By JaviMontano
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.
Alias for audit. Use /pqa:audit instead.
Full QA audit of a Claude Code plugin. Runs 9 skills across 4 movements: validate, audit, report.
Scaffold a complete plugin directory from architecture plans and specs.
Create MOAT directory structures and populate asset files for plugin skills.
Scaffold a complete plugin directory from architecture plans and specs.
Design orchestrator for plugin creation. Guides ideation, architecture planning, and component design. Owns the upstream pipeline: IDEATE, PLAN, DESIGN movements.
Scaffolding specialist that creates plugin directories, writes files to disk, generates MOAT assets, and assembles complete plugins. Owns the BUILD movement.
Orchestrates plugin QA: validates structure, audits quality, generates reports, auto-fixes issues. Owns movements 6-9 in the PQA lifecycle. Default agent for downstream QA operations.
Specification specialist generating production-ready SKILL.md, agent .md, and command .md files at MOAT quality. Owns the SPECIFY movement.
Audits all SKILL.md files in a plugin against a 6-criteria excellence rubric, producing per-skill scores, plugin averages, and actionable improvement recommendations. Trigger: audit content quality, score skills, check skill quality, content rubric.
Performs a comprehensive security audit on a Claude Code plugin, detecting leaked secrets, unsafe paths, shell injection risks, sensitive files, and insecure scripts. Trigger: audit security, security scan, check for secrets, find vulnerabilities.
Create MOAT directory structures and populate asset files (references/, examples/, prompts/, scripts/, assets/) for plugin skills. Trigger: build MOAT assets, create skill assets, populate references, generate examples, build skill directories.
Scaffold a complete plugin directory from architecture plans and specs. Creates all files, then validates structure. Trigger: build plugin, scaffold plugin, create plugin directory, assemble plugin, generate plugin files.
Design a plugin agent: role, tool allowlist, skill assignments, execution flows, operating principles. Trigger: design agent, agent design, create agent spec, plan agent, draft agent. Enforces plugin subagent constraints (no hooks/mcpServers/permissionMode in frontmatter).
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.
De requisitos a producción — 3 plugins para el ciclo completo
Kit de desarrollo agéntico que integra 3 plugins de Claude Code para cubrir el ciclo completo de software: discovery, arquitectura y calidad.
git clone https://github.com/JaviMontano/jm-adk.git && cd jm-adk
MAO (discovery) + SA (arquitectura) + PQA (calidad) → workspace unificado
| Repo | Descripción |
|---|---|
| jm-adk-alfa | ADK Alfa |
| mao-discovery-framework | MAO Discovery |
| mao-sovereign-architect | Sovereign Architect |
| mao-plugin-qa | Plugin QA |
Javier Montaño — Founder JM Labs & MetodologIA
40.000 horas convirtiendo retos en casos de éxito.
GitHub · MetodologIA · LinkedIn
MIT — © 2026 Javier Montaño · JM Labs
From requirements to production — 3 plugins for the full lifecycle
Agentic development kit integrating 3 Claude Code plugins for the full software lifecycle: discovery, architecture, and quality.
MAO (discovery) + SA (architecture) + PQA (quality) → unified workspace
| Repo | Description |
|---|---|
| jm-adk-alfa | ADK Alfa |
| mao-discovery-framework | MAO Discovery |
| mao-sovereign-architect | Sovereign Architect |
| mao-plugin-qa | Plugin QA |
Created by Javier Montaño · JM Labs · MIT
npx claudepluginhub javimontano/jm-adk --plugin plugin-qaSDD — 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.
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.
Sovereign 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.
Genera playbooks HTML branded v2 con metodologia vivida: 13 flujos AI-native, 5 katas (Shu-Ha-Ri), 65 modals interactivos, contenido bilingue ES/EN, 13 anti-patrones, glosario, perfiles de manager, adopcion progresiva, VR-AID, semaforo de valor. Sofka DS v5.1.
PMO-APEX v1.0 — Agentic Project Excellence. Living ontology (CLAUDE.md hub + 13 sub-files), progressive MOAT loading (L1/L2/L3), G0 security gate, context optimization, rendering engine, CLI init wizard, PM retrospective, browser audit (MCP Playwright), cross-platform skill conversion, meta-cognition protocols (FULL/LIGHT), formalized committee spawning (Steering Committee 7 Advisors). 48 agentes, 109 skills MOAT, 103 comandos, 19 scripts, 5 quality gates (G0-G3). Zero-hallucination protocol. Evidence tagging obligatorio. NUNCA precios — solo magnitudes de esfuerzo.
Language-agnostic development process harness implementing the Stateless Agent Methodology (SAM) 7-stage pipeline with ARL human touchpoint model and Voltron-style language plugin composition. Provides orchestration, workflows, planning, verification, and testing methodology that any language plugin can compose with.
Use this agent when evaluating new development tools, frameworks, or services for the studio. This agent specializes in rapid tool assessment, comparative analysis, and making recommendations that align with the 6-day development cycle philosophy. Examples:\n\n<example>\nContext: Considering a new framework or library
Use Claude Code As Is - native plugin leveraging built-in architecture
Spec-driven development workflow system with structured phases: Requirements → Design → Tasks → Implementation
Generic agent harness for Copilot CLI — pipeline agents, skills, plus the engine setup (re-run per update).
13 agents, 35 skills, 19 commands, 15 hooks — spec-driven, multi-agent orchestration for Claude Code with per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.