ADRs Management plugins for Architecture Decision Records analysis, generation, and linking
Generate formal ADRs from potential ADRs
Identify potential ADRs for specific modules based on the codebase mapping (Phase 2)
Detect and create bidirectional relationships between existing ADRs with clickable links
Create a modular codebase mapping to prepare for ADR identification (Phase 1)
Use this agent when you need to analyze a codebase to understand its architecture and generate Architecture Decision Records (ADRs). This is a two-phase process: Phase 1 - Codebase Mapping: <example> Context: User wants to start analyzing their codebase for ADR generation. user: "I need to understand the architecture of this project and create ADRs for it" assistant: "I'll use the adr-analyzer agent to begin the codebase mapping phase, which will analyze the project structure and create the initial mapping document." <Task tool call to adr-analyzer agent> </example> <example> Context: User has a large legacy codebase without documentation. user: "Can you help me document the architectural decisions in this codebase?" assistant: "Let me use the adr-analyzer agent to first map out the codebase structure and identify the technologies and architectural patterns used." <Task tool call to adr-analyzer agent> </example> Phase 2 - ADR Identification: <example> Context: The mapping.md file has been created with modular structure and user wants to proceed with ADR identification. user: "The mapping is complete, now identify potential ADRs for the AUTH and API modules" assistant: "I'll use the adr-analyzer agent to analyze the AUTH and API modules from the mapping and identify potential ADRs for these specific areas." <Task tool call to adr-analyzer agent> </example> <example> Context: User has a large codebase (5000+ files) and wants to analyze incrementally. user: "Start identifying ADRs, but do it module by module to avoid overwhelming the context" assistant: "I'll use the adr-analyzer agent to read the mapping and present the available modules, then we can analyze them systematically one or two at a time." <Task tool call to adr-analyzer agent> </example> <example> Context: User wants to continue ADR analysis from where they left off. user: "Continue the ADR analysis. We already did AUTH and API, let's do DATA and PAYMENT next" assistant: "I'll use the adr-analyzer agent to analyze the DATA and PAYMENT modules and append the findings to the existing potential_adrs.md." <Task tool call to adr-analyzer agent> </example> <example> Context: User is working on improving project documentation after initial development. user: "We've built this system over the past year but never documented our architectural decisions. Can you help?" assistant: "I'll use the adr-analyzer agent to analyze your codebase systematically. We'll start with mapping the architecture into logical modules, then identify key decisions module by module to keep analysis manageable." <Task tool call to adr-analyzer agent> </example>
Generate a formal ADR from a single potential ADR file identified in the codebase. This agent processes ONE file at a time. When multiple files need processing, the command launcher invokes multiple instances of this agent in parallel.
Detect and create bidirectional relationships between existing ADRs with clickable Markdown links. Analyzes temporal evolution, technical dependencies, semantic similarity, and explicit hints to build a comprehensive ADR relationship graph.
Uses power tools
Uses Bash, Write, or Edit tools
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uma coleção de plugins para o Claude Code voltados à arquitetura de software e à documentação de design. Os plugins automatizam tarefas como registrar decisões arquiteturais, gerar diagramas, analisar a arquitetura de projetos e produzir guias de desenvolvimento por linguagem.
Este marketplace oferece quatro plugins para documentação e análise arquitetural:
| Plugin | Descrição | Comandos |
|---|---|---|
| ADRs Management | Análise, geração e vinculação de Architecture Decision Records (ADRs) | /adrs-management:adr-map, :adr-identify, :adr-generate, :adr-link |
| Diagrams Generator | Geração de diagramas C4 (PlantUML) e Mermaid a partir de Feature Design Documents (FDDs) | /diagrams-generator:c4-generate, :mermaid-generate |
| Project Analyzer | Análise arquitetural completa, análise profunda de componentes e auditoria de dependências | /project-analizer:generate-architectural-report, :run-dependency-audit |
| Development Guidelines | Geração de guias de desenvolvimento abrangentes e específicos por linguagem | /development-guidelines:guidelines-generate |
Todos os comandos abaixo são executados dentro do Claude Code no terminal (rode
claude). Em outros ambientes (extensões/IDE) o comando/pluginpode não estar disponível.
/plugin marketplace add Lucassamuel97/claude-plugins
Esse comando registra o repositório do GitHub como uma fonte de plugins. Você verá: Successfully added marketplace: lucassamuel-plugins.
O identificador do marketplace (
lucassamuel-plugins) é o camponamedefinido em .claude-plugin/marketplace.json — não é o nome do repositório.
Instale apenas os que for usar (ou todos):
/plugin install adrs-management@lucassamuel-plugins
/plugin install diagrams-generator@lucassamuel-plugins
/plugin install project-analizer@lucassamuel-plugins
/plugin install development-guidelines@lucassamuel-plugins
Após instalar, os comandos não ficam ativos imediatamente. Recarregue:
/reload-plugins
Se os comandos ainda não aparecerem após o
/reload-plugins, feche e reabra o Claude Code (saia e rodeclaudenovamente).
Os comandos dos plugins são namespaced pelo nome do plugin, no formato /<plugin>:<comando>:
/diagrams-generator:mermaid-generate docs/features/FDD_Rate_Limiter.md
/adrs-management:adr-map
/project-analizer:generate-architectural-report
/development-guidelines:guidelines-generate Python
Dica: digite
/e comece a escrever o nome do comando (ex.:/merou/diagrams) para o autocomplete mostrar o nome/namespace exato com que cada comando foi registrado.
Para navegar pelos plugins instalados e seus comandos a qualquer momento:
/plugin
Os comandos usam o prefixo do plugin (
/<plugin>:<comando>). Se preferir, digite/e use o autocomplete para localizá-los.
Documente decisões arquiteturais de forma sistemática, seguindo um fluxo de 3 fases (mapear → identificar → gerar) com vinculação ao final:
/adrs-management:adr-map # Fase 1: mapeia a base de código em módulos lógicos
/adrs-management:adr-identify AUTH DATA # Fase 2: identifica ADRs em potencial nos módulos
/adrs-management:adr-generate BILLING # Fase 3: gera ADRs formais no formato MADR
/adrs-management:adr-link # Vincula os ADRs com relacionamentos bidirecionais
Os ADRs podem ser gerados em vários idiomas (en, pt-BR, es, fr, de). O plugin aplica filtragem rigorosa — apenas cerca de 5% das descobertas viram ADRs — e usa o histórico do git para enriquecer o contexto temporal.
Crie documentação visual a partir de Feature Design Documents (FDDs):
/diagrams-generator:c4-generate docs/features/FDD_Rate_Limiter.md # Diagramas C4 (C1–C4) em PlantUML
/diagrams-generator:mermaid-generate docs/features/FDD_Rate_Limiter.md # Diagramas Mermaid (sequência, fluxo, classe, ER)
O idioma dos diagramas é detectado automaticamente a partir do FDD, mantendo os termos técnicos em inglês (Service, Gateway, Redis etc.). Nenhum diagrama é inventado quando o FDD não tem informação suficiente.
Este repositório já inclui um FDD de exemplo em docs/features/FDD_Rate_Limiter.md (um SDK de rate limiting em Go) para você testar os comandos imediatamente.
Analise a arquitetura e as dependências do projeto (somente leitura — não modifica o código):
Development Guidelines plugin for generating comprehensive language-specific development guideline documents
Project Analyzer plugins for comprehensive architectural analysis, component deep analysis, and dependency auditing
Diagrams Generator plugins for C4 and Mermaid diagram generation from Feature Design Documents
npx claudepluginhub lucassamuel97/claude-plugins --plugin adrs-managementUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.