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 tamtom/image-generation-skills --skill gemini-nano-banana-2git clone --depth 1 https://github.com/tamtom/image-generation-skillsWrote 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/tamtom/image-generation-skills/gemini-nano-banana-2)<a href="https://agentmods.dev/skills/tamtom/image-generation-skills/gemini-nano-banana-2"><img src="https://agentmods.dev/badge/skills/tamtom/image-generation-skills/gemini-nano-banana-2/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/tamtom/image-generation-skills/gemini-nano-banana-2"><img src="https://agentmods.dev/badge/skills/tamtom/image-generation-skills/gemini-nano-banana-2.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00153 | $0.04225 |
| Opus 5 | $0.00077 | $0.02112 |
| Sonnet 5 | $0.00031 | $0.00845 |
| Haiku 4.5 | $0.00015 | $0.00422 |
Grade A, and why
gemini-nano-banana-2 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.
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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Nano Banana 2 - Image Generation & Editing
Generate new images or edit existing ones using Google's Gemini Nano Banana 2 model (gemini-3.1-flash-image-preview) via the Gemini API. This is the latest and most capable Gemini image model, featuring advanced reasoning ("Thinking") with controllable levels, high-fidelity text rendering, Google Web + Image Search grounding, output from 512 up to 4K resolution, and 14 aspect ratios.
Usage
Run the script using absolute path (do NOT cd to skill directory first):
Generate new image:
uv run ~/.claude/skills/gemini-nano-banana-2/scripts/generate_image.py --prompt "your image description" --filename "output.png" [--aspect-ratio 1:1|1:4|1:8|2:3|3:2|3:4|4:1|4:3|4:5|5:4|8:1|9:16|16:9|21:9] [--resolution 512|1K|2K|4K] [--output-format png|webp|jpeg] [--response-modality text-and-image|image-only] [--thinking-level minimal|high] [--google-search] [--image-search] [--yes] [--cost-threshold 0.10] [--api-key KEY]
Edit existing image:
uv run ~/.claude/skills/gemini-nano-banana-2/scripts/generate_image.py --prompt "editing instructions" --filename "output.png" --input-image "path/to/input.png" [--aspect-ratio 1:1] [--resolution 2K] [--api-key KEY]
Edit with multiple reference images (compositing/style transfer, up to 14 images):
uv run ~/.claude/skills/gemini-nano-banana-2/scripts/generate_image.py --prompt "combine the subject from first image with the style of second image" --filename "output.png" --input-image "subject.png" --input-image "style-ref.png" [--resolution 2K] [--api-key KEY]
Generate with Google Web Search grounding (real-time data):
uv run ~/.claude/skills/gemini-nano-banana-2/scripts/generate_image.py --prompt "visualize the current weather forecast for San Francisco" --filename "output.png" --google-search --aspect-ratio 16:9 [--api-key KEY]
Generate with Google Image Search grounding (visual reference from the web):
uv run ~/.claude/skills/gemini-nano-banana-2/scripts/generate_image.py --prompt "a detailed painting of a resplendent quetzal bird resting on a flower" --filename "output.png" --image-search [--api-key KEY]
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.
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.
- 12d ago First seen · 290 lines · 153 tokens per session scan A 67ab4cd71ed0
gemini-nano-banana-2 is a skill published in the GitHub repository tamtom/image-generation-skills (9 stars, last pushed 6mo ago), licensed MIT. It adds 153 tokens to every session and 4,225 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…