convez.ai
AgenteDesenvolvimento WebAvançado
costrict-plugins-repo

Agent Teams para Claude Code

costrict-plugins-repo/wshobson-claude-code-workflows-agent-teams

Orquestre equipes de agentes para revisão, debug e desenvolvimento em paralelo

Ver no GitHub
InicialPluginScore · de 0 a 100

Plugin que orquestra equipes multi-agentes para revisão de código paralela, debugging hypothesis-driven e desenvolvimento coordenado de features. Utiliza o recurso experimental Agent Teams do Claude Code para decomposição automática de trabalho, comunicação estruturada entre agentes e síntese de resultados.

Instalação

$npx convez-ai costrict-plugins-repo/wshobson-claude-code-workflows-agent-teams

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
37%
Último commit
há 2 semanas
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Revisão de código multi-dimensional paralela (segurança, performance, arquitetura, testes, acessibilidade)
  • Debugging hypothesis-driven com múltiplos agentes investigando teorias diferentes simultaneamente
  • Desenvolvimento paralelo de features com limites de propriedade de arquivos
  • Audit de segurança coordenado (OWASP, autenticação, dependências, configuração)
  • Migração de codebase com múltiplos fluxos de implementação e verificação de correção

Veredito

Plugin experimental robusto que traz verdadeira paralelização de tarefas complexas ao Claude Code através de orquestração inteligente de agentes. Ideal para equipes que precisam de revisões sistemáticas e debugging distribuído, mas requer ativação experimental e setup tmux/terminal.

README

A tradução para o português deste README ainda está na fila.

Agent Teams Plugin

Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's experimental Agent Teams feature.

Setup

Prerequisites

  1. Enable the experimental Agent Teams feature:
export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1
  1. Configure teammate display mode in your ~/.claude/settings.json:
{
  "teammateMode": "tmux"
}

Available display modes:

  • "tmux" — Each teammate runs in a tmux pane (recommended)
  • "iterm2" — Each teammate gets an iTerm2 tab (macOS only)
  • "in-process" — Teammates run in the same process (default)

Installation

First, add the marketplace (if you haven't already):

/plugin marketplace add wshobson/agents

Then install the plugin:

/plugin install agent-teams@claude-code-workflows

Features

  • Preset Teams — Spawn pre-configured teams for common workflows (review, debug, feature, fullstack, research, security, migration)
  • Multi-Reviewer Code Review — Parallel review across security, performance, architecture, testing, and accessibility dimensions
  • Hypothesis-Driven Debugging — Competing hypothesis investigation with evidence-based root cause analysis
  • Parallel Feature Development — Coordinated multi-agent implementation with file ownership boundaries
  • Parallel Research — Multiple Explore agents investigating different questions or codebase areas simultaneously
  • Security Audit — Comprehensive parallel security review across OWASP, auth, dependencies, and configuration
  • Migration Support — Coordinated codebase migration with parallel implementation streams and correctness verification
  • Task Coordination — Dependency-aware task management with workload balancing
  • Team Communication — Structured messaging protocols for efficient agent collaboration

Commands

CommandDescription
/team-spawnSpawn a team using presets or custom composition
/team-statusDisplay team members, tasks, and progress
/team-shutdownGracefully shut down a team and clean up resources
/team-reviewMulti-reviewer parallel code review
/team-debugCompeting hypotheses debugging with parallel investigation
/team-featureParallel feature development with file ownership
/team-delegateTask delegation dashboard and workload management

Agents

AgentRoleColor
team-leadTeam orchestrator — decomposes work, manages lifecycle, synthesizes resultsBlue
team-reviewerMulti-dimensional code reviewer — operates on assigned review dimensionGreen
team-debuggerHypothesis investigator — gathers evidence to confirm/falsify assigned hypothesisRed
team-implementerParallel builder — implements within strict file ownership boundariesYellow

Skills

SkillDescription
team-composition-patternsTeam sizing heuristics, preset compositions, agent type selection
task-coordination-strategiesTask decomposition, dependency graphs, workload monitoring
parallel-debuggingHypothesis generation, evidence collection, result arbitration
multi-reviewer-patternsReview dimension allocation, finding deduplication, severity calibration
parallel-feature-developmentFile ownership strategies, conflict avoidance, integration patterns
team-communication-protocolsMessage type selection, plan approval workflow, shutdown protocol

Quick Start

Multi-Reviewer Code Review

/team-review src/ --reviewers security,performance,architecture

Spawns 3 reviewers, each analyzing the codebase from their assigned dimension, then consolidates findings into a prioritized report.

Hypothesis-Driven Debugging

/team-debug "API returns 500 on POST /users with valid payload" --hypotheses 3

Generates 3 competing hypotheses, spawns investigators for each, collects evidence, and presents the most likely root cause with a fix.

Parallel Feature Development

/team-feature "Add user authentication with OAuth2" --team-size 3 --plan-first

Decomposes the feature into work streams with file ownership boundaries, gets your approval, then spawns implementers to build in parallel.

Parallel Research

/team-spawn research --name codebase-research

Spawns 3 researchers to investigate different aspects in parallel — across your codebase (Grep/Read) and the web (WebSearch/WebFetch). Each reports findings with citations.

Security Audit

/team-spawn security

Spawns 4 security reviewers covering OWASP vulnerabilities, auth/access control, dependency supply chain, and secrets/configuration. Produces a consolidated security report.

Codebase Migration

/team-spawn migration --name react-hooks-migration

Spawns a lead to plan the migration, 2 implementers to migrate code in parallel streams, and a reviewer to verify correctness of the migrated code.

Custom Team

/team-spawn custom --name my-team --members 4

Interactively configure team composition with custom roles and agent types.

Best Practices

  1. Start with presets — Use /team-spawn review, /team-spawn debug, or /team-spawn feature before building custom teams
  2. Use --plan-first — For feature development, always review the decomposition before spawning implementers
  3. File ownership is critical — Never assign the same file to multiple implementers; use interface contracts at boundaries
  4. Monitor with /team-status — Check progress regularly and use /team-delegate --rebalance if work is uneven
  5. Graceful shutdown — Always use /team-shutdown rather than killing processes manually
  6. Keep teams small — 2-4 teammates is optimal; larger teams increase coordination overhead
  7. Use Shift+Tab — Claude Code's built-in delegate mode (Shift+Tab) complements these commands for ad-hoc delegation
Ver o original no GitHub

Bom para

Relacionados