gemini-review

gemini-review is a command for Claude Code from bgreenwell/claude-plugins. It costs 37 tokens per session (1,869 once invoked), scanned A, original, MIT.

A command that asks Google Gemini to review selected files, or the files currently staged in Git when no files are specified.

In plain words
What is it for?
Use it for a quick review of individual files, file patterns, directories, or staged changes, choosing Gemini's faster Flash model or more thorough Pro model.
Why use it?
It provides an independent review of code and lets you focus the review on areas such as security, performance, maintainability, or testing.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Gemini CLI.

Part of the gemini-review plugin — 2 commands shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/bgreenwell/claude-plugins/gemini-review
Clone the repo
git clone --depth 1 https://github.com/bgreenwell/claude-plugins

Made for: Claude Code.

Or install gemini-review, the plugin that ships this one along with the rest of its 2 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for gemini-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/bgreenwell/claude-plugins/gemini-review.svg)](https://agentmods.dev/commands/bgreenwell/claude-plugins/gemini-review)
Your own site
<a href="https://agentmods.dev/commands/bgreenwell/claude-plugins/gemini-review"><img src="https://agentmods.dev/badge/commands/bgreenwell/claude-plugins/gemini-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00037 $0.01869
Opus 5 $0.00018 $0.00934
Sonnet 5 $0.00007 $0.00374
Haiku 4.5 $0.00004 $0.00187

Measured 5d ago against content hash 2d7995a303b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

gemini-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

gemini-review/commands/gemini-review.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gemini-review Command

Quick, explicit Gemini review with sensible defaults and structured output.

Syntax

/gemini-review [file-pattern] [--model flash|pro] [--focus area]

Arguments

file-pattern (optional)

  • File path, glob pattern, or directory to review
  • If omitted: Reviews git staged files (git diff --cached --name-only)
  • Examples: src/auth/*, src/auth/login.js, tests/*.test.js

--model (optional)

  • Model to use for review
  • Options: flash (fast, default) or pro (thorough)
  • Default: gemini-2.5-flash

--focus (optional)

  • Specific area to focus review on
  • Examples: security, performance, maintainability, testing
  • Default: General code quality review

How It Works

When user invokes this command:

  1. Parse Arguments

    • Extract file pattern (or use git staged files)
    • Determine model (Flash or Pro)
    • Identify focus area if specified
  2. Validate Files

    • Check gemini-cli is installed and authenticated
    • Verify files exist and are accessible
    • Filter out binary/build files
  3. Construct Prompt

    • Build focused Gemini prompt based on review type
    • Include @ file references
    • Add focus-specific criteria if --focus provided
  4. Execute Review

    • Call gemini-cli with --output-format json
    • Use specified model (--model flag)
    • Capture structured JSON response
  5. Parse Results

    • Extract review findings from JSON
    • Extract token usage statistics
    • Parse for errors, warnings, suggestions
  6. Format Output

    • Display file-by-file breakdown
    • Show severity levels (✓ OK, ⚠ Warning, ❌ Error)
    • Present actionable recommendations
    • Show token usage at bottom

Examples

Review Git Staged Files

/gemini-review

Behavior: Reviews all files in git staging area

Review Specific Files

/gemini-review src/auth/login.js src/auth/session.js

Behavior: Reviews just those two files

Review with Pattern

/gemini-review src/auth/*

Behavior: Reviews all files in src/auth/

Read the full file on GitHub · 300 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 300 lines · 37 tokens per session scan A 2d7995a303b8

Subscribe to this mod's changes

gemini-review is a command published in the GitHub repository bgreenwell/claude-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 37 tokens to every session and 1,869 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.