convez.ai
PluginProdutividadeIntermediário
AltimateAI

Claude Consensus

AltimateAI/claude-consensus

Revisão multi-modelo com síntese consensual para código e planos

Ver no GitHub
BomPluginScore · de 0 a 100

Plugin de revisão de código e planos que mobiliza múltiplos modelos de IA para analisar independentemente e convergir em um consenso estruturado. Funciona em Claude Code e Codex, integrando GPT, Gemini, DeepSeek e outros modelos via OpenRouter.

Instalação

$npx convez-ai AltimateAI/claude-consensus

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
34
Forks
3
Acompanhando
1
Saúde
87%
Último commit
há 2 semanas
Versão
—
Issues abertas
0
Contribuidores
2

Casos de uso

  • Revisão de código em estágios com validação de múltiplos modelos
  • Aprovação de planos de arquitetura e implementação técnica
  • Análise de documentação técnica com perspectivas convergentes

Veredito

Ferramenta madura que reduz viés individual ao agregar julgamentos de múltiplos modelos. Requer setup moderado (API keys e CLI), mas entrega valor real para equipes que valorizam rigor em revisões técnicas.

README

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

claude-consensus

Multi-model code review, plan review, and general review for Claude Code and Codex

License: MIT Claude Code

Multiple AI models independently review code, implementation plans, documents, or technical proposals, then converge through structured synthesis and approval rounds. The lead host participates directly: Claude leads in Claude Code, and Codex leads in Codex.

Quick Start

Claude Code

Tell Claude:

"Set up claude-consensus: https://github.com/AltimateAI/claude-consensus"

Manual install:

/plugin marketplace add AltimateAI/claude-consensus
/plugin install consensus
/consensus-setup

Then use:

/code-review "staged changes"
/plan-review "Add caching to the API layer"
/consensus:review docs/architecture.md

Codex

From a local clone, add this repo marketplace to Codex and install the consensus plugin:

git clone https://github.com/AltimateAI/claude-consensus.git

Use the repo marketplace at:

.agents/plugins/marketplace.json

Then configure and run:

consensus-setup
consensus-code-review staged changes
consensus-plan-review Add caching to the API layer
consensus-review docs/architecture.md

Alias skills are also provided for code-review, plan-review, plan-reviwe, and claude-consensus.

Prerequisites

RequirementRequired?Notes
Claude Code or CodexYesThe host environment determines the lead reviewer
Kilo CLIRecommendedRoutes OpenRouter models with one API key
OpenRouter API keyRecommendedRequired for Kilo/OpenRouter models
Native CLIsOptionalClaude supports codex, gemini, and qwen; Codex supports non-Codex native CLIs
CodeRabbit CLIOptionalSupplementary static analysis for code reviews

Minimal setup: the host lead plus 1 external model is enough for consensus reviews.

Supported Panels

ModelProviderOpenRouter IDClaude nativeCodex external
ClaudeAnthropicbuilt-inleadnot used
Codex / GPTOpenAIopenai/gpt-5.4-codexcodexlead, not external
Gemini 3.1 ProGooglegoogle/gemini-3.1-pro-previewgeminigemini
Kimi K2.6Moonshotmoonshotai/kimi-k2.6KiloKilo
Grok 4.20xAIx-ai/grok-4.20-betaKiloKilo, disabled by default
MiniMax M2.7MiniMaxminimax/minimax-m2.7KiloKilo
GLM-5.1Zhipu AIzai-coding-plan/glm-5.1KiloKilo
Qwen 3.6 PlusAlibabaqwen/qwen3.6-plusqwen or KiloKilo by default
MiMo V2 ProXiaomixiaomi/mimo-v2-proKiloKilo
DeepSeek V4 ProDeepSeekdeepseek/deepseek-v4-proKiloKilo

Codex intentionally excludes Codex/GPT from the external panel because Codex is already the lead reviewer.

Configuration

HostUser configDefault configEnv file
Claude Code~/.claude/consensus.jsonplugins/consensus/consensus.config.json~/.claude/.env
Codex~/.codex/consensus.jsonplugins/consensus/consensus.codex.config.json~/.codex/.env first, then ~/.claude/.env read-only fallback

Claude setup can smoke-test live model calls. Codex setup does not run live smoke tests unless you ask, because they consume credits.

Example Codex config:

{
  "version": "1.6.0",
  "lead": {
    "id": "codex",
    "name": "Codex",
    "excluded_model_ids": ["gpt", "codex"]
  },
  "models": [
    {
      "id": "gemini",
      "name": "Gemini 3.1 Pro",
      "command": "gemini",
      "resume_flag": "",
      "enabled": true
    },
    {
      "id": "kimi",
      "name": "Kimi K2.6",
      "command": "kilo run -m openrouter/moonshotai/kimi-k2.6 --auto",
      "resume_flag": "-c",
      "enabled": true
    }
  ],
  "min_quorum": 3
}

Commands And Skills

HostCommand / skillPurpose
Claude/consensus-setupConfigure models, API keys, and quorum
Claude/code-review [target]Multi-model code review with convergence
Claude/plan-review [task]Multi-model implementation planning
Claude/consensus:review [target]General document/topic review
Codexconsensus-setupConfigure the Codex consensus panel
Codexconsensus-code-review [target]Codex-led code review with convergence
Codexconsensus-plan-review [task]Codex-led implementation plan review
Codexconsensus-review [target]Codex-led document/topic review

How It Works

Host lead  Model 1  Model 2  Model N
    |         |        |        |
    v         v        v        v
Independent review or planning
    |_________|________|________|
              |
              v
Synthesis: consensus, conflicts, comparison table
              |
              v
Convergence: APPROVE / CHANGES NEEDED, max 2 rounds
              |
              v
Final result with attribution
  • Quorum: configurable per host.
  • Graceful degradation: unavailable models are skipped if quorum still holds.
  • Session artifacts: saved in /tmp/ for debugging and auditability.
  • Independent reviews: each model starts from the same prompt with no cross-contamination.
  • Codex isolation: Codex uses separate config and never writes Claude user config.

Contributing

Contributions are welcome. Please read the Contributing Guide before submitting a PR.

This project follows the Contributor Covenant Code of Conduct.

License

MIT License. Copyright (c) 2026 Altimate AI.

Ver o original no GitHub

Bom para

Relacionados