gemini

Gemini-backed plugin for Claude Code

Use Gemini from inside Claude Code for code reviews or to delegate tasks without leaving your existing /gemini:* workflow.

This plugin is for Claude Code users who want Gemini to be both the provider and the visible command surface inside Claude Code.

The repository and marketplace source slug may still contain codex-plugin-cc as a historical identifier, but the supported provider, runtime, and slash-command surface in this project are all Gemini for Claude Code.

What You Get

• /gemini:review for a normal read-only Gemini-backed review
• /gemini:adversarial-review for a steerable challenge review
• /gemini:rescue, /gemini:status, /gemini:result, and /gemini:cancel to delegate work and manage background jobs

Requirements

• Gemini CLI access.
  • Supported paths include signing into Gemini CLI with a Google account or providing GEMINI_API_KEY / GOOGLE_API_KEY.
• Node.js 18.18 or later

Install

Add the marketplace in Claude Code:

/plugin marketplace add ByteLandTechnology/gemini-cc

Install the plugin:

/plugin install gemini@gemini-cc

ByteLandTechnology/gemini-cc is the repository slug, while gemini-cc is the published marketplace name for this plugin and is declared in the repository-root .claude-plugin/marketplace.json.

Reload plugins:

/reload-plugins

Then run:

/gemini:setup

/gemini:setup will tell you whether Gemini is ready. If Gemini CLI is missing and npm is available, it can offer to install Gemini for you.

If you prefer to install Gemini yourself, use:

npm install -g @google/gemini-cli

If Gemini CLI is installed but not authenticated yet, run:

gemini

Then complete /auth, or set GEMINI_API_KEY / GOOGLE_API_KEY before rerunning /gemini:setup.

After install, you should see:

• the slash commands listed below
• the gemini:rescue subagent in /agents

One simple first run is:

/gemini:review --background
/gemini:status
/gemini:result

Maintainer Checks

npm run verify
npm run check
npm run validate:claude
npm run release:check
npm run release:bundle
npm run release:full

npm run verify is the main maintainer preflight command and runs the test suite, the repository type-check, and release metadata validation. npm run check is kept as an alias for npm run verify. npm run validate:claude runs Claude's local marketplace validator against the repository root when Claude Code is installed locally. npm run release:full runs the full local release preflight: verify, Claude validation, and release bundle staging. npm run build type-checks the shipped runtime scripts and the checked-in release tooling. Running /gemini:* commands still requires a working Gemini CLI install and authentication state. npm run release:bundle writes the staged marketplace bundle to dist/release/gemini-cc-v<version>/, plus a tarball, SHA-256 checksum, release notes, and a release manifest in dist/release/. The release checklist is documented in RELEASE.md.

Usage

/gemini:review

Runs a normal Gemini-backed review on your current work.

[!NOTE] Code review especially for multi-file changes might take a while. It's generally recommended to run it in the background.

Use it when you want:

• a review of your current uncommitted changes
• a review of your branch compared to a base branch like main

Use --base <ref> for branch review. Use --scope working-tree to force an uncommitted review or --scope branch to compare against the detected default branch. It also supports --scope auto, --wait, and --background. It is not steerable and does not take custom focus text. Use /gemini:adversarial-review when you want to challenge a specific decision or risk area.

Examples:

/gemini:review
/gemini:review --base main
/gemini:review --scope working-tree
/gemini:review --background

This command is read-only and will not perform any changes. When run in the background you can use /gemini:status to check on the progress and /gemini:cancel to cancel the ongoing task.

/gemini:adversarial-review

Runs a steerable review that questions the chosen implementation and design.

It can be used to pressure-test assumptions, tradeoffs, failure modes, and whether a different approach would have been safer or simpler.

It uses the same review target selection as /gemini:review, including --base <ref> for branch review and --scope auto|working-tree|branch for explicit target selection. It also supports --wait and --background. Unlike /gemini:review, it can take extra focus text after the flags.

Use it when you want: