agentmods.dev

nano-banana

nano-banana is a skill for Claude Code, Codex from pbc-os/smb-starter-kit. It costs 52 tokens per session (2,280 once invoked), scanned A, original, MIT.

A guide for creating and editing images with Google Gemini models. It can turn text descriptions into images, change existing images, remove backgrounds, and edit selected areas.

In plain words
What is it for?
Generating illustrations or other images, editing existing pictures, making transparent-background PNGs, and changing specific regions of an image.
Why use it?
It helps produce or adjust image assets without doing the work manually in an image editor. It also describes the setup and access checks needed before using the image tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is --output ./assets/ --filename subject.png.

not rated 10repo 3mo ago A scan 52 tokens original MIT

Good fit Generating illustrations or other images, editing existing pictures, making transparent-background PNGs, and changing specific regions of an image.

Compare 6 skills from other repositories ↓
View source ↗ pbc-os/smb-starter-kit
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/pbc-os/smb-starter-kit
agentmods
npx agentmods add skills/pbc-os/smb-starter-kit/nano-banana

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 nano-banana

README.md
[![agentmods](https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/nano-banana/github.svg)](https://agentmods.dev/skills/pbc-os/smb-starter-kit/nano-banana)
Your own site
<a href="https://agentmods.dev/skills/pbc-os/smb-starter-kit/nano-banana"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/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/pbc-os/smb-starter-kit/nano-banana"><img src="https://agentmods.dev/badge/skills/pbc-os/smb-starter-kit/nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,280 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 $0.00052 $0.02280
Opus 5 $0.00026 $0.01140
Sonnet 5 $0.00010 $0.00456
Haiku 4.5 $0.00005 $0.00228

Measured 12d ago against content hash 070cac7e25d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nano-banana 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/edit_image.py, scripts/generate_image.py, scripts/inpaint_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.

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/tier-4-growth/nano-banana/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nano Banana

AI image generation and editing skill powered by Google Gemini. Generates images from text prompts, edits existing images, removes backgrounds for web-ready transparent PNGs, and performs region-targeted inpainting.

Setup Verification

The agent should verify the following before using this skill:

  1. Check Python: python3 --version (requires 3.9+)
  2. Check dependencies: python3 -c "from google import genai; print('ok')" — if it fails, install: pip install -r scripts/requirements.txt
  3. Check API key: Verify GEMINI_API_KEY is available. Retrieve from your secret manager:
    • GCP: gcloud secrets versions access latest --secret=GEMINI_API_KEY
    • Or check for a .env / .env.local file in the working directory
  4. For inpainting only: Verify Vertex AI auth: gcloud auth application-default print-access-token (inpainting uses Vertex AI, not the Gemini API key)

If the API key is in a secret manager, export it before running scripts:

export GEMINI_API_KEY=$(gcloud secrets versions access latest --secret=GEMINI_API_KEY)

Capabilities

1. Text-to-Image Generation

Generate images from text descriptions.

python3 scripts/generate_image.py "a serene Japanese garden with cherry blossoms" \
  --aspect-ratio 16:9

Parameters:

  • prompt (required): Text description of the image to generate
  • --output / -o: Output directory or file path (default: current directory)
  • --filename / -f: Custom filename (default: auto-generated with timestamp)
  • --aspect-ratio / -a: Image aspect ratio (default: 1:1)
  • --model / -m: Model to use (default: gemini-2.5-flash-image)

2. Image Editing

Edit existing images with text prompts.

python3 scripts/edit_image.py "change the sky to sunset colors" \
  --images landscape.jpg

# Multiple images for consistency/reference (up to 14):
python3 scripts/edit_image.py "create a collage combining these images" \
  --images img1.png img2.png img3.png --aspect-ratio 16:9

Read the full file on GitHub · 201 lines

Files

What ships with it

8 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. 12d ago First seen · 201 lines · 52 tokens per session scan A 070cac7e25d7

Subscribe to this mod's changes

nano-banana is a skill published in the GitHub repository pbc-os/smb-starter-kit (10 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 2,280 once invoked, about $0.0003 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.

Creative and media
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens