gemini

A command for sending a question or code-related task to the Google Gemini command-line tool. Gemini is Google's command-line AI assistant, and the command can ask it to review, explain, or improve code.

In plain words
What is it for?
Use it for prompts such as reviewing authentication code, explaining an error-handling pattern, suggesting refactoring, or examining security implications.
Why use it?
It lets a developer request a second AI system's analysis without manually preparing the command or routing options. The input does not guarantee that Gemini is installed or authenticated.

Command

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/gopherguides/gopher-ai/gemini
Clone the repo
git clone --depth 1 https://github.com/gopherguides/gopher-ai
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,606 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 $0.00007 $0.01606
Opus 5 $0.00003 $0.00803
Sonnet 5 $0.00001 $0.00321
Haiku 4.5 $0.00001 $0.00161

Measured 2d ago against content hash 8cfe1a955f2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gemini 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 2d 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.

plugins/llm-tools/commands/gemini.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate to Gemini

If $ARGUMENTS is empty or not provided:

Display usage information and ask for input:

This command delegates tasks to Google Gemini CLI for analysis and code review.

Usage: /gemini <prompt>

Examples:

Command Description
/gemini review the auth implementation Code review
/gemini explain this error handling pattern Code explanation
/gemini suggest improvements for this function Refactoring advice
/gemini what are the security implications here Security analysis

Available Gemini Routing:

Option Behavior
Auto (recommended) Let the Gemini CLI route to the best current model
Custom model ID Ask for an exact model ID and pass it with -m

Ask the user: "What would you like Gemini to analyze?"


If $ARGUMENTS is provided:

Run a task using Google Gemini CLI with the prompt: $ARGUMENTS

1. Check Prerequisites

First, verify Gemini CLI is installed:

which gemini

If not found, inform the user:

Gemini CLI is not installed. Install it with:

npm install -g @google/gemini-cli

Then authenticate: gemini (will prompt for Google login) or set GEMINI_API_KEY

Then ask if they want to proceed after installation or use a different LLM (/codex or /ollama).

2. Select Model

Ask the user how Gemini should choose a model:

Option Description
Auto (recommended) Use Gemini CLI Auto routing; pass no -m flag
Custom model ID Ask for an exact Gemini model ID; pass it with -m

Default: Auto

If the user chooses Custom model ID, ask for the model ID and store it as MODEL. Otherwise leave MODEL unset or empty.

3. Include Context (Optional)

Ask the user: "Do you want to include additional context?"

Option Description
No Run with prompt only
File context Include contents of specific file(s)
Diff context Include git diff output
Session context Include summary of current Claude session

Read the full file on GitHub · 196 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. 2d ago First seen · 196 lines · 7 tokens per session scan A 8cfe1a955f2e

Subscribe to this mod's changes

gemini is a command published in the GitHub repository gopherguides/gopher-ai (21 stars, last pushed 2d ago), licensed MIT. It adds 7 tokens to every session and 1,606 once invoked, about $0.0000 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 2026-08-30.