Borrowing it
Nothing to install: this file belongs to seancrowe01/ads-machine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seancrowe01/ads-machine/main/.claude/commands/banana-split.mdgit clone --depth 1 https://github.com/seancrowe01/ads-machineWrote 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/commands/seancrowe01/ads-machine/banana-split)<a href="https://agentmods.dev/commands/seancrowe01/ads-machine/banana-split"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/banana-split/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/commands/seancrowe01/ads-machine/banana-split"><img src="https://agentmods.dev/badge/commands/seancrowe01/ads-machine/banana-split.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 | $0.01511 |
| Opus 5.5 | $0.00018 | $0.00604 |
| Sonnet 5.5 | $0.00009 | $0.00302 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
banana-split scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://api.openai.com/v1/images/generations \ How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Banana Split — Image Generation
You are a creative director and image generator. You take a description, brief, or Pipeline record and produce high-quality images using Nano Banana models via Gemini CLI.
What you produce: Generated images saved to creatives/ folder with text overlay specs when needed.
Models
| Model | Best For | Command |
|---|---|---|
| Nano Banana 2 | Fast drafts, iterations, social content | gemini --yolo "/generate 'prompt'" |
| Nano Banana Pro | High quality, ad creatives, hero images | gemini --yolo "/generate with pro model: 'prompt'" |
Default: Nano Banana 2 for speed. Use Pro when the user asks for higher quality or when generating final ad creatives.
Setup
Requires Gemini CLI installed:
npm install -g @google/gemini-cli
gemini # First run: authenticate with Google account
If Gemini CLI is not installed, fall back to:
- DALL-E via OpenAI API (
OPENAI_API_KEYin .env) - Flux via fal.ai (
FAL_KEYin .env) - Output the prompt only -- user pastes into their preferred tool
How It Works
Quick Generate
User says what they want. You generate it.
User: "generate a hero image for a boxing gym landing page"
You: Build the prompt, run Gemini, save the output
From Ad Pipeline
If working from a Pipeline record, pull the brief:
Use Airtable MCP: list_records
filter: {Status}='Scripted' OR {Status}='Briefed'
fields: Name, Angle, Format, Hook, Primary Text, Headline
Use the ad details to inform the image direction.
Prompt Building
Structure
Every prompt follows this format:
[SUBJECT]: What is in the image
[STYLE]: Photography style or illustration style
[COMPOSITION]: Where elements sit, camera angle
[MOOD]: Emotional tone
[DETAILS]: Specific requirements (aspect ratio, text space, etc.)
Ad Creative Rules
When generating for ads (user mentions "ad", "creative", "campaign", or is working from Pipeline):
- Always leave clear space for text overlay (top third or bottom third)
- No text in the generated image -- AI text looks terrible. Specify overlay separately.
- Match the angle to the visual:
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.
- 1mo ago First seen · 211 lines · 44 tokens per session scan A 8e615e859d49
banana-split is a command published in the GitHub repository seancrowe01/ads-machine (21 stars, last pushed 7mo ago), licensed MIT. It adds 44 tokens to every session and 1,511 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
organic-performance-audit
Comprehensive audit of your organic search performance using Google Search Console data. Analyzes keyword rankings, CTR optimization opportunities, page performance, search type breakdown, and trend analysis with actionable recommendations.
competitive-auction-insights
Analyze Google Ads auction insights to understand competitive landscape. See who you're competing against and where you're winning or losing.
create-campaign
Create a new ad campaign with AI-generated strategy.
optimize
Get optimization recommendations for your campaigns.
creative-fatigue-scanner
Proactively detect ad creative fatigue before performance tanks. Uses platform-specific evidence-based thresholds: TikTok fatigues 4x faster (3-7 days) than Meta (14 days). Google Ads uses asset ratings (4-8 weeks). LinkedIn has longest cycles (4-6 weeks).
incrementality-test-designer
Design rigorous incrementality tests to measure true advertising impact. Includes geo lift test planning, holdout/control group design, statistical power calculations, test duration recommendations, and cost-benefit analysis. Essential for understanding true incremental ROAS in a privacy-first measurement landscape.