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 BlackBeltTechnology/pi-agent-dashboard --skill nano-banana-imagegengit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/nano-banana-imagegen)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/nano-banana-imagegen"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/nano-banana-imagegen/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/blackbelttechnology/pi-agent-dashboard/nano-banana-imagegen"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/nano-banana-imagegen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
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 →
- high Excessive Agency · line 33 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium MCP Rug Pull · line 37 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 75 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 92 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 98 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00088 | $0.01244 |
| Opus 5 | $0.00044 | $0.00622 |
| Sonnet 5 | $0.00018 | $0.00249 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
nano-banana-imagegen 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana Image Generation
Generate and edit images using Google's Gemini image models. This skill ships the
pi-nano-banana CLI (a TypeScript wrapper — no Python) that resolves the
GEMINI_API_KEY for you and delegates to @the-focus-ai/nano-banana.
Prerequisites
GEMINI_API_KEYset via the environment or a gitignored.envin the project or package directory (the CLI resolves it automatically).- Network access — the underlying
@the-focus-ai/nano-bananaCLI is fetched vianpx.
Quick Reference
Prefer the bundled pi-nano-banana bin (auto key resolution, output-dir creation):
# Generate a new image
pi-nano-banana "a serene mountain landscape at sunset"
# Edit an existing image
pi-nano-banana "add a hot air balloon to the sky" --file photo.jpg
# Specify output path
pi-nano-banana "a minimalist logo" --output logo.png
# Use a specific model / faster flash model
pi-nano-banana "detailed illustration" --model gemini-2.0-flash-exp
pi-nano-banana "a quick sketch" --flash
The raw CLI still works if you prefer it (npx @the-focus-ai/nano-banana "…").
For batch generation from code, import batchGenerate from
@blackbelt-technology/pi-dashboard-nano-banana/nano-banana.js.
Workflow
Step 1: Understand the Request
Before generating, clarify:
- Subject: What should be in the image?
- Style: Photorealistic, illustration, cartoon, abstract?
- Mood: Bright, dark, moody, cheerful?
- Composition: Close-up, wide shot, specific aspect ratio?
- Use case: Hero image, icon, social media, print?
Step 2: Craft an Effective Prompt
Read references/prompting-guide.md for comprehensive guidance.
Key principles:
- Be specific and descriptive
- Include style references
- Specify what you DON'T want
- Describe composition and framing
Example — Weak prompt:
"a cat"
Example — Strong prompt:
"A fluffy orange tabby cat curled up on a velvet armchair, soft afternoon sunlight streaming through a window, warm cozy interior, photorealistic style, shallow depth of field"
What ships with it
6 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.
- 9d ago First seen · 155 lines · 88 tokens per session scan A d7487a54c618
nano-banana-imagegen is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (280 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,244 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.
goga-review-plan
Verify execution plan completeness and correctness.
goga-brainstorm
Pipeline orchestrator for brainstorming the cells architecture.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.