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 DojoCodingLabs/nanobanana-mcp --skill image-promptinggit clone --depth 1 https://github.com/DojoCodingLabs/nanobanana-mcpWrote 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/dojocodinglabs/nanobanana-mcp/image-prompting)<a href="https://agentmods.dev/skills/dojocodinglabs/nanobanana-mcp/image-prompting"><img src="https://agentmods.dev/badge/skills/dojocodinglabs/nanobanana-mcp/image-prompting/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/dojocodinglabs/nanobanana-mcp/image-prompting"><img src="https://agentmods.dev/badge/skills/dojocodinglabs/nanobanana-mcp/image-prompting.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 | $0.00044 | $0.00518 |
| Opus 5 | $0.00022 | $0.00259 |
| Sonnet 5 | $0.00009 | $0.00104 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
image-prompting 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.
What it actually says
Image Prompting Best Practices
When helping users generate or edit images with nanobanana, apply these guidelines.
Prompt Structure for Generation
A strong image prompt follows this pattern: [Subject] + [Style] + [Composition] + [Lighting/Mood] + [Details]
Example: "A cozy coffee shop interior, watercolor illustration style, wide angle view, warm golden lighting, with plants on shelves and a cat sleeping on a chair"
Model Selection Guide
nanobanana supports three Gemini models via the NANOBANANA_MODEL env var:
| Model | Best For |
|---|---|
gemini-2.5-flash-image (default) |
Fast generation, prototyping, high-volume work |
gemini-3-pro-image-preview |
Complex prompts, text rendering in images, high quality |
gemini-3.1-flash-image-preview |
Latest features, advanced capabilities |
Recommend model changes when appropriate:
- User needs text in the image -> suggest Pro
- User is iterating rapidly -> stick with Flash (default)
- User wants highest quality for final output -> suggest Pro
Editing Best Practices
When using edit_image or continue_editing:
- Be specific about what to change: "Make the sky more orange" not "improve the colors"
- Reference specific areas: "Add a tree in the bottom-left corner"
- For style transfer, use reference images via the
referenceImagesparameter - Each edit creates a new file -- the original is always preserved
Constraints
- Prompts over 10,000 characters will be rejected
- Image files must be under 20MB
- Supported input formats: JPEG, PNG, WebP, GIF
- Output is always PNG
- File paths must resolve within
$HOMEor$TMPDIR(security constraint) - Images are saved to
~/nanobanana-images/
Iterative Workflow
The most effective image workflow is:
- Generate a base image with a detailed prompt
- Use
continue_editingfor incremental refinements - Each iteration should address ONE specific change
- If the result diverges too far, start fresh with
generate_image
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 · 59 lines · 44 tokens per session scan A 062f5299d2d5
image-prompting is a skill published in the GitHub repository DojoCodingLabs/nanobanana-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 518 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 2026-08-31.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…