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 memorysaver/dotfiles --skill nanobana-promptsgit clone --depth 1 https://github.com/memorysaver/dotfilesWrote 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/memorysaver/dotfiles/nanobana-prompts)<a href="https://agentmods.dev/skills/memorysaver/dotfiles/nanobana-prompts"><img src="https://agentmods.dev/badge/skills/memorysaver/dotfiles/nanobana-prompts/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/memorysaver/dotfiles/nanobana-prompts"><img src="https://agentmods.dev/badge/skills/memorysaver/dotfiles/nanobana-prompts.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 | $0.00172 | $0.00963 |
| Opus 5 | $0.00086 | $0.00481 |
| Sonnet 5 | $0.00034 | $0.00193 |
| Haiku 4.5 | $0.00017 | $0.00096 |
Grade A, and why
nanobana-prompts 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 9d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana Pro Prompt Crafting
Write excellent prompts for Nano Banana Pro (and compatible models) by applying proven structural patterns from 12,400+ community prompts.
References
Load these files when needed — do not load all of them upfront:
- references/prompt-structure.md — the universal 9-layer prompt structure (Subject → Outward). Load before crafting any prompt.
- references/styles.md — style descriptors and keywords for 16 styles (photography, anime, 3D render, etc.). Load when the user picks a style or needs help choosing one.
- references/technical-specs.md — camera, lighting, composition, rendering, and resolution keywords. Load when adding technical polish to a prompt.
- references/example-prompts.md — complete example prompts organized by category. Load when the user wants to see examples or needs a starting point.
Workflow Routing
workflows/craft-prompt.md — Creating a new prompt from scratch
- "Write me a prompt for..."
- "I need a prompt for a YouTube thumbnail / social post / character"
- "Help me describe [concept] for image generation"
- "Create a Nano Banana prompt for..."
- Any request to write a new image generation prompt from nothing
workflows/refine-prompt.md — Improving an existing prompt
- "Improve this prompt: [prompt text]"
- "This prompt isn't giving good results"
- "Make this prompt more detailed / specific / vivid"
- "What's wrong with this prompt?"
- "Add more detail to this prompt"
- Any request where the user already has prompt text and wants it better
workflows/adapt-style.md — Changing the style of a prompt
- "Convert this prompt to anime style"
- "Make this more cinematic / photorealistic / 3D"
- "I have a prompt for photography but I want it as an illustration"
- "Restyle this prompt for [target style]"
- Any request to keep the same subject/scene but change the visual style
What ships with it
9 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.
- evals/evals.json 8.6 KB
- references/example-prompts.md 11 KB
- references/prompt-structure.md 8.6 KB
- references/styles.md 6.1 KB
- references/technical-specs.md 6.7 KB
- workflows/adapt-style.md 2.2 KB
- workflows/craft-prompt.md 3.5 KB
- workflows/describe-to-prompt.md 2.3 KB
- workflows/refine-prompt.md 2.2 KB
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.
- 9d ago First seen · 77 lines · 172 tokens per session scan A 0ab35488d1f3
nanobana-prompts is a skill published in the GitHub repository memorysaver/dotfiles (7 stars, last pushed today), licensed MIT. It adds 172 tokens to every session and 963 once invoked, about $0.0009 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
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
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.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.