)
+- Basis for ADRs (if decisions are architectural)

package/dist/templates/commands/en/warm-up.md

@@ -1,122 +1,59 @@
 # Warm-up - Context Loading
 
-This command prepares the environment by loading the full context of the current project and workspace.
+Prepares the environment by loading optimized project context.
 
-## 1. Identify Current Workspace
+## 1. Load Configuration
 
-Check if you are inside a workspace created by `context-cli`:
+Read the orchestrator files:
+- **`context-manifest.json`** - Repositories and roles
+- **`ai.properties.md`** - base_path, task_management_system
 
-```bash
-# Check if you are in a workspace directory
-pwd
-# The workspace is usually located at ~/workspaces/<ISSUE-ID>/
-```
-
-If you are not in a workspace, ask the user which workspace to use or if a new one should be created with `feature:start`.
-
-## 📋 Project Configuration
+## 2. Load Compact Context (OPTIMIZED)
 
-**⚠️ IMPORTANT: Always read the project configuration files BEFORE running this command!**
+**IMPORTANT**: Use PROGRESSIVE loading to save context window.
 
-### Required Files
+### Required (warm-up)
 
-1. **`context-manifest.json`** (root of the orchestrator)
-   - List of project repositories
-   - Roles of each repository (metaspecs, application, etc.)
-   - URLs and dependencies between repositories
+Locate metaspecs via `context-manifest.json` (role: "specs-provider"):
 
-2. **`ai.properties.md`** (root of the orchestrator)
-   - Project settings (`project_name`, `base_path`)
-   - Task management system (`task_management_system`)
-   - Credentials and specific configurations
-
-### How to Read
-
-```bash
-# 1. Read context-manifest.json
-cat context-manifest.json
-
-# 2. Read ai.properties.md
-cat ai.properties.md
+```
+{base_path}/{metaspecs-id}/specs/_meta/WARM_UP_CONTEXT.md  (~100 lines)
 ```
 
-### Essential Information
-
-After reading the files, you will have:
-- ✅ Complete list of project repositories
-- ✅ Location of the metaspecs repository
-- ✅ Base path to locate repositories
-- ✅ Configured task management system
-- ✅ Project-specific configurations
-
-**🛑 DO NOT proceed without reading these files!** They contain critical information for the correct execution of the command.
-
-## 2. Load Project Configuration
-
-You are already in the project orchestrator (root of the current repository).
-
-1. **Verify you are at the orchestrator root**: `pwd` should show the orchestrator directory
-2. **Read the `context-manifest.json` file** at the orchestrator root
-3. **Read the `ai.properties.md` file** to obtain local configurations (base_path, etc.)
-
-## 3. Load Project Manifest
-
-Read the `context-manifest.json` from the orchestrator to understand:
-- Complete list of ecosystem repositories
-- URL of the MetaSpecs repository
-- Dependencies between repositories
-- Roles of each repository (application, library, service, specs-provider)
-
-## 4. Load MetaSpecs
-
-The MetaSpecs repository is **separate** and defined in `context-manifest.json` with `role: "metaspecs"`.
-
-**Locate the metaspecs repository:**
-
-1. Read `context-manifest.json` and find the repository with `role: "metaspecs"`
-2. Obtain the `id` of that repository (e.g., "my-project-metaspecs")
-3. Read `ai.properties.md` to get the `base_path`
-4. The metaspecs repository is located at: `{base_path}/{metaspecs-id}/`
+This file contains ALL essentials:
+- Technology stack
+- Context hierarchy
+- 5 critical rules
+- Minimal code patterns
+- On-demand loading table
 
-**Always read the index files first:**
+### On Demand (DO NOT load during warm-up)
 
-1. **`README.md`** - Project overview and documentation structure
-2. **`index.md`** (in root or subfolders) - Index of available specifications
+| Need | Document |
+|------|----------|
+| Generate code | `CLAUDE.meta.md` |
+| Architecture | `ARCHITECTURE.md` |
+| Specific feature | `features/{FEATURE}.md` |
+| Complete anti-patterns | `ANTI_PATTERNS.md` |
 
-**Use the indexes as a reference** to navigate to the specific specifications you need. Do not assume specific files exist — always consult the indexes first.
+## 3. Verify Repositories
 
-## 5. Load Current Session (if any)
+For each repository in `context-manifest.json`:
+- Verify existence at `{base_path}/{repo-id}/`
+- **DO NOT** read README.md now (on demand)
 
-Check if there is a saved session for this workspace:
+## 4. Verify Session (if exists)
 
 ```bash
-# Look for session in the orchestrator
 ls -la .sessions/<ISSUE-ID>/ 2>/dev/null
 ```
 
-If it exists, read the session files to recover the context of the last execution.
-
-## 6. Repository Context
-
-For each repository present in the workspace, read:
-- `README.md` - Purpose and overview of the repository
-- Main configuration file (`package.json`, `pom.xml`, `requirements.txt`, etc.)
-
-## 7. Smart Navigation
-
-- **Code**: Use search tools (glob, grep) to locate relevant files
-- **Documentation**: Use MetaSpecs indexes as reference
-- **Wait for Instructions**: DO NOT read other files now. Wait for the next command.
-
-## 8. Jidoka Principle (Stop Upon Detecting Problems)
+## 5. Jidoka Principle
 
-If you detect misalignment, conflicts, or problems:
-1. 🛑 **STOP** immediately
-2. 📝 **DOCUMENT** the problem found
-3. 💬 **ALERT** the user before proceeding
+If problems detected: **STOP**, document, alert the user.
 
 ---
 
-**Provided arguments**: #$ARGUMENTS
+**Arguments**: #$ARGUMENTS
 
-**Status**: Context loaded. Awaiting next command.
+**Status**: Context loaded. Awaiting next command.

package/dist/templates/commands/es/warm-up.md

@@ -1,123 +1,59 @@
 # Calentamiento - Carga de Contexto
 
-Este comando prepara el entorno cargando el contexto completo del proyecto y del workspace actual.
+Prepara el entorno cargando el contexto optimizado del proyecto.
 
-## 1. Identificar Workspace Actual
+## 1. Cargar Configuración
 
-Verifique si está dentro de un workspace creado por `context-cli`:
+Lee los archivos del orquestador:
+- **`context-manifest.json`** - Repositorios y roles
+- **`ai.properties.md`** - base_path, task_management_system
 
-```bash
-# Verificar si está en un directorio de workspace
-pwd
-# El workspace generalmente está en ~/workspaces/<ISSUE-ID>/
-```
-
-Si no está en un workspace, pregunte al usuario qué workspace usar o si debe crear uno nuevo con `feature:start`.
-
-## 📋 Configuración del Proyecto
+## 2. Cargar Contexto Compacto (OPTIMIZADO)
 
-**⚠️ IMPORTANTE: ¡Siempre lea los archivos de configuración del proyecto ANTES de ejecutar este comando!**
+**IMPORTANTE**: Usa carga PROGRESIVA para economizar la ventana de contexto.
 
-### Archivos Obligatorios
+### Obligatorio (warm-up)
 
-1. **`context-manifest.json`** (raíz del orchestrator)
-   - Lista de repositorios del proyecto
-   - Roles de cada repositorio (metaspecs, application, etc.)
-   - URLs y dependencias entre repositorios
+Localiza metaspecs vía `context-manifest.json` (role: "specs-provider"):
 
-2. **`ai.properties.md`** (raíz del orchestrator)
-   - Configuraciones del proyecto (`project_name`, `base_path`)
-   - Sistema de gestión de tareas (`task_management_system`)
-   - Credenciales y configuraciones específicas
-
-### Cómo Leer
-
-```bash
-# 1. Leer context-manifest.json
-cat context-manifest.json
-
-# 2. Leer ai.properties.md
-cat ai.properties.md
+```
+{base_path}/{metaspecs-id}/specs/_meta/WARM_UP_CONTEXT.md  (~100 líneas)
 ```
 
-### Información Esencial
-
-Después de leer los archivos, tendrá:
-- ✅ Lista completa de repositorios del proyecto
-- ✅ Ubicación del repositorio de metaspecs
-- ✅ Base path para localizar repositorios
-- ✅ Sistema de gestión de tareas configurado
-- ✅ Configuraciones específicas del proyecto
-
-**🛑 NO continúe sin leer estos archivos!** Contienen información crítica para la correcta ejecución del comando.
-
-
-## 2. Cargar Configuración del Proyecto
-
-Ya está en el orchestrator del proyecto (raíz del repositorio actual).
-
-1. **Verifique que está en la raíz del orchestrator**: `pwd` debe mostrar el directorio del orchestrator
-2. **Lea el archivo `context-manifest.json`** en la raíz del orchestrator
-3. **Lea el archivo `ai.properties.md`** para obtener configuraciones locales (base_path, etc.)
-
-## 3. Cargar Manifiesto del Proyecto
-
-Lea el `context-manifest.json` del orchestrator para entender:
-- Lista completa de repositorios del ecosistema
-- URL del repositorio de MetaSpecs
-- Dependencias entre repositorios
-- Roles de cada repositorio (application, library, service, specs-provider)
-
-## 4. Cargar MetaSpecs
-
-El repositorio de MetaSpecs es **separado** y está definido en el `context-manifest.json` con `role: "metaspecs"`.
-
-**Localice el repositorio de metaspecs:**
-
-1. Lea `context-manifest.json` y encuentre el repositorio con `role: "metaspecs"`
-2. Obtenga el `id` de ese repositorio (ej: "my-project-metaspecs")
-3. Lea `ai.properties.md` para obtener el `base_path`
-4. El repositorio de metaspecs está en: `{base_path}/{metaspecs-id}/`
+Este archivo contiene TODOS los esenciales:
+- Stack tecnológico
+- Jerarquía de contexto
+- 5 reglas críticas
+- Patrones de código mínimos
+- Tabla de carga bajo demanda
 
-**Lea siempre los archivos de índice primero:**
+### Bajo Demanda (NO cargar durante warm-up)
 
-1. **`README.md`** - Visión general del proyecto y estructura de documentación
-2. **`index.md`** (en la raíz o en subcarpetas) - Índice de especificaciones disponibles
+| Necesidad | Documento |
+|-----------|-----------|
+| Generar código | `CLAUDE.meta.md` |
+| Arquitectura | `ARCHITECTURE.md` |
+| Feature específica | `features/{FEATURE}.md` |
+| Anti-patrones completos | `ANTI_PATTERNS.md` |
 
-**Use los índices como referencia** para navegar hasta las especificaciones específicas que necesite. No asuma que archivos específicos existen - siempre consulte los índices primero.
+## 3. Verificar Repositorios
 
-## 5. Cargar Sesión Actual (si existe)
+Para cada repositorio en `context-manifest.json`:
+- Verificar existencia en `{base_path}/{repo-id}/`
+- **NO** leer README.md ahora (bajo demanda)
 
-Verifique si existe una sesión guardada para este workspace:
+## 4. Verificar Sesión (si existe)
 
 ```bash
-# Buscar sesión en el orchestrator
 ls -la .sessions/<ISSUE-ID>/ 2>/dev/null
 ```
 
-Si existe, lea los archivos de sesión para recuperar el contexto de la última ejecución.
-
-## 6. Contexto de los Repositorios
-
-Para cada repositorio presente en el workspace, lea:
-- `README.md` - Propósito y visión general del repositorio
-- Archivo de configuración principal (`package.json`, `pom.xml`, `requirements.txt`, etc.)
-
-## 7. Navegación Inteligente
-
-- **Código**: Use herramientas de búsqueda (glob, grep) para localizar archivos relevantes
-- **Documentación**: Use los índices de los MetaSpecs como referencia
-- **Espere Instrucciones**: NO lea otros archivos ahora. Espere el próximo comando.
-
-## 8. Principio Jidoka (Parar al Detectar Problemas)
+## 5. Principio Jidoka
 
-Si detecta desalineamientos, conflictos o problemas:
-1. 🛑 **PARE** inmediatamente
-2. 📝 **DOCUMENTE** el problema encontrado
-3. 💬 **ALERTE** al usuario antes de continuar
+Si se detectan problemas: **PARA**, documenta, alerta al usuario.
 
 ---
 
-**Argumentos proporcionados**: #$ARGUMENTS
+**Argumentos**: #$ARGUMENTS
 
-**Estado**: Contexto cargado. Esperando próximo comando.
+**Estado**: Contexto cargado. Esperando próximo comando.