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 oyusypenko/creo --skill creo-image-promptgit clone --depth 1 https://github.com/oyusypenko/creoWrote 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/oyusypenko/creo/creo-image-prompt)<a href="https://agentmods.dev/skills/oyusypenko/creo/creo-image-prompt"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-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/oyusypenko/creo/creo-image-prompt"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-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 | $0.00073 | $0.01249 |
| Opus 5 | $0.00036 | $0.00624 |
| Sonnet 5 | $0.00015 | $0.00250 |
| Haiku 4.5 | $0.00007 | $0.00125 |
Grade A, and why
creo-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 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Prompt Generator
Generate detailed, contextually appropriate image prompts for marketing websites. Creates prompts optimized for multiple AI image generation models that accurately represent page purpose and appeal to target audiences.
Commands
| Command | Description |
|---|---|
/creo image-prompt hero |
Generate hero image prompts for pages |
/creo image-prompt feature |
Generate feature/card image prompts |
/creo image-prompt batch |
Generate all image prompts for the site |
Core Instructions
Configuration
- Check for project-specific config at
.claude/project-config.md - Read
project_id,project_name, visual style settings - Load project extension if it exists at
.claude/skills/creo-image-prompt/creo-image-prompt-{project_id}.md. This file contains project-specific visual style, color palette, brand imagery, and image category conventions.{project_id}comes fromproject-config.md. Always load it before doing work. - If no config exists, use defaults or ask user
Supported Models
Prompts should be compatible with:
- DALL-E 3 (OpenAI)
- Midjourney
- Stable Diffusion XL
- Flux
- Ideogram
- Leonardo AI
Write prompts in a universal style that works across different models.
Visual Style Guide
Overall Aesthetic
- Style: Modern, professional, documentary-style photography
- Lighting: Natural lighting, soft shadows, clean look
- Setting: Modern offices, home offices, studios, co-working spaces
- People: Diverse professionals, authentic expressions, engaged in work
- Tech: Modern devices (laptops, tablets, smartphones)
- Colors: Clean whites, soft blues, professional neutrals
Do Include
- Real work scenarios (editing, reviewing, collaborating)
- Professional equipment when relevant
- Screen interfaces showing relevant content (blurred for realism)
- Natural, candid moments (not staged stock photo poses)
- Modern, minimalist workspaces
Do Not Include
- Text overlays or watermarks (except ogImage which may have text space)
- Logos or brand names
- Cluttered or messy environments
- Overly dramatic lighting
- Artificial or staged poses
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 · 173 lines · 73 tokens per session scan A f909ab58649a
creo-image-prompt is a skill published in the GitHub repository oyusypenko/creo (4 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 1,249 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 2026-08-31.
Other skills, from other repositories
agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
ci-pipeline
Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions).
ci-status
Show current pipeline status for the active branch (GitLab CI or GitHub Actions).
remotion
Use when creating programmatic videos, animated explainers, or visual compositions with Remotion.