claude-gemini

claude-gemini is a skill for Claude Code from sonichi/sutando. It costs 49 tokens per session (503 once invoked), scanned A, original, MIT.

A way to run Google's Gemini command-line tool from Claude Code, using the Gemini login or API settings already configured on the computer. It supports large repository scans, image or other media analysis, second opinions, and structured results.

In plain words
What is it for?
Use it for broad repository reviews, multimodal analysis, alternative implementation plans, and structured Gemini passes inside the current workspace.
Why use it?
It lets a developer ask another model to inspect a large codebase or review a plan without manually moving the work to another tool. Read-only mode helps keep analysis from changing project files.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Claude Code; mentions Gemini CLI.

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 skills/sonichi/sutando/claude-gemini
Any agent
npx skills add sonichi/sutando --skill claude-gemini
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code.

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 claude-gemini

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/claude-gemini.svg)](https://agentmods.dev/skills/sonichi/sutando/claude-gemini)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/claude-gemini"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/claude-gemini.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 503 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 $0.00049 $0.00503
Opus 5 $0.00024 $0.00251
Sonnet 5 $0.00010 $0.00101
Haiku 4.5 $0.00005 $0.00050

Measured 6d ago against content hash 4d07f7b098f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claude-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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/gemini-run.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/claude-gemini/SKILL.md · 60 lines

What it actually says

Claude Gemini

Delegate work from Claude Code to the local gemini CLI. This skill uses whatever authentication the Gemini CLI is already configured to use on this machine, including API key or signed-in CLI flows. It does not copy or export secrets.

Usage: /claude-gemini [prompt]

ARGUMENTS: $ARGUMENTS

When to Use

  • "Use Gemini on this repo"
  • Need a large-context scan across many files
  • Need multimodal or cross-module analysis from a second model
  • Need a read-only or JSON-formatted Gemini pass from the current workspace

Guardrails

  • Default to --approval-mode plan for read-only analysis.
  • Switch to --approval-mode auto_edit only when the user wants Gemini to make edits.
  • Keep Gemini in the same repo by changing into the target workspace before running it.
  • Prefer --output-format json or stream-json when another tool will consume the output.

Quick Checks

bash "$SKILL_DIR/scripts/gemini-run.sh" --check

Common Commands

# Read-only analysis
bash "$SKILL_DIR/scripts/gemini-run.sh" -- "Trace how tasks flow from voice input to execution"

# Explicit model selection
bash "$SKILL_DIR/scripts/gemini-run.sh" --model gemini-2.5-pro -- "Review the repo structure and identify weak points"

# Machine-readable output
bash "$SKILL_DIR/scripts/gemini-run.sh" --output-format json -- "Summarize risks in src/startup.sh"

# Allow edits when the user asked for implementation help
bash "$SKILL_DIR/scripts/gemini-run.sh" --approval-mode auto_edit -- "Implement a safer startup preflight for missing services"

If Invoked As A Slash Command

  • If ARGUMENTS is empty, explain the available modes and suggest --approval-mode plan for analysis.
  • If ARGUMENTS is present, run:
bash "$SKILL_DIR/scripts/gemini-run.sh" -- "$ARGUMENTS"
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 60 lines · 49 tokens per session scan A 4d07f7b098f6

Subscribe to this mod's changes

claude-gemini is a skill published in the GitHub repository sonichi/sutando (392 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 503 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 2026-08-30.