AbadIA-MCP

Patrón de escalado de capacidad del modelo por subtarea — cuándo cambiar RALPH_MODEL_CAPABILITY en .ralph/.env

Metodología de planificación para el bucle ralph en AbadIA-MCP — granularidad, estructura de tareas y prerrequisitos

Estrategia para promover componentes compartidos en vault/components/ — cuándo emitir un fichero vs. anotar en pending-components.md

Patrón de 3 capas (Alcance, Criterios, Evidencias) para [juez] checkpoints en tasks de vault

Estructura modular del vault de AbadIA-MCP — separación server-core/server-map y orden de dependencias entre pasadas

Reglas universales al escribir ficheros en vault/ — frontmatter de provenance, bloques Evidence y prohibición de código fuente

Estrategia para emitir edges tipados en vault/relations/ — cuándo crear un fichero de edge vs. anotar en pending-relations.md

Patrón de delimitación por ficheros entre módulos hermanos para evitar solapamiento de alcance en el vault

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

Gestiona credenciales de GitHub, limpieza de caché y autenticación robusta para push en entornos agénticos. Úsalo cuando el push falle por 403 Forbidden o problemas de identidad.

Local logic validator to offload geometry and collision checks from the LLM. High-efficiency deterministic validation.

High-efficiency log parser for 'The Chronicler'. Extracts failures and NPC routine patterns from JSONL logs without LLM inference.

Automatic reaction engine for environmental signals (Sounds/Phrases). Deterministic plan re-evaluation without LLM inference.

Implementation of the 7-step Osmani Standard for Harness-Driven Development. Designed for autonomous, long-running agent loops.

Implementation of the Osmani Standard for Agentic Engineering. Enforces the Spec-Plan-Build-Verify cycle to ensure production-grade output.