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.
npx skills add azmym/gemini-plugin --skill gemini-image-gengit clone --depth 1 https://github.com/azmym/gemini-pluginWrote 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.
[](https://agentmods.dev/skills/azmym/gemini-plugin/gemini-image-gen)<a href="https://agentmods.dev/skills/azmym/gemini-plugin/gemini-image-gen"><img src="https://agentmods.dev/badge/skills/azmym/gemini-plugin/gemini-image-gen.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.00787 |
| Opus 5 | $0.00019 | $0.00394 |
| Sonnet 5 | $0.00008 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
gemini-image-gen 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Image Gen
Use this skill to generate images via Gemini's native image generation capability or Google's Imagen 4 model. Both produce high-quality raster images suitable for UI mockups, marketing assets, and visual prototyping.
When to use this skill
- UI mockups: Quickly visualize a screen layout, dashboard design, or component arrangement.
- Hero images: Generate a compelling banner or header image for a landing page or blog post.
- Product shots: Create lifestyle or conceptual product imagery.
- Infographic frames: Generate illustrative backgrounds or iconographic elements for data visualizations.
- Concept illustrations: Visualize an architectural metaphor, system diagram in artistic form, or abstract concept.
- Avatar and icon generation: Create custom icons, mascots, or profile images.
MCP tools
| Tool | Purpose |
|---|---|
gemini_generate_image |
Gemini native image generation (Nano Banana model, fast, conversational quality) |
gemini_generate_image_imagen |
Imagen 4 (higher fidelity, better photorealism and typography, slightly slower) |
Choosing between the two tools
| Need | Tool |
|---|---|
| Quick prototyping, iterative concepts, low cost | gemini_generate_image |
| High-fidelity output, photorealistic, sharp text in image | gemini_generate_image_imagen |
Usage pattern
Quick concept with native Gemini image generation
{
"tool": "gemini_generate_image",
"arguments": {
"prompt": "A minimal dashboard UI showing a line chart, three KPI cards, and a sidebar navigation. Clean, modern, dark mode, flat design.",
"aspect_ratio": "16:9"
}
}
High-fidelity product shot with Imagen 4
{
"tool": "gemini_generate_image_imagen",
"arguments": {
"prompt": "A sleek mobile app screenshot showing a fitness tracking screen with a circular progress ring, step count, and heart rate graph. iOS-style, white background, soft shadows.",
"aspect_ratio": "9:16",
"number_of_images": 2
}
}
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.
- 8d ago First seen · 79 lines · 39 tokens per session scan A ffae65a42073
gemini-image-gen is a skill published in the GitHub repository azmym/gemini-plugin (1 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 787 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.
Other skills, from other repositories
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.
yt-dlp-downloader
Generate and run yt-dlp download commands with probe-driven format selection, safe output naming, retry defaults, and structured execution reports. Use when users want to download videos, extract audio, fetch playlists, grab subtitles, handle authenticated/age-gated content, or download live streams. Covers single…
gemini-imagegen
Use when the user asks to generate, create, draw, edit, or restyle an image, or when a task needs image assets — logos, icons, illustrations, hero images, textures, photos, placeholder art, social/OG cards. Claude cannot produce raster images; a Gemini session via the agy (Antigravity) CLI has a generateimage tool…
nanobanana-adc
Generate images with Google's Nano Banana Pro (Gemini 3 Pro Image) using Application Default Credentials (ADC) or a GEMINIAPIKEY. Use this when the user asks to create, generate, draw, or render an image via Google / Vertex AI / Gemini.
grok-prompting
Internal guidance for composing Grok prompts for coding, review, diagnosis, and research tasks inside the Grok Claude Code plugin.
pasteup
Pipeline for halftone paper-collage and stop-motion-graphic ads. Decodes a reference image into a field-editable JSON spec, generates cut-out elements directly on the Gemini image API (nano-banana line), then assembles them into build-from-empty stop motion with code: a bundled Python compositor by default, or…