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 NanmiCoder/open-image-prompts --skill img-gen-tastegit clone --depth 1 https://github.com/NanmiCoder/open-image-promptsWrote 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/nanmicoder/open-image-prompts/img-gen-taste)<a href="https://agentmods.dev/skills/nanmicoder/open-image-prompts/img-gen-taste"><img src="https://agentmods.dev/badge/skills/nanmicoder/open-image-prompts/img-gen-taste/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/nanmicoder/open-image-prompts/img-gen-taste"><img src="https://agentmods.dev/badge/skills/nanmicoder/open-image-prompts/img-gen-taste.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.00950 |
| Opus 5 | $0.00036 | $0.00475 |
| Sonnet 5 | $0.00014 | $0.00190 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
img-gen-taste 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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Img Gen Taste
Act as the art-direction layer before generation. The 39 cards are reusable visual grammars, not subjects or phrases to paste wholesale into a prompt. Load only the reference needed for the request.
Route the request
Identify the literal subject, intended use, mood, hard constraints, and aspect ratio. Ask about the target generator only when generator-specific syntax is actually needed.
| Request | Read |
|---|---|
| Product, packaging, vehicle, jewelry, commercial still | references/product-advertising.md |
| Portrait, beauty, lifestyle photography | references/portrait-photography.md |
| Printmaking, layered paper craft, ink painting, tactile painting | references/print-paint-craft.md |
| Food and drink | references/food-drink.md |
| Children's art, narrative art, comics | references/illustration-storytelling.md |
| Poster, cover, typography-led composition | references/poster-cover.md |
| Architecture or interior | references/architecture-interior.md |
| Natural landscape, city atmosphere, aerial or miniature city | references/landscape-city.md |
| Fantasy, science fiction, game concept | references/sci-fi-fantasy.md |
| Abstract, 3D, graphic or web-hero visual | references/graphic-abstract.md |
Read at most two references for a genuinely cross-domain request. If no card fits, compose from first principles and say that no card was used. Route by the requested visual grammar: a tattoo, car, or bottle is a subject, not a style.
Every card carries an explicit id bullet, written as - `id`: `card-id` . Take
style_card_id from that bullet only — some files use the id as the section
heading and others use a prose title, so a heading is not a reliable id.
Work in two phases
- Explore when direction is unclear. Offer two or three strong, visibly different cards with one-sentence tradeoffs. Do not force a weak third option. Wait for the user's choice before writing a long prompt.
- Commit when direction is clear or chosen. Select one primary card, produce the creative spec, then write the final prompt.
What ships with it
11 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.
- agents/openai.yaml 258 B
- references/architecture-interior.md 6.2 KB
- references/food-drink.md 1.4 KB
- references/graphic-abstract.md 5.9 KB
- references/illustration-storytelling.md 9.0 KB
- references/landscape-city.md 6.6 KB
- references/portrait-photography.md 11 KB
- references/poster-cover.md 5.7 KB
- references/print-paint-craft.md 9.0 KB
- references/product-advertising.md 12 KB
- references/sci-fi-fantasy.md 7.8 KB
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.
- 12d ago First seen · 89 lines · 71 tokens per session scan A c1e4820216cc
img-gen-taste is a skill published in the GitHub repository NanmiCoder/open-image-prompts (244 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 950 once invoked, about $0.0004 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-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-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-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.
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.