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/banananpx skills add agentic-dev3o/devx-plugins --skill bananagit 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 | $0.00058 | $0.01024 |
| Opus 5 | $0.00029 | $0.00512 |
| Sonnet 5 | $0.00012 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
banana 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Nano Banana Ultimate — Image Generation
Input: $ARGUMENTS (optional plain-language description of what to generate)
If $ARGUMENTS is provided, use it as the user's intent and skip to prompt building. If empty, ask a clarifying question.
Requirements
uvinstalledGEMINI_API_KEYenvironment variable set (get one at https://aistudio.google.com/apikey)
Workflow
- Understand — Parse the user's request. If the subject or intent is unclear, ask ONE clarifying question.
- Build prompt — Construct a detailed Gemini prompt using the formula below.
- Configure — Choose aspect ratio, resolution, and model. Use defaults unless the user specifies otherwise.
- Generate — Run the script.
- Deliver — Report the saved file path. Do NOT read the image file back. Offer to iterate: adjust style, composition, or prompt.
Prompt Formula
Build every prompt using this structure:
[Subject] + [Action/Pose] + [Environment/Location] + [Composition/Framing] + [Style/Medium]
Rules
- Positive framing: Describe what IS in the image, never what is absent. Say "empty street" not "no cars".
- Strong verb opener: Start with Generate, Create, Capture, Render, Design, Compose.
- Be specific: Include concrete details — materials, lighting direction, time of day, textures.
- Camera/lens (photorealistic): "shot on 85mm f/1.4 lens", "low angle", "aerial view".
- Lighting: "golden hour side light", "studio softbox", "dramatic chiaroscuro", "overcast diffused".
- Materiality: "brushed aluminum", "matte ceramic", "glossy lacquer", "translucent glass".
- Text in images: Enclose any text to render in quotes. Specify font style. Note: text rendering may be imperfect.
Generation
uv run "${CLAUDE_PLUGIN_ROOT}/scripts/banana.py" \
--prompt "<detailed prompt>" \
--output "<YYYY-MM-DD-HH-MM-SS-descriptive-name>.png" \
--resolution <1K|2K|4K> \
--aspect-ratio <ratio> \
--model <model>
Editing (with input images)
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 · 112 lines · 58 tokens per session scan A 16816be680a4
banana is a skill published in the GitHub repository agentic-dev3o/devx-plugins (11 stars, last pushed 14d ago), licensed MIT. It adds 58 tokens to every session and 1,024 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
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…
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.