Borrowing it
Nothing to install: this file belongs to djbelieny/nova. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/djbelieny/nova/main/.agents/skills/nano-banana-2/SKILL.mdgit clone --depth 1 https://github.com/djbelieny/novaWrote 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/djbelieny/nova/nano-banana-2)<a href="https://agentmods.dev/skills/djbelieny/nova/nano-banana-2"><img src="https://agentmods.dev/badge/skills/djbelieny/nova/nano-banana-2/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.
<a href="https://agentmods.dev/skills/djbelieny/nova/nano-banana-2"><img src="https://agentmods.dev/badge/skills/djbelieny/nova/nano-banana-2.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.01291 |
| Opus 5 | $0.00044 | $0.00646 |
| Sonnet 5 | $0.00018 | $0.00258 |
| Haiku 4.5 | $0.00009 | $0.00129 |
Grade A, and why
nano-banana-2 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 11d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana 2 - Gemini 3.1 Flash Image Preview
Generate images with Google Gemini 3.1 Flash Image Preview via inference.sh CLI.
Quick Start
Requires inference.sh CLI (
infsh). Get installation instructions:npx skills add inference-sh/skills@agent-tools
infsh login
infsh app run google/gemini-3-1-flash-image-preview --input '{"prompt": "a banana in space, photorealistic"}'
Examples
Basic Text-to-Image
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "A futuristic cityscape at sunset with flying cars"
}'
Multiple Images
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Minimalist logo design for a coffee shop",
"num_images": 4
}'
Custom Aspect Ratio
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Panoramic mountain landscape with northern lights",
"aspect_ratio": "16:9"
}'
Image Editing (with input images)
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Add a rainbow in the sky",
"images": ["https://example.com/landscape.jpg"]
}'
High Resolution (4K)
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Detailed illustration of a medieval castle",
"resolution": "4K"
}'
With Google Search Grounding
infsh app run google/gemini-3-1-flash-image-preview --input '{
"prompt": "Current weather in Tokyo visualized as an artistic scene",
"enable_google_search": true
}'
Input Options
| Parameter | Type | Description |
|---|---|---|
prompt |
string | Required. What to generate or change |
images |
array | Input images for editing (up to 14). Supported: JPEG, PNG, WebP |
num_images |
integer | Number of images to generate |
aspect_ratio |
string | Output ratio: "1:1", "16:9", "9:16", "4:3", "3:4", "auto" |
resolution |
string | "1K", "2K", "4K" (default: 1K) |
output_format |
string | Output format for images |
enable_google_search |
boolean | Enable real-time info grounding (weather, news, etc.) |
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.
- 11d ago First seen · 167 lines · 89 tokens per session scan A 7c1abc624e84
nano-banana-2 is a skill published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 1,291 once invoked, about $0.0004 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
design
Use when the user wants the visual/experiential design of a product done systematically — a design system, a screen, a landing page, or a visual identity — grounded in researched real-world prior art and free of AI slop. Establishes/extends the design system, invokes the matching local taste skill, dispatches the…
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
image-generation
Generate images using structured prompts and optional reference images. Supports character design, scenes, product visualization, and any visual content creation. Use this skill when the user requests to generate, create, imagine, draw, or visualize images, characters, portraits, scenes, products, or any visual…
podcast-generation
Convert text content into two-host conversational podcast audio. Transforms articles, reports, documentation, or any written content into natural dialogue between male and female hosts, then synthesizes speech audio. Use this skill when the user requests to generate, create, or produce a podcast from text content -…
video-generation
Generate videos using structured prompts and optional reference images. Supports scene generation with camera, dialogue, and audio specifications. Use this skill when the user requests to generate, create, or produce videos, clips, animations, or motion content -- even if they just say "make a video of X" or "animate…
businesses
Business lifecycle skill (DOMAIN-AGNOSTIC). Creates, lists, inspects, validates, and migrates businesses — autonomous multi-agent organizations — following the Business Protocol v2 (v1 businesses still load unchanged). Works for ANY domain: marketing, healthcare, engineering, legal, real-estate, gaming, foodtech…