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 vstorm-co/content-skills --skill content-imagegit clone --depth 1 https://github.com/vstorm-co/content-skillsWrote 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/vstorm-co/content-skills/content-image)<a href="https://agentmods.dev/skills/vstorm-co/content-skills/content-image"><img src="https://agentmods.dev/badge/skills/vstorm-co/content-skills/content-image/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/vstorm-co/content-skills/content-image"><img src="https://agentmods.dev/badge/skills/vstorm-co/content-skills/content-image.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 | $0.00046 | $0.02151 |
| Opus 5 | $0.00023 | $0.01076 |
| Sonnet 5 | $0.00009 | $0.00430 |
| Haiku 4.5 | $0.00005 | $0.00215 |
Grade A, and why
content-image 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 9d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Image Skill
Important: This Skill Generates Prompts, Not Images
Claude cannot generate images. This skill produces ready-to-paste prompts optimized for AI image generation models. The output is text that the user copies into DALL-E, Midjourney, Stable Diffusion, or another image generation tool.
Every output includes:
- The prompt text (optimized for the target model)
- Recommended model and settings
- Negative prompt (where the model supports it)
- Variations to try
When This Skill Activates
- User asks for an image, illustration, or visual asset
- User wants to create image prompts or optimize existing prompts
- User mentions DALL-E, Midjourney, Stable Diffusion, Flux, or other image generation tools
- User says "generate an image of..." or "I need a visual for..."
- User wants a hero image, social media graphic, blog illustration, or product shot
Prompt Structure
Every effective image prompt has four components:
1. Subject
What is in the image. Be specific and concrete.
- Bad: "a person working"
- Good: "a software developer sitting at a standing desk with dual monitors, writing code, coffee mug nearby"
The subject should be described in enough detail that two different artists would produce recognizably similar images.
2. Style
The visual treatment. Reference a specific style from the style library or describe it explicitly.
- Bad: "nice looking"
- Good: "editorial photography, shallow depth of field, natural window light, 35mm lens"
See style-library/ for pre-built style descriptions:
style-library/editorial.md-- Clean, professional photographystyle-library/flat-illustration.md-- Bold, geometric, vector-likestyle-library/3d-render.md-- Soft lighting, smooth surfaces, product-shot feelstyle-library/film-still.md-- Cinematic, dramatic, atmospheric
3. Mood / Atmosphere
The emotional tone of the image.
- Calm, focused, productive
- Energetic, vibrant, optimistic
- Dramatic, tense, high-stakes
- Warm, inviting, approachable
- Minimal, quiet, contemplative
What ships with it
5 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.
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.
- 9d ago First seen · 266 lines · 46 tokens per session scan A 86049dc873bf
content-image is a skill published in the GitHub repository vstorm-co/content-skills (22 stars, last pushed 4mo ago), licensed MIT. It adds 46 tokens to every session and 2,151 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
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-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.
ai-video-prompt-pack
Create, adapt, and review AI video generation prompt packs for tools such as Gemini/Veo, Sora, Runway, Pika, Luma, and similar systems. Use when Codex is asked for video generation prompts, Shorts prompts, AI ad concepts, timing maps, scene prompts, negative prompts, voiceover/audio directions, reference-image…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.
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.
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.