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 animalzinc/claude-plugins --skill image-promptgit clone --depth 1 https://github.com/animalzinc/claude-pluginsWrote 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/animalzinc/claude-plugins/image-prompt)<a href="https://agentmods.dev/skills/animalzinc/claude-plugins/image-prompt"><img src="https://agentmods.dev/badge/skills/animalzinc/claude-plugins/image-prompt/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/animalzinc/claude-plugins/image-prompt"><img src="https://agentmods.dev/badge/skills/animalzinc/claude-plugins/image-prompt.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 | $0.00060 | $0.03550 |
| Opus 5 | $0.00030 | $0.01775 |
| Sonnet 5 | $0.00012 | $0.00710 |
| Haiku 4.5 | $0.00006 | $0.00355 |
Grade A, and why
image-prompt 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 today.
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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Prompt Creator
Create production-quality image generation prompts for Nano Banana (Google's AI image generator).
$ARGUMENTS — Optional: brand name, or description of what's needed. If empty, start from brand selection.
Plugin root
This skill is part of the image-prompt-creator plugin. Resolve all relative paths (brands/, docs/, examples/) from the plugin root — the directory containing this skill's skills/ folder.
At the start: read docs/nano-banana-guide.md for prompting reference. Keep it loaded throughout.
Phase 1: Brief
Step 1 — Brand selection
List available brands by scanning brands/*/brand-config.md. Present them:
Which brand are you creating images for? Available: {list of brand names from folder names} Or type a new brand name to set one up.
Always pause for the user to confirm — even if only one brand exists. The user may want to add a new brand or may have opened the skill by mistake.
If no brands exist yet, tell the user:
No brands configured yet. Let's set one up. What's the brand name? I'll create the folder and guide you through the brand config. See
brands/README.mdfor the full template.
If the user names a brand that doesn't exist yet, guide them through creating brands/{slug}/brand-config.md using the template in brands/README.md.
Read the selected brands/{name}/brand-config.md. Also check if brands/{name}/references/ exists and scan for subfolders (e.g., featured-blog-images/, social-graphics/). These are curated style references from previous successful images — use them to inform your prompt writing and optionally recommend attaching them as style references.
If $ARGUMENTS includes a brand name, still confirm it but don't ask from scratch.
Step 2 — Input intake
Ask:
What do you need? Describe your image — what it's for, any ideas you have, and what source material you can share.
Examples: "featured image for this blog article", "social ad showing our product", "infographic visualizing this data", "I have a rough idea for an illustration."
You can provide article text, documents, other images, voice notes, or just a rough idea. Type
helpfor more guidance.
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.
- today Changed · +60 tokens per session 85247a6e71fa
- 9d ago First seen · 316 lines · 0 tokens per session scan A 18b7d506b20f
image-prompt is a skill published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 3,550 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
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-examples-ja
This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.