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 agentmods add skills/agentic-dev3o/devx-plugins/banana-adsnpx skills add agentic-dev3o/devx-plugins --skill banana-adsgit clone --depth 1 https://github.com/agentic-dev3o/devx-pluginsWhat 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 | $0.00063 | $0.00938 |
| Opus 5 | $0.00032 | $0.00469 |
| Sonnet 5 | $0.00013 | $0.00188 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
banana-ads 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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Online Advertising Visuals
Input: $ARGUMENTS (optional — product/service and ad format)
If $ARGUMENTS is provided, use it as the campaign brief and skip to prompt building. If empty, ask about the product and target placement.
Requirements
uvinstalledGEMINI_API_KEYenvironment variable set (get one at https://aistudio.google.com/apikey)
Workflow
- Understand — Clarify the product or service, the value proposition, and the target ad placement (Instagram feed, YouTube pre-roll, web banner, etc.).
- Build prompt — Apply the Prompt Formula below to construct a bold, commercially viable image description.
- Configure — Detect the ad format from context and select aspect ratio and resolution from the Ad Format Detection table.
- Generate — Run the script. the generation script with the assembled prompt and settings.
- Deliver — Report the saved file path. Do NOT read the image file back. Offer to iterate: adjust composition, color palette, or layout.
Prompt Formula
[Product/Service] + [Value Proposition as Action] + [Ad Placement Context] + [Bold Center-Weighted Composition] + [Clean Commercial Photography or Flat Design]
Ad Format Detection
| Placement | Aspect Ratio | Resolution |
|---|---|---|
| Instagram/Facebook feed | 4:5 | 2K |
| Instagram story | 9:16 | 2K |
| YouTube pre-roll | 16:9 | 2K |
| Web banner | 21:9 | 2K |
| Square social | 1:1 | 2K |
Key Instructions
- Negative space for text overlay -- Always leave generous negative space (top, bottom, or side) for headline and CTA placement. Ad visuals are incomplete without copy; design the composition to accommodate it.
- No baked-in text -- Do NOT prompt Gemini to render text into the image. Gemini text rendering is unreliable and produces artifacts. Advise the user to add headlines, CTAs, and legal copy in a separate design tool (Figma, Canva, Photoshop).
- Bold center-weighted composition -- Place the hero product or key visual element at the center or slightly off-center with clean breathing room around it.
- Commercial lighting -- Default to clean, bright studio lighting with soft shadows. Use high-key lighting for upbeat campaigns and moody side lighting for premium or luxury positioning.
- Color psychology -- Match the color palette to the campaign intent: warm tones for urgency and sales, cool tones for trust and tech, vibrant saturated hues for youth and energy.
What ships with it
1 file 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.
- 2d ago First seen · 85 lines · 63 tokens per session scan A 879dd7aaad71
banana-ads is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 63 tokens to every session and 938 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
comfyui-topology-viz
Turn a network topology into one stylized, AI-generated still image via a self-hosted ComfyUI instance — reuses the same topology model as threejs-network-viz (any of 8 topology-source integrations, or a freeform description). Use when the operator asks for a stylized, flashy, or AI-generated…