Nano Banana is a Gemini CLI extension for creating, editing, restoring, and managing image files through natural-language requests. Developers use it from Gemini CLI with supported Gemini image-generation models and an API key. The catalogue instruction supports operating this extension.
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 agentmods add instructions/gemini-cli-extensions/nanobanana/gemini-mdgit clone --depth 1 https://github.com/gemini-cli-extensions/nanobananaWrote 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/instructions/gemini-cli-extensions/nanobanana/gemini-md)<a href="https://agentmods.dev/instructions/gemini-cli-extensions/nanobanana/gemini-md"><img src="https://agentmods.dev/badge/instructions/gemini-cli-extensions/nanobanana/gemini-md.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 | $0.01037 | $0.01037 |
| Opus 5 | $0.00518 | $0.00518 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
nanobanana GEMINI.md 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 6d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- mcp-nanobanana GEMINI.md — 95% identical, 4 lines differ
- mcp-nanobanana AGENTS.md — 95% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana - Gemini Image Generation Instructions
This file contains specific instructions for the Nano Banana 2 (gemini-3.1-flash-image-preview) model when working with the Nano Banana extension for image generation, editing, and restoration.
Core Generation Principles
1. Precise Count Adherence
CRITICAL: When a user specifies a --count=N parameter, you MUST generate exactly N images, no more and no less. This is a strict requirement:
--count=3means exactly 3 images--count=6means exactly 6 images- If no count is specified, generate 1 image (default)
- Never generate fewer images than requested due to "similar results" or other reasons
2. Style and Variation Compliance
Always respect user-specified design preferences:
--styles: Apply the exact artistic styles requested (watercolor, oil-painting, sketch, photorealistic, etc.)--variations: Implement the specific variation types (lighting, angle, color-palette, composition, mood, season, time-of-day)- Maintain the essence of the original prompt while applying the requested stylistic changes
- When multiple styles are requested, ensure each image distinctly represents its assigned style
3. Visual Consistency for Story Commands
When processing /story commands, maintain strict visual consistency across all generated images:
- Color Palette: Use the same or very similar color schemes across all story frames
- Typography: Keep fonts, text sizes, and formatting identical throughout the sequence
- Art Style: Maintain consistent artistic approach (same level of detail, shading, line work)
- Character Design: Keep character appearances consistent (clothing, proportions, features)
- Visual Theme: Preserve the same visual mood and aesthetic throughout the story
- Layout: Use similar composition and framing approaches for coherence
4. Text Accuracy and Quality
When generating text within images, prioritize accuracy and professionalism:
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.
- 6d ago First seen · 124 lines · 1,037 tokens per session scan A 288aa0cf61b8
nanobanana GEMINI.md is an instructions file published in the GitHub repository gemini-cli-extensions/nanobanana (1,126 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,037 tokens to every session, about $0.0052 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.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).