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 pigfoot/claude-code-hubs --skill nano-bananagit clone --depth 1 https://github.com/pigfoot/claude-code-hubsWrote 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/pigfoot/claude-code-hubs/nano-banana)<a href="https://agentmods.dev/skills/pigfoot/claude-code-hubs/nano-banana"><img src="https://agentmods.dev/badge/skills/pigfoot/claude-code-hubs/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/pigfoot/claude-code-hubs/nano-banana"><img src="https://agentmods.dev/badge/skills/pigfoot/claude-code-hubs/nano-banana.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 | $0.00042 | $0.01823 |
| Opus 5 | $0.00021 | $0.00911 |
| Sonnet 5 | $0.00008 | $0.00365 |
| Haiku 4.5 | $0.00004 | $0.00182 |
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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
| 5. Present | Show prompt with explanation and variations | How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana
Unified image generation workflow using a fixed Python script with JSON configuration. Eliminates AI hallucinations by avoiding dynamic code generation.
Two modes:
- Unified Generation: detailed prompt → write JSON config → run
generate_images.py - Interactive Prompting: vague prompt or "help me craft" → guide user, then generate
When to Use
- Image generation ("draw", "create", "generate"), slides, presentations
- Image editing with AI
- Prompt help ("help me craft", "improve my prompt")
- Brand styles ("use trendlife style", "notebooklm style")
- Reproducible generation ("use seed 42", "regenerate that image")
Mode selection
- Interactive Prompting: prompt help requested OR prompt is <5 words
- Unified Generation: detailed prompt provided
🚨 CRITICAL: API Routing
The script picks the API based on IMAGE_GEN_MODEL and reference_image:
| Condition | API | Endpoint |
|---|---|---|
gpt-image-2, no reference_image, no TrendLife featured |
client.images.generate() |
POST /images/generations |
gpt-image-2 + reference_image |
client.images.edit() |
POST /images/edits |
gpt-image-2 + style: "trendlife" + layout: "featured" |
client.images.edit() (logo as image) |
POST /images/edits |
| Gemini or other | client.chat.completions.create() |
POST /chat/completions |
gpt-image-2: Always uses quality="low" — other values timeout or return 400. Seed and temperature
unsupported (silently ignored, one warning per job).
Gemini (gemini-3-pro-image, gemini-3.1-flash-image): use chat.completions with
extra_body={"response_modalities": ["IMAGE"]}.
client.chat.completions.create(
model=os.environ.get("IMAGE_GEN_MODEL") or "gemini-3-pro-image",
messages=[{"role": "user", "content": prompt}],
seed=seed,
temperature=temperature,
extra_body={"response_modalities": ["IMAGE"]},
)
IMAGE_GEN_MODEL: NEVER override
If IMAGE_GEN_MODEL is set, use it EXACTLY as-is. Custom endpoints have their own model names —
do not append suffixes like -preview. Only choose a default when the env var is unset.
What ships with it
19 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.
- .gitattributes 150 B
- .gitignore 261 B
- assets/logos/README.md 2.1 KB
- assets/logos/trendlife-2026-logo-light.png 131 B
- assets/README.md 2.1 KB
- assets/templates/README.md 921 B
- references/api-compatibility.md 4.5 KB
- references/batch-generation.md 15 KB
- references/brand-styles.md 3.5 KB
- references/config-reference.md 3.2 KB
- references/examples.md 2.8 KB
- references/guide.md 11 KB
- references/logo-overlay.md 2.2 KB
- references/slide-deck-styles.md 21 KB
- references/temperature-seed.md 2.8 KB
- references/troubleshooting.md 4.4 KB
- scripts/generate_images.py 26 KB runs code
- scripts/logo_overlay.py 11 KB runs code
- scripts/test_gpt_image.py 5.8 KB runs code
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 · 195 lines · 42 tokens per session scan B ab571e4cde36
nano-banana is a skill published in the GitHub repository pigfoot/claude-code-hubs (5 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,823 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.