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 OpenMinis/MinisSkills --skill nano-bananagit clone --depth 1 https://github.com/OpenMinis/MinisSkillsWrote 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/openminis/minisskills/nano-banana)<a href="https://agentmods.dev/skills/openminis/minisskills/nano-banana"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/nano-banana/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/openminis/minisskills/nano-banana"><img src="https://agentmods.dev/badge/skills/openminis/minisskills/nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 93 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
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 | $0.00083 | $0.01518 |
| Opus 5 | $0.00042 | $0.00759 |
| Sonnet 5 | $0.00017 | $0.00304 |
| Haiku 4.5 | $0.00008 | $0.00152 |
Grade B, and why
nano-banana scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Run any script with: How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana — Image Generation Skill
Generate or edit images locally using the Google Gemini image generation API (a.k.a. Nano Banana).
Quick Workflow
- Check environment (API key + dependencies)
- Identify the mode: text-to-image / image editing / batch generation
- Choose the right model
- Use the bundled scripts directly — no need to rewrite them
- Run the script and save output to
/var/minis/attachments/ - Display the result inline in the conversation
Environment Setup
Check API Key
source /etc/profile && echo $GEMINI_API_KEY | head -c 10
⚠️ Always run
source /etc/profilefirst — environment variables are stored there and won't be available otherwise.
If not set, direct the user to Google AI Studio to obtain a key, then:
echo 'export GEMINI_API_KEY="your_key_here"' >> /etc/profile
Check Dependencies
pip show google-genai pillow 2>&1 | grep -E "^Name|not found"
If missing:
pip install google-genai pillow
Model Selection
| Model | Model ID | Best For |
|---|---|---|
| Nano Banana 2 (recommended) | gemini-3.1-flash-image-preview |
Fast, high quality, 2K support — default choice |
| Nano Banana Pro | gemini-3-pro-image-preview |
Complex prompts, professional assets, precise text rendering |
| Nano Banana (original) | gemini-2.5-flash-image |
Ultra-low latency, simple tasks |
Default to gemini-3.1-flash-image-preview unless the user explicitly requests another version.
⚠️ Known API Pitfalls
1. Aspect ratio / resolution config
❌ Wrong (old API, throws AttributeError):
# types.ImageGenerationConfig does not exist!
image_generation_config=types.ImageGenerationConfig(aspect_ratio="16:9")
✅ Correct:
config=types.GenerateContentConfig(
response_modalities=["IMAGE"],
image_config=types.ImageConfig(
aspect_ratio="16:9", # options: 1:1, 4:3, 3:4, 16:9, 9:16
image_size="2K", # options: 1K, 2K (default: 1K)
),
)
What ships with it
3 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 · 167 lines · 83 tokens per session scan B 5ef6fe6c6884
nano-banana is a skill published in the GitHub repository OpenMinis/MinisSkills (409 stars, last pushed 7d ago), licensed MIT. It adds 83 tokens to every session and 1,518 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.