gemini

Gemini plugin for Claude Code

Installation

/plugin marketplace add m-ghalib/gemini-plugin-cc
/plugin install gemini@gemini-plugin-cc
/reload-plugins
/gemini:setup --verify

The /gemini:setup command checks whether the Gemini CLI is installed and authenticated. If the CLI is missing and npm is available, it offers to install the pinned CLI with npm install -g @google/[email protected].

Prerequisites

• Claude Code installed and authenticated. Run the install commands above inside a Claude Code session.
• Node.js 18.18 or later on PATH.
• Gemini CLI access through Google OAuth, a Gemini API key, a Google API key, Vertex AI, or an AI gateway.
• Gemini CLI authentication configured in ~/.gemini/settings.json, or completed interactively by running gemini in a terminal.

What it does

gemini-plugin-cc gives Claude Code a local Gemini companion for code review, adversarial review, and delegated task work. It wraps Google's Gemini CLI (@google/[email protected]) through the Agent-Client Protocol (ACP), using JSON-RPC 2.0 over stdio so Claude and Gemini can work side by side on the same repository.

The plugin exposes seven slash commands plus the gemini-rescue subagent. Review commands are read-only. Rescue defaults to Gemini CLI's write-capable --yolo --sandbox mode, scoped to the repository worktree; use --plan for a read-only planning run.

Commands

Command	Purpose
/gemini:setup	Verify Gemini CLI readiness, check auth, and toggle the review gate
/gemini:review	Review code changes with structured findings
/gemini:adversarial-review	Challenge implementation choices, tradeoffs, and assumptions
/gemini:rescue	Delegate investigation, diagnosis, research, or fix work to Gemini
/gemini:status	Check active and recent Gemini jobs
/gemini:result	Show the stored output of a finished job
/gemini:cancel	Cancel an active background job

Quick Flows

Verify the install:

/gemini:setup --verify

Review current work:

/gemini:review --wait

Challenge a feature branch:

/gemini:adversarial-review --base main challenge whether this retry logic handles all failure modes

Delegate an investigation:

/gemini:rescue --background investigate the N+1 query problem in the user dashboard
/gemini:status --wait
/gemini:result

Enable stop-time review:

/gemini:setup --enable-review-gate

Detailed Reference

/gemini:review

Reads your working-tree diff or branch diff and asks Gemini to review it. Returns structured findings covering correctness, regression risk, and code quality. Review-only -- never modifies code.

Flags: --base <ref> (explicit base branch), --scope auto|working-tree|branch, --wait (foreground), --background (detach).

If neither --wait nor --background is specified, Claude estimates the review size and recommends an execution mode.

/gemini:review
/gemini:review --base main
/gemini:review --scope branch --background

---

/gemini:adversarial-review

Same target selection as /gemini:review, but challenges the chosen implementation, design choices, tradeoffs, and assumptions. Not just a stricter pass over defects -- it asks whether the current approach is the right one and where the design could fail under real-world conditions.

Steerable: accepts focus text after flags to direct the review toward specific concerns.

Flags: same as /gemini:review.

/gemini:adversarial-review
/gemini:adversarial-review --base main challenge the error handling strategy
/gemini:adversarial-review challenge whether this retry logic handles all failure modes

---

/gemini:rescue

Delegates code investigation, fixes, or diagnosis to Gemini. For exploratory or diagnostic tasks, the plugin suggests that Gemini use its built-in codebase_investigator subagent before drafting a fix.

Flags:

Flag	Description
--background	Detach and run as a background job
--wait	Run in the foreground (block until complete)
--resume	Continue from the last Gemini thread in this repository
--fresh	Start a new Gemini thread (ignore any prior session)
--model <alias>	Choose a specific Gemini model (see model aliases below)
--effort low|medium|high	Set Gemini's thinking level (accepted; pending upstream ACP support)
--plan	Read-only planning run (Gemini proposes but does not execute)

Model aliases: