By JaviMontano
SA — Sovereign Architect. Evidence-based technical leadership for codebase analysis, architecture design, implementation planning, and quality assurance. 66 agents, 128 skills, 120 commands.
Alias → analyze. Use /sa:analyze instead.
Alias → audit-accessibility. Use /sa:audit-accessibility instead.
Alias → generate-adr. Use /sa:generate-adr instead.
Full 5-phase workflow: discovery → diagnosis → design → plan → delivery
Alias → map-api. Use /sa:map-api instead.
Accessibility compliance expert — WCAG 2.1 AA/AAA auditing, assistive technology testing, inclusive design. Activated when a11y requirements are in scope.
ML pipeline and model governance lead — MLOps, feature stores, model serving, experiment tracking, responsible AI. Activated when machine learning infrastructure or AI system design is in scope.
BI and analytics pipeline lead — dbt modeling, semantic layers, metrics definitions, dashboard design, self-service analytics. Activated when analytics infrastructure or BI engineering is in scope.
Angular 18+ expert — Signals, standalone components, SSR, zoneless, Nx monorepo. Activated for Angular development.
API contract specialist — REST, GraphQL, gRPC design, versioning strategy, contract-first development. Activated when API surface is being designed or reviewed.
Writes testable acceptance criteria in Given/When/Then format, covering happy paths, edge cases, and error scenarios. Trigger: "acceptance criteria", "given when then", "write AC", "define done", "user story criteria".
Implement WCAG 2.1 AA / 2.2 accessibility: semantic HTML audit, ARIA implementation, keyboard navigation, screen reader testing, color contrast. Use when user asks to "implement accessibility", "fix a11y issues", "make WCAG compliant", or "audit for accessibility".
Produces Architecture Decision Records following the Nygard/MADR template with full context, consequences, and traceability. Trigger: "generate ADR", "document decision", "architecture decision record", "record this decision".
dbt-style transformations, dimensional data modeling, testing strategies, and documentation generation for analytics platforms. Trigger: "analytics engineering", "dbt", "data modeling", "dimensional model", "star schema", "data marts".
REST, GraphQL, and gRPC API governance, versioning strategy, rate limiting, and developer experience design. Trigger: "API architecture", "API design", "REST", "GraphQL", "gRPC", "API governance", "developer experience".
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Liderazgo técnico basado en evidencia
Plugin de arquitectura de software que actúa como Principal Software Systems Lead. Analiza código, repositorios, especificaciones e incidentes para decisiones arquitectónicas fundamentadas.
git clone https://github.com/JaviMontano/mao-sovereign-architect.git ~/.claude/plugins/mao-sovereign-architect
principal-architect orquesta → 66 agentes especialistas → evidence-auditor valida
| Repo | Descripción |
|---|---|
| mao-discovery-framework | MAO Discovery |
| mao-sdd | SDD |
| mao-pm-apex | PM APEX |
| mao-plugin-qa | Plugin QA |
Javier Montaño — Founder MetodologIA & JM Labs
40.000 horas convirtiendo retos en casos de éxito.
GitHub · MetodologIA · LinkedIn
GPL-3.0 — © 2026 MetodologIA. Copyleft — Para uso y aprovechamiento de profesionales en la era de la IA.
Evidence-based technical leadership
Software architecture plugin that acts as Principal Software Systems Lead. Analyzes code, repositories, specifications, and incidents for evidence-based architectural decisions.
principal-architect orchestrates → 66 specialist agents → evidence-auditor validates
| Repo | Description |
|---|---|
| mao-discovery-framework | MAO Discovery |
| mao-sdd | SDD |
| mao-pm-apex | PM APEX |
| mao-plugin-qa | Plugin QA |
Created by Javier Montaño · MetodologIA / JM Labs · GPL-3.0
npx claudepluginhub javimontano/mao-sovereign-architectSovereign Architect — Evidence-based technical leadership for software engineering. 66 specialists · 127 skills MOAT · 119 commands · 19 scripts · 13 ontology files · 39 RAG docs · 4 quality gates (G0-G2). Development Kit Edition: Supabase, Firebase, React, Angular, Vue, Next.js, PostgreSQL, MongoDB, Redis, CSS architecture, web performance, scaffolding. Zero-assumption protocol.
Plugin QA — Full plugin development lifecycle for Claude Code plugins. 4 agents, 20 skills, 31 commands, 9 scripts, 13 ontology files, 9 movements (IDEATE, PLAN, DESIGN, SPECIFY, BUILD, VALIDATE, AUDIT, REPORT, FIX). Session automation with hooks, living ontology, and the autoridad moral: the plugin that audits plugins passes its own standards.
PQA — Plugin Quality Auditor. Plugin development lifecycle management: ideate, plan, design, specify, build, validate, audit, report, and fix plugins. 4 agents, 20 skills, 31 commands.
SDD — Spec Driven Development by MetodologIA. Specification-driven AI development with cryptographic BDD verification, autonomous heartbeat sentinel, insights engine, and Neo-Swiss lifecycle dashboard. Powered by IIC/kit.
MAO v1.4 — MetodologIA de Aprovechamiento de Oportunidades. Universal Discovery Framework. G0 security gate, context optimization, rendering engine, CLI init wizard. Progressive MOAT Loading. Meta-cognition protocols (FULL/LIGHT). Formalized committee spawning. 101 agentes, 108 skills MOAT, 109 comandos, 19 scripts, 5 quality gates (G0-G3). Design System v5. Zero-hallucination protocol. MIT.
Editorial "Architecture & Design" bundle for Claude Code from Antigravity Awesome Skills.
Architecture Deep Research — scan a repo, draft a PRD, run live deep research, get a cited handoff. Use when picking a topology, retrieval architecture, event bus, storage engine, auth pattern, or any system-design decision before code lands.
AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode
[Beta] 6つの専門エージェントチームでコードベースのアーキテクチャを多角的に分析するスキル
Enforces best-practice software design & architecture
Architecture analysis, brainstorming, ADR generation, LLM-as-judge comparison, and spec gap resolution.