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 commands/gregpriday/create-image-mcp/create-stylegit clone --depth 1 https://github.com/gregpriday/create-image-mcpWhat 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 | $0.00009 | $0.01110 |
| Opus 5 | $0.00005 | $0.00555 |
| Sonnet 5 | $0.00002 | $0.00222 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade A, and why
create-style 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 yesterday.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a New Image Style
You are creating a new style preset for the create-image MCP server. A style is a JSON file placed in create-image-styles/ that guides image generation towards a specific visual style.
Input
Style name and goal: $ARGUMENTS
Style names must be in kebab-case (e.g., ui-mockup, hand-drawn-sketch, pixel-art). The filename becomes the style name.
Reference: Existing Style Format
Read the built-in style in src/styles.js to understand the JSON structure. Each style has:
name: Human-readable display namedescription: What the style achieves (1-2 sentences)systemPrompt: The prompt text that guides the image model. This is the core of the style.defaults: Optional parameter defaults (size,quality,background,output_mime_type)
Valid sizes: 1024x1024, 1024x1536, 1536x1024, auto
Valid qualities: low, medium, high, auto
Valid backgrounds: transparent, opaque, auto
Valid output MIME types: image/png, image/jpeg, image/webp
Process
Step 1: Research the visual style
Use mcp__ask-google__ask_google to research what makes this visual style effective. Ask specifically about:
- What defines this style visually (colors, composition, line work, etc.)
- Best practices for AI image generation in this style
- What to avoid (common failure modes with AI image generators)
- How to describe it in a prompt that GPT Image 1.5 will interpret well
Do 2-3 rounds of research to refine your understanding. Be specific about GPT Image / OpenAI image models when searching.
Step 2: Draft the system prompt
Write a system prompt following these principles (learned from creating the ui-mockup style):
- Lead with the core style directive — one clear sentence describing what to create
- Use structured categories — break constraints into labeled sections (Color scheme, Typography, Layout, Constraints, etc.)
- Be specific about what to include AND what to avoid — the model needs negative constraints
- Use concrete values — hex colors, specific terms (e.g., "flat vector" not "nice looking")
- Keep it focused — the system prompt should be under 500 words. Shorter is better.
- Avoid vague terms — "beautiful", "nice", "good" mean nothing to the model. Use precise visual language.
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.
- yesterday First seen · 113 lines · 9 tokens per session scan A ac9102bb3a63
create-style is a command published in the GitHub repository gregpriday/create-image-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 1,110 once invoked, about $0.0000 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 commands, from other repositories
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
status
Show 3d-design team status and recent activity.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
frontend-3d
You are an expert in 3D web development using Three.js, React Three Fiber, WebGL, and WebGPU. You create immersive 3D experiences for the web.