By bbingz
Use Gemini from Claude Code to review code or delegate tasks. Streaming support, task runtime, thread resumption.
Run a Gemini review that challenges the implementation approach and design choices
Delegate a task or ask a question to Gemini
Cancel an active Gemini background job
Delegate investigation, an explicit fix request, or follow-up work to the Gemini rescue subagent
Retrieve the full output of a completed Gemini job
Internal helper contract for calling the gemini-companion runtime from Claude Code
Internal guidance for optimizing prompts before sending to Gemini CLI
Internal guidance for presenting Gemini helper output back to the user
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
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.
A Claude Code plugin that integrates Google Gemini CLI for code review and task delegation.
npm install -g @google/gemini-cli)gemini interactively once to log in)# From this repository
claude plugins add ./plugins/gemini
/gemini:setupCheck Gemini CLI installation and authentication status.
/gemini:setup
/gemini:askDelegate a task or ask a question to Gemini.
/gemini:ask What does the function foo() in src/bar.ts do?
/gemini:ask --model gemini-2.5-flash Summarize this codebase
/gemini:reviewRun a Gemini code review on the current diff.
/gemini:review
/gemini:review --scope branch
/gemini:review --base main focus on security
Options:
--base <ref> — Base branch for diff (default: auto-detected)--scope <auto|working-tree|branch> — What to review (default: auto)--model <model> — Gemini model to useThe plugin calls Gemini CLI in headless mode (gemini -p "..." -o json) and presents the structured response. No persistent processes, no MCP server — each call is independent.
Review flow:
git diff based on scopeplugins/gemini/
├── .claude-plugin/plugin.json # Plugin identity
├── commands/ # Slash command definitions
│ ├── setup.md # /gemini:setup
│ ├── ask.md # /gemini:ask
│ └── review.md # /gemini:review
├── hooks/hooks.json # Session lifecycle hooks
└── scripts/
├── gemini-companion.mjs # Main entry point
├── session-lifecycle-hook.mjs # Session management
└── lib/
├── args.mjs # Argument parsing
├── gemini.mjs # Gemini CLI wrapper
├── git.mjs # Git diff collection
├── process.mjs # Process management
├── render.mjs # Output formatting
└── state.mjs # Configuration persistence
MIT
npx claudepluginhub bbingz/gemini-plugin-ccUse Qwen from Claude Code to review code or delegate tasks.
Use MiniMax (via Mini-Agent) from Claude Code.
Use multiple provider CLIs from one Claude Code plugin, including background job lifecycle.
Use Kimi from Claude Code to review code or delegate tasks.
Use Gemini CLI from Claude Code to review code or delegate tasks.
OpenAI Codex CLI integration with MCP server and skills for plan review, code review, and codebase analysis
Integrate Gemini CLI for long-context code exploration from Claude Code and Codex
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns