image-generation

image-generation is a skill for Claude Code, Codex from JimothySnicket/gemini-image-mcp. It costs 18 tokens per session (1,806 once invoked), scanned A, original, MIT.

A skill that tells an agent how to generate and edit images through Google Gemini using an MCP image server. It also describes continuing an image-editing session across multiple requests.

In plain words
What is it for?
Creating visual assets, editing existing images, refining results over several turns, and saving outputs in an organized way.
Why use it?
It provides a defined workflow for turning image requests into generated or revised files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Creating visual assets, editing existing images, refining results over several turns, and saving outputs in an organized way.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jimothysnicket/gemini-image-mcp/image-generation
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.

Any agent
npx skills add JimothySnicket/gemini-image-mcp --skill image-generation
Clone the repo
git clone --depth 1 https://github.com/JimothySnicket/gemini-image-mcp

Made for: Claude Code, Codex.

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 image-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/jimothysnicket/gemini-image-mcp/image-generation/github.svg)](https://agentmods.dev/skills/jimothysnicket/gemini-image-mcp/image-generation)
Your own site
<a href="https://agentmods.dev/skills/jimothysnicket/gemini-image-mcp/image-generation"><img src="https://agentmods.dev/badge/skills/jimothysnicket/gemini-image-mcp/image-generation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for image-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/jimothysnicket/gemini-image-mcp/image-generation"><img src="https://agentmods.dev/badge/skills/jimothysnicket/gemini-image-mcp/image-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,806 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00018 $0.01806
Opus 5 $0.00009 $0.00903
Sonnet 5 $0.00004 $0.00361
Haiku 4.5 $0.00002 $0.00181

Measured 9d ago against content hash f3634614d26f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

image-generation 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 9d 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.

skills/image-generation/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Generation Skill

You have access to Google Gemini image generation via the generate_image MCP tool.

When to Use

Generate images when the user:

  • Asks for an image, illustration, or visual asset
  • Needs a hero image, placeholder, icon, or background for a project
  • Asks to edit, modify, or iterate on an existing image
  • Mentions creating visual content of any kind

How to Use

Call the generate_image tool. The behaviour depends on the parameters:

Text-to-Image (no input images)

{
  "prompt": "A modern dashboard UI with dark theme and blue accent colours",
  "aspectRatio": "16:9",
  "resolution": "2K",
  "filename": "dashboard-hero",
  "subfolder": "landing-page"
}

Image Editing (with input images)

{
  "prompt": "Change the background to a sunset over water",
  "images": ["./src/assets/hero.png"],
  "aspectRatio": "16:9"
}

Multi-Turn Refinement

The tool returns a sessionId with every response. Pass it back to continue editing:

{
  "prompt": "Make the colours warmer and add more contrast",
  "sessionId": "session-1711929600000-a1b2c3"
}

This preserves the conversation history so the model remembers what it generated.

Output Organization

  • Use filename to give images meaningful names (e.g. hero-banner instead of gemini-1711929600000-a1b2c3)
  • Use subfolder to group related assets (e.g. landing-page, blog-posts)
  • Duplicate filenames are auto-versioned: hero.png, hero-v2.png, hero-v3.png
  • When generating assets for a project, save them directly to the project's asset directory using outputDir

Image Processing (process_image)

Use process_image for local, free operations that don't need AI:

Common Pipelines

Subject on a specific background (canvas approach — recommended): Create a solid colour canvas with process_image, then feed it to generate_image as input. Gemini places the subject with correct lighting and reflections — no chroma key needed.

// Step 1: generate_image with a canvas image as input
{
  "prompt": "Place a yellow rubber duck on this background. Product photography, studio lighting, centered.",
  "images": ["./canvas-white.png"],
  "filename": "duck-on-white"
}

This is better than chroma key for yellow, green, or glass/reflective subjects.

Read the full file on GitHub · 160 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. 9d ago First seen · 160 lines · 18 tokens per session scan A f3634614d26f

Subscribe to this mod's changes

image-generation is a skill published in the GitHub repository JimothySnicket/gemini-image-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 18 tokens to every session and 1,806 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

ai-studio-image

Geracao de imagens humanizadas via Google AI Studio (Gemini). Fotos realistas estilo influencer ou educacional com iluminacao natural e imperfeicoes sutis.

sickn33/agentic-awesome-skills · 38 tokens

ima2

Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.

lidge-jun/ima2-gen · 25 tokens

videoagent-image-studio

Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, with zero setup. Use when you want to generate any image without worrying about API keys.

pexoai/pexo-skills · 53 tokens

image-generation

Optimizes image generation prompts using Subject-Context-Style structure. Use this skill when generating images, creating illustrations, photos, visual assets, editing images, or crafting prompts for any image generation model.

shinpr/mcp-image · 43 tokens

crossgen-artist

Use CrossGen to plan and execute image generation, editing, inpainting, model selection, media-aware job monitoring, Gallery inspection, and asset export through MCP or its JSON CLI.

Bliveren/CrossGen · 41 tokens

model-aware-image-prompt-engineer

Model-aware image prompt engineering for any agent or image generation workflow. Use when writing, improving, translating, debugging, or evaluating prompts for OpenAI image models, Gemini Nano Banana, Midjourney, FLUX, Qwen-Image, Z-Image, Stable Diffusion, SDXL, Pony, Illustrious, NoobAI, Animagine, HunyuanImage…

Emily2040/nano-banana-image-skill · 210 tokens