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 skills add mgiovani/cc-arsenal --skill nanobananagit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/nanobanana)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/nanobanana"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/nanobanana/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/mgiovani/cc-arsenal/nanobanana"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/nanobanana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00163 | $0.02905 |
| Opus 5 | $0.00081 | $0.01452 |
| Sonnet 5 | $0.00033 | $0.00581 |
| Haiku 4.5 | $0.00016 | $0.00291 |
Grade A, and why
nanobanana scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nanobanana: Nano Banana Image Generation
Generate and edit images using Google's Nano Banana (Gemini image generation API). This skill handles direct image generation, iterative editing, and expert guidance for integrating the API into codebases.
Core differentiator: A prompt enhancement system that analyzes user intent and project context to craft optimized prompts before calling the API.
This is the explicit Gemini/Nano Banana path (named directly by the user): for a generic "generate an image" request with no engine named, codex-imagegen is the default generator instead.
Phase 0: Environment Check
Before anything else, verify the environment is ready.
1. Check API key:
echo "${GEMINI_API_KEY:0:10}..." # Show first 10 chars only (security)
If GEMINI_API_KEY is empty or unset:
- Read
references/integration-guide.md(the setup section) - Present setup instructions to the user
- Stop here until the key is configured
2. Check uv is available:
uv --version 2>&1
If uv is not installed, direct the user to https://docs.astral.sh/uv/getting-started/installation/ and stop. uv handles dependency installation automatically via PEP 723 inline metadata: no manual pip install needed.
Phase 1: Understand Intent & Detect Mode
Mine the conversation for:
- Subject/scene: What is the image of?
- Purpose: What is it for? (hero image, icon, mockup, blog post, etc.)
- Style: Photorealistic, illustration, minimalist, etc.
- Technical requirements: Aspect ratio, resolution, specific dimensions
- Mood/atmosphere: Energetic, calm, professional, playful, etc.
Detect Mode
Expert Integration Mode: if the user wants to integrate Nano Banana into their codebase (e.g., "how do I add image generation to my app", "show me the API", "I'm building a feature that generates images"):
- Read
references/integration-guide.md - Provide SDK examples, authentication patterns, and production best practices
- Skip to guidance, do not call the API
What ships with it
7 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.
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 · 285 lines · 163 tokens per session scan A 502040a14a4c
nanobanana is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 2d ago), licensed MIT. It adds 163 tokens to every session and 2,905 once invoked, about $0.0008 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
heygen
Agent-callable HeyGen tools — generate AI avatar videos, translate and lip-sync videos, synthesize speech, and clone or browse voices and avatars. Use when the user mentions HeyGen or wants to create, translate, or check the status of AI videos, or to generate or clone a voice — including requests that don't name…
runway
Agent-callable Runway tools — generate images and video from text or images, edit and upscale media, animate characters, generate speech and sound effects, and run marketing recipes, plus track generation jobs. Use when the user mentions Runway or wants to generate, edit, or upscale AI media, even if they don't name…
elevenlabs
Agent-callable ElevenLabs tools — generate spoken audio from text, create sound effects and multi-speaker dialogue, re-voice and clean up audio, transcribe audio and video, design synthetic voices, and manage voices, history, and quota. Use when the user mentions ElevenLabs or wants AI audio work — text to speech…
atmos-cast
Atmos cast recording and rendering: atmos cast play/render, output-format inference (gif/mp4/html/ascii/png/jpg/jpeg), the --cast/ATMOSCAST auto-recording flag, workflow type: cast (steps/session modes) and type: simulate step types, and committed .cast screengrabs.
cli-anything-photoshop
A command-line tool that controls Adobe Photoshop through Windows automation. It can work with Photoshop documents, layers, selections, text, image adjustments, and exports.
youtube
Use whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation. Manages videos, playlists, comments, captions, subscriptions, thumbnails, analytics, and more.