A workflow for generating new images or editing existing ones with Google Gemini Nano Banana Pro, using text prompts and optional reference images.

Use it to create or revise diagrams, illustrations, posters, covers, product images, and other visual assets.

It gives image tasks a repeatable command-line process and saves the generated images and any accompanying text locally.

nano-banana — Skill for Claude Code and Codex by jimezsa

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 jimezsa/opencolab --skill nano-banana

Clone the repo

git clone --depth 1 https://github.com/jimezsa/opencolab

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jimezsa/opencolab/nano-banana/github.svg)](https://agentmods.dev/skills/jimezsa/opencolab/nano-banana)

Your own site

<a href="https://agentmods.dev/skills/jimezsa/opencolab/nano-banana"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jimezsa/opencolab/nano-banana"><img src="https://agentmods.dev/badge/skills/jimezsa/opencolab/nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,391 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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.01391
Opus 5	$0.00016	$0.00696
Sonnet 5	$0.00007	$0.00278
Haiku 4.5	$0.00003	$0.00139

Measured 11d ago against content hash e1faa8cf9310, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/nano_banana.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.

projects/SKILLS/nano-banana/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nano Banana Pro Skill

Use this skill when the user wants image generation or image editing with Google Gemini, especially for:

paper architecture diagrams,
figure redraws and cleanups,
annotated illustrations,
posters, covers, assets, and product shots,
edits to an existing image while preserving the important parts.

This skill defaults to Nano Banana Pro (gemini-3-pro-image-preview), which Google documents as the professional image model for complex instructions and high-fidelity asset production.

Mission

Given a prompt and zero or more reference images:

Generate a new image or edit an existing one with Gemini.
Save every returned image locally.
Save any accompanying model text next to the image outputs.
Keep the workflow deterministic and scriptable from the terminal.

Prerequisites

python3 is installed and available in PATH.
google-genai is installed:

python3 -m pip install google-genai

Network access is available when the Gemini request runs.

Hard Requirements

Use projects/SKILLS/nano-banana/scripts/nano_banana.py for the API call so key loading stays consistent with the repo.
Default to gemini-3-pro-image-preview unless the user explicitly wants a cheaper or faster model.
Save generated images in the current project folder under images/, not under artifacts/.
If the generated image should be sent back to Telegram, emit a raw @telegram-file {"kind":"photo","file":"<path>","caption":"optional"} line on its own line after generation. Do not wrap it in backticks or code fences. Keep the JSON on one line, keep kind as photo (never image/png/jpg), and on Windows write the path with forward slashes.
For edits, pass the existing image with --input and tell the model exactly what must stay unchanged.
For diagrams, specify the layout, labels, arrow directions, grouping, legend, and aspect ratio explicitly.
When exact text matters, write the exact text in the prompt and keep it short.
Do not assume the model inferred the paper structure correctly if the diagram is research-critical; inspect the generated image afterward.

Read the full file on GitHub · 145 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.

scripts/nano_banana.py 11 KB runs code

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.

11d ago First seen · 145 lines · 33 tokens per session scan A e1faa8cf9310

Subscribe to this mod's changes

nano-banana is a skill published in the GitHub repository jimezsa/opencolab (11 stars, last pushed 28d ago), licensed MIT. It adds 33 tokens to every session and 1,391 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 2026-08-30.

Creative and media agent-skills ai ai-agents automation deep-research search

skin-creator

Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.

netease-youdao/LobsterAI · 48 tokens

bilibili_search

Search for videos on Bilibili using keyword queries generated from user interests.

whiteguo233/OpenBiliClaw · 20 tokens

canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

netease-youdao/LobsterAI · 59 tokens

nano-banana