nano-banana

nano-banana is a skill for Claude Code from LichAmnesia/lich-skills. It costs 62 tokens per session (1,213 once invoked), scanned C, original, MIT.

An image-generation and image-editing skill using Google’s Nano Banana 2 model. It creates PNG images from text or changes an image supplied by the user.

In plain words
What is it for?
Use it to make pictures, thumbnails, cover art, posters, icons, README visuals, and slide graphics, or to change an image’s background, objects, or style.
Why use it?
It removes the need to switch to a separate image tool for quick visual work. It is intended for images, not videos, pixel-perfect interface mockups, or licensed stock photography.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the lich-skills plugin — 12 skills shipped together

Good fit Use it to make pictures, thumbnails, cover art, posters, icons, README visuals, and slide graphics, or to change an image’s background, objects, or style.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lichamnesia/lich-skills/nano-banana
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 LichAmnesia/lich-skills --skill nano-banana
Clone the repo
git clone --depth 1 https://github.com/LichAmnesia/lich-skills

Made for: Claude Code.

Or install lich-skills, the plugin that ships this one along with the rest of its 12 skills.

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 nano-banana

README.md
[![agentmods](https://agentmods.dev/badge/skills/lichamnesia/lich-skills/nano-banana/github.svg)](https://agentmods.dev/skills/lichamnesia/lich-skills/nano-banana)
Your own site
<a href="https://agentmods.dev/skills/lichamnesia/lich-skills/nano-banana"><img src="https://agentmods.dev/badge/skills/lichamnesia/lich-skills/nano-banana/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 nano-banana

Your own site · 80×15
<a href="https://agentmods.dev/skills/lichamnesia/lich-skills/nano-banana"><img src="https://agentmods.dev/badge/skills/lichamnesia/lich-skills/nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,213 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00062 $0.01213
Opus 5 $0.00031 $0.00607
Sonnet 5 $0.00012 $0.00243
Haiku 4.5 $0.00006 $0.00121

Measured 11d ago against content hash e3eb69d316c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

nano-banana scanned grade C with 2 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_image.py), 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh
skills/nano-banana/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nano Banana 2

Text-to-image and image edit via Google's Nano Banana 2 model, aka gemini-3.1-flash-image-preview. Fast, cheap, high-quality. Returns PNG.

When to use

  • User asks for an image, picture, photo, thumbnail, cover art, poster, icon, etc.
  • User provides an input image and wants it modified (background change, object removal, style swap)
  • You need a quick visual for a blog post, README, demo, or slide

When NOT to use

  • User wants a video — Nano Banana is image-only
  • User wants a pixel-perfect UI mockup — use a design tool
  • User needs a specific licensed stock photo — use a stock service

Setup

  1. Get a Gemini API key: https://aistudio.google.com/app/apikey

  2. Export it:

    export GEMINI_API_KEY="YOUR_KEY_HERE"
    # or
    export GOOGLE_API_KEY="YOUR_KEY_HERE"
    
  3. Install uv if missing:

    command -v uv || curl -LsSf https://astral.sh/uv/install.sh | sh
    

First run auto-installs google-genai and pillow via uv's inline script deps.

Generate

uv run ~/.claude/skills/lich-skills/skills/nano-banana/scripts/generate_image.py \
    --prompt "A cinematic rainy Tokyo alley, neon reflections, 35mm, low angle" \
    --filename "tokyo-alley.png" \
    --resolution 1K

Output is saved to tokyo-alley.png in the current directory unless the filename is absolute.

Edit

Pass an input image with --input-image. The model sees the image + your instruction.

uv run .../generate_image.py \
    --prompt "Remove the crowd behind the subject. Keep framing and grading unchanged." \
    --filename "cleaned.png" \
    --input-image "./portrait.png" \
    --resolution 2K

When editing, the script auto-matches output resolution to the input's dimensions unless you explicitly pass --resolution.

Flags

Flag Default Purpose
--prompt, -p required Image description or edit instruction
--filename, -f required Output path (PNG)
--input-image, -i Source image for editing
--resolution, -r 1K One of 512, 1K, 2K, 4K
--api-key, -k env Overrides GEMINI_API_KEY / GOOGLE_API_KEY
--model, -m gemini-3.1-flash-image-preview Rarely needed

Read the full file on GitHub · 144 lines

Files

What ships with it

1 file 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. 11d ago First seen · 144 lines · 62 tokens per session scan C e3eb69d316c6

Subscribe to this mod's changes

nano-banana is a skill published in the GitHub repository LichAmnesia/lich-skills (233 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,213 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

openclaw-persona-forge

A persona-design guide for OpenClaw agents, including their identity, personality, boundaries, names, and avatar prompts. OpenClaw is the specific agent platform this guide targets.

Jamkris/everything-gemini-code · 221 tokens

manim-video

Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.

Jamkris/everything-gemini-code · 54 tokens

building-canvases

Create or edit a PostHog freeform canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in PostHog and rendered by the desktop/web app. Use when a task asks to build, generate, update, or fix a standalone canvas app, or when a freeform canvas id is given as the…

PostHog/ai-plugin · 148 tokens

validating-and-publishing-canvases

Validate and publish a canvas source project safely: the source-project shape, declared capabilities, reading the current version pointer, iterating on validation diagnostics, guarded publishing with expectedcurrentversionid, staging a draft build and promoting it, waiting out the queued build, and recovering from a…

PostHog/ai-plugin · 118 tokens

cogp-klee

A visual-composition review method for examining shapes, lines, movement, rhythm, symbolism, and empty space in an image or design.

ArchSightLabs/archsight-cognition · 41 tokens

frontend-slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

Jamkris/everything-gemini-code · 63 tokens