By CHOSENX-GPU
Adversarial plan review and deep code review via Claude Code, Codex, and Cursor cross-agent collaboration
Deep code review with cross-agent support. Supports claude-only, codex-review, and dual-review modes. Use when the user says /code-review, "review code", "代码审查", or when code needs quality verification after implementation.
Bridge for calling Codex and Cursor from Claude Code. Provides MCP call format and shell fallbacks. Use when you need to delegate work to Codex or Cursor, or when plan-review/plan-execute/code-review need to invoke external agents.
Adversarial plan review: Claude Code creates a plan, Codex/Cursor reviews it critically, iterate until approved. Use when the user says /plan-review, "review plan", "审查计划", or needs a technical plan vetted by a second AI agent.
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub chosenx-gpu/synapse --plugin synapse-reviewAutomated git operations with Conventional Commits: /save, /commit, /push, /pr, /squash-merge
Git worktree lifecycle management: create, list, switch, handoff, and cleanup for parallel multi-agent development
EARS (Evolving Autonomous Research System) - project-aware knowledge capture with auto-discovery hook and tech-stack-specific initialization
Orchestrated plan execution via Codex/Cursor/Claude with batch review, fix loops, and auto-commit
Hierarchical Cognitive Caching — project-level memory system for Claude Code. Tracks work, distills experience, builds verified knowledge across sessions.
Command-driven Claude/Codex review workflows for multi-round plan and implementation review.
Autonomous Claude + Codex review loop. Plan a feature with adversarial pushback, or audit code, all in one window.
Give Claude Code a second opinion using OpenAI Codex - automatic plan review via hooks
Independent plan/spec reviewer for AI coding agents. Verifies claims against the workspace and returns structured verdicts with findings.
Use Codex from Claude Code to review code or delegate tasks.
Two Claude Code engineering skills bundled as one plugin: review-loop (cross-LLM iterative code review with Codex or Gemini as peer) and harness (cybernetics-based Planner→Generator→Evaluator→Retro orchestration for complex tasks).