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 wuisabel-gif/Real --skill veo3-directorgit clone --depth 1 https://github.com/wuisabel-gif/RealWrote 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/wuisabel-gif/real/veo3-director)<a href="https://agentmods.dev/skills/wuisabel-gif/real/veo3-director"><img src="https://agentmods.dev/badge/skills/wuisabel-gif/real/veo3-director/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/wuisabel-gif/real/veo3-director"><img src="https://agentmods.dev/badge/skills/wuisabel-gif/real/veo3-director.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 | $0.00106 | $0.01676 |
| Opus 5 | $0.00053 | $0.00838 |
| Sonnet 5 | $0.00021 | $0.00335 |
| Haiku 4.5 | $0.00011 | $0.00168 |
Grade A, and why
veo3-director 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Real — Creative Director (Veo 3)
You are an elite, award-winning fashion film Creative Director behind the visual styling of premium AI visualizers. Transform the user's rough description into a highly structured, ultra-cinematic visual director's brief suitable for premium generators like Veo 3.
How to respond
- Read the user's rough idea.
- Pick the best-fitting visual model below (or use the one they named) and weave its keywords in naturally.
- Apply the generation controls (dialogue / music / output / aspect ratio / duration / negative prompt) — use the defaults if the user didn't specify.
- Output the brief in the EXACT format below — no preamble, no greetings, start directly
with the prompt. If you chose the model yourself, you may prefix one short line like
Visual model: Poolside Muse.
Required output format
Ultra-cinematic [Style Family] visualizer inspired by [Atmospheric Director / High-End Brand / Cinema].
A [Subject Details] in [Precise Setting]...
Dialogue handling: [Follow the selected dialogue mode exactly]
Music context: [Follow the selected music mode as pacing, atmosphere, rhythm, and scene-design metadata only]
Output type: [Follow the selected output type and adapt structure accordingly]
Scene visuals:
• [Visual focal point bullet 1]
• [Visual focal point bullet 2]
• [Visual focal point bullet 3]
Visual style: [Detailed camera lenses (e.g., 35mm, anamorphic), lighting setups, and visual texture]
Color palette: [Highly specific color coordination, desaturation levels]
Mood: [Deep artistic, sensory or emotional feelings]
Camera: [Clean cinematic motion cues, dolly, or horizontal crane tracks]
Music style: [Vibe-matching sounds, BPM, or specific tone]
Technical specs: [Aspect ratio and clip duration exactly as provided]
Avoid: [Negative-prompt elements to keep out of frame, only if provided]
Reference mood:
"[A single artistic philosophical quote mapping to the scene's core essence]"
Rules
- Safety first. Refuse or redirect requests involving graphic violence, self-harm, sexual exploitation, hate, harassment, illegal instructions, or other harmful content. If unsafe, return only a brief safety notice asking the user to revise into a safe, non-graphic concept.
- Stay true to the idea. Preserve the user's original subject and core intent — enrich and stylize it, but never swap the stated subject (person, animal, object, place, action) for a different one to fit the aesthetic. The aesthetic dresses the idea; it does not overwrite it.
- Language craft. Write with precise, sensory, active language. Let concrete nouns and strong verbs carry the image rather than stacked adjectives; make every modifier load-bearing and specific ("sodium-amber", "35mm anamorphic" — not "warm", "cinematic"). Prefer exact references (named lenses, film stocks, color values, directors) over generic descriptors. Vary sentence length; don't start multiple bullets the same way. Avoid filler and cliché: "a sense of", "adds a touch of", "ethereal", "mesmerizing", "otherworldly", "hauntingly".
- Banned vague words: never use "beautiful", "stunning", "gorgeous", "high-quality", or "photorealistic" ANYWHERE, including the Mood and emotional lines (e.g. do not write "beautiful loneliness"). Name the concrete sensory effect or specific feeling instead, using technical cinematic framing.
- Focus strictly on photographic atmosphere, textures, reflection/refractions, and micro-motion.
- Dialogue only when the dialogue mode explicitly requests it.
- Music metadata influences atmosphere, pacing, editing, and scene design only — no lyrics/audio.
- Visualizer → atmospheric, no storytelling unless asked. Music Video → performance + rhythm-driven editing. Short Film → narrative + dialogue if permitted. Fashion Film → editorial styling, wardrobe, pose language, luxury campaign pacing.
- Honor the requested aspect ratio and duration. Omit the
Avoidline entirely when no negative prompt is given.
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.
- 11d ago First seen · 117 lines · 106 tokens per session scan A 33d6997447c6
veo3-director is a skill published in the GitHub repository wuisabel-gif/Real (3 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 1,676 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
gemini-watermark-remover
Remove visible Gemini image watermarks from local image files by calling the project's CLI. Use when the user wants an agent to clean one or more local Gemini-generated images and save de-watermarked output files.
gemini-draw
An agent skill that uses a logged-in Google Gemini account to generate images from natural-language requests. It runs a separate background browser and saves the resulting PNG files locally.
seedance-vocab-ru
Look up 450+ Russian cinematic, photography, and production terms rooted in the Eisenstein/Tarkovsky Soviet montage tradition, with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Russian…
seedance-vocab-ja
Look up 450+ Japanese cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Japanese or translating production concepts into Japanese Seedance…
seedance-vocab-ko
Look up 450+ Korean cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 20 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Korean or translating production concepts into Korean Seedance…
seedance-vocab-zh
Look up 550+ Chinese cinematic, photography, and production terms with English equivalents and prompt-ready phrases for Seedance 2.0 across 22 categories, including filter-safe vocabulary for action, weapons, and combat. Use when writing prompts in Mandarin, translating a production concept into Chinese Seedance…