Cross-vendor agent-to-agent protocol — Claude, Codex, and Gemini communicate via file-based P2P messaging.

Govern AI coding across Claude Code, Codex, Cursor, and Gemini CLI. Breaking-change detection, deploy gates, and multi-model consensus — delivered as MCP server, CLI, and GitHub Action.

Cross-model audit gate with autonomous quality loop — AST hybrid scanning, fitness gate, blast radius, structured orchestration. 19 MCP tools, 743 tests. CLI + Claude Code plugin.

Multi-agent pipeline for Claude Code — 12 steps with cross-model council and blind verification

Review triad plugin for Claude Code: prompt optimization, adversarial red-team review, plan validation, and intelligent orchestration.

CSP-1: Portable Conversational Identity — A User-Owned Protocol for Preserving AI Relational Style Across Models

Orchestrate multiple agents to execute Claude Code workflows with cross-model verification for reliable AI code automation.

Claude Code skill for cross-model review. One command packages files + prompt for ChatGPT Pro deep reasoning.

Cross-model orchestration for Claude Code — Claude builds, Codex validates. Blind TDD, adversarial stress testing, mixed-model teams, and automatic fallback. Two AI models enter, better code leaves.

Multi-perspective code review council for Claude Code. 3 advisors by default, 10 agents in deep mode (Opus + Codex). Evidence chains, adversarial self-test, dual-path verdict. Based on Karpathy's LLM Council.

Cross-model AI dialogue archive (Japanese). / AI横断問答録

Cross-model code review plugin for Claude Code — get independent second opinions from GPT-5.3 Codex High via Cursor CLI

Agentic code-hardening plugin for Claude Code. Multi-model AI review loop -- Claude writes and decides, Codex CLI critiques one axis at a time (correctness / security / performance / readability / design) until convergence. Cross-LLM adversarial review with audit trail.