By stopman
Get a second opinion on your Claude Code plans and code changes from other AI models (GPT-5.3 Codex, Gemini 3.1 Pro) via OpenRouter.
A Claude Code plugin that sends your plans and code changes to other AI models for a second opinion via OpenRouter.
When you invoke /secondpass-multireview:secondpass_multireview, Claude gathers your current plan, the git diff, and surrounding code context, then sends it to GPT-5.3 Codex and Gemini 3.1 Pro in parallel. You get back a structured review from each model covering correctness, risks, simplicity, and missing pieces.
# Add the marketplace (one time)
/plugin marketplace add stopman/secondpass-multireview
# Install the plugin
/plugin install secondpass-multireview@secondpass-multireview
Set your OpenRouter API key:
export OPENROUTER_API_KEY="sk-or-v1-..."
Get a key at openrouter.ai/keys.
During any Claude Code session, invoke the skill:
/secondpass-multireview:secondpass_multireview
Claude will:
Override the default models with an environment variable:
export SECONDPASS_MODELS="anthropic/claude-sonnet-4-6,meta-llama/llama-4-maverick"
Any model available on OpenRouter works.
urllib, json, concurrent.futures)MIT
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub stopman/secondpass-multireview --plugin secondpass-multireviewAI-to-AI collaboration — review code, brainstorm ideas, and debate plans across Gemini, Codex, and Ollama
Configurable multi-model code review, plan review, and general review with consensus convergence
Codex, Gemini, Claude の3つの AI に並列でコードレビューを依頼し、統合レポートを生成する
Symmetric two-AI peer review using OpenAI Codex CLI. Both AIs review independently in a blind pass, then debate per-issue with terminal states until convergence. Catches significantly more issues than single-pass validation.
Multi-agent code review for Claude Code — parallel review by Codex (GPT-5.5), Gemini 3.1 Pro, and five Claude specialist subagents (one run blind), then verified synthesis.
Command-driven Claude/Codex review workflows for multi-round plan and implementation review.