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 Galbaz1/video-research-mcp --skill image-generationgit clone --depth 1 https://github.com/Galbaz1/video-research-mcpWrote 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/galbaz1/video-research-mcp/image-generation)<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/image-generation"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/image-generation/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/galbaz1/video-research-mcp/image-generation"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/image-generation.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 | $0.00045 | $0.01357 |
| Opus 5 | $0.00023 | $0.00678 |
| Sonnet 5 | $0.00009 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00136 |
Grade A, and why
image-generation 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 10d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Generation Prompt Best Practices
Prompt Structure
Enhance every image generation prompt around three core elements:
1. SUBJECT (What)
The main focus of the image.
- Physical characteristics: textures, materials, colors, scale
- Actions, poses, expressions if applicable
- Distinctive features that define the subject
2. CONTEXT (Where/When)
The environment and conditions.
- Setting, background, spatial relationships (foreground, midground, background)
- Time of day, weather, atmospheric conditions
- Mood and emotional tone of the scene
3. STYLE (How)
The visual treatment.
- Artistic or photographic approach: reference specific artists, movements, or styles
- Lighting design: direction, quality, color temperature, shadows
- Camera/lens choices: specify focal length, aperture, and shooting angle when photographic
Core Principles
- Preserve intent -- Enrich the user's original vision, never override it
- Positive descriptions only -- Describe what should be present; rephrase any exclusion as an inclusion
- Specific over vague -- "golden hour sunlight at 15 degree angle" beats "nice lighting"
- Natural flow -- Weave elements into a single flowing description, not a bullet list
Enhancement Patterns
Hyper-Specific Details
Add concrete visual details where the user left gaps:
- Lighting: direction, quality, color temperature, shadow behavior. Always name the physical source ("warm afternoon sun through west window", not "warm lighting") -- named sources produce consistent shadows
- Textures: surface materials, weathering, reflectivity
- Atmosphere: particulates, humidity, depth haze
- Scale: relative sizes, distances, proportions
Camera Control Terminology
When a photographic look is appropriate:
- Lens type: "shot with 85mm portrait lens", "wide-angle 24mm"
- Aperture: "shallow depth of field at f/1.8", "deep focus at f/11"
- Angle: "low angle emphasizing height", "bird's eye view"
- Motion: "motion blur on the paws", "frozen mid-action"
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.
- 10d ago First seen · 143 lines · 45 tokens per session scan A 54964f229e9c
image-generation is a skill published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,357 once invoked, about $0.0002 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
prism
Consultant for NotebookLM steering prompt design. Optimizes Audio/Video/Slide/Infographic output quality through source preparation, prompt engineering, and Custom Goals persona design.
happyhorse-prompt-studio
Interactive prompt studio for HappyHorse 1.0 video generation. Guides users through scenario discovery with vivid examples, then assembles production-ready prompts in JP/CN/EN. Use when someone wants to create AI video content with HappyHorse but doesn't know where to start, or when they have a specific scenario and…
prompt-decorators-usage
Use when a user's prompt would clearly benefit from a reasoning, structure, tone, or verification decorator - or when they ask "what decorators should I use?". Teaches when and how to suggest inline ::Name(params) sigils instead of repeating verbose prompt-engineering instructions manually.
prompt-craft
Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.
nano-banana-pro-prompts-recommend-skill
Recommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs. Optimized for Nano Banana Pro (Gemini), but prompts also work with Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E, Flux, Stable Diffusion, and any text-to-image AI model. Use this skill when users want…
gpt-image-2-prompting
Prompt OpenAI's GPT Image 2 — the five-slot Scene/Subject/Details/Use case/Constraints template it responds to, the change-versus-preserve shape for edits, labelled multi-image compositing, and how to get text on an image to render verbatim. Use whenever the model id contains gpt-image-2 (openai/gpt-image-2…