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 skills/recomposesh/recompose/image-generationnpx skills add recomposesh/recompose --skill image-generationgit clone --depth 1 https://github.com/recomposesh/recomposeWrote 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/recomposesh/recompose/image-generation)<a href="https://agentmods.dev/skills/recomposesh/recompose/image-generation"><img src="https://agentmods.dev/badge/skills/recomposesh/recompose/image-generation.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.02101 |
| Opus 5 | $0.00016 | $0.01051 |
| Sonnet 5 | $0.00006 | $0.00420 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade C, and why
image-generation scanned grade C with 1 finding 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 4d 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.
Instruction-override phrasinghighPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- Bypass content policies of AI tools How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Generation Skill
Overview
I help you create effective prompts for AI image generation tools like DALL-E, Midjourney, and Stable Diffusion. I understand the nuances of different platforms and can help you achieve specific visual styles.
What I can do:
- Write detailed image generation prompts
- Optimize prompts for specific AI tools
- Suggest style keywords and modifiers
- Create negative prompts to avoid unwanted elements
- Adapt prompts for different aspect ratios
- Generate variations and alternatives
What I cannot do:
- Generate images directly
- Guarantee exact output from AI tools
- Predict how AI will interpret prompts
- Bypass content policies of AI tools
How to Use Me
Step 1: Describe Your Vision
Tell me:
- What you want to see in the image
- The purpose (presentation, social media, marketing)
- Style preferences (realistic, artistic, minimalist)
- Mood or emotion to convey
Step 2: Choose the Platform
- DALL-E 3: Best for clarity and instruction-following
- Midjourney: Best for artistic and aesthetic images
- Stable Diffusion: Most customizable, local options
Step 3: Specify Parameters
- Aspect ratio (1:1, 16:9, 4:3, etc.)
- Quality level
- Style references
- Things to avoid
Prompt Engineering Framework
Basic Prompt Structure
[Subject] + [Action/State] + [Environment] + [Style] + [Technical Parameters]
Detailed Template
[Main Subject]
- Who/what is the focus?
- What are they doing?
[Environment/Setting]
- Where is this taking place?
- Time of day? Weather? Season?
[Composition]
- Camera angle (eye-level, bird's eye, low angle)
- Framing (close-up, medium shot, wide shot)
- Focus (depth of field)
[Style]
- Art style (photorealistic, watercolor, oil painting, etc.)
- Artist reference (optional)
- Era/period
[Lighting]
- Type (natural, studio, dramatic, soft)
- Direction (backlit, side-lit, front-lit)
[Color]
- Palette (warm, cool, monochrome)
- Specific colors to include
[Mood/Atmosphere]
- Emotion to evoke
- Overall feeling
[Technical]
- Quality modifiers
- Aspect ratio
- Negative prompts
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.
- 4d ago First seen · 375 lines · 32 tokens per session scan C 3a0a93b23716
image-generation is a skill published in the GitHub repository recomposesh/recompose (26 stars, last pushed 7d ago), licensed MIT. It adds 32 tokens to every session and 2,101 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
image-generation
Create effective AI image generation prompts for DALL-E, Midjourney, and Stable Diffusion. Generate prompts for various styles and use cases.
model-aware-image-prompt-engineer
Model-aware image prompt engineering for any agent or image generation workflow. Use when writing, improving, translating, debugging, or evaluating prompts for OpenAI image models, Gemini Nano Banana, Midjourney, FLUX, Qwen-Image, Z-Image, Stable Diffusion, SDXL, Pony, Illustrious, NoobAI, Animagine, HunyuanImage…
cinematic-frame-director
Turn a user's idea, scene description, or mood into ONE production-grade cinematic still-image prompt in English for text-to-image models (Seedream, Midjourney, Flux, DALL-E, or any image generator). Use this skill whenever the user asks for an image prompt, a cinematic frame, a "movie still" look, a photorealistic…
nano-banana-image-skill
Model-aware image prompting for Nano Banana Pro and Nano Banana 2. Covers generation, editing, continuity, text-in-image, style routing, and structured JSON output.
vynly-post
A skill that lets an agent publish images it generated to Vynly (vynly.co) - a public, AI-only social feed where every post carries verified provenance (C2PA / SynthID / generator metadata). No signup; two HTTP calls. Use after you create an image the user wants shared publicly.
aigc-prompt-optimizer
把口语化或模糊的 AIGC 创作需求，优化成适合具体工具的专业提示词；支持 prompt battle / 比赛主题发散、Midjourney 出图反馈、二选一选图、视觉问题诊断与迭代改写，并补全构图意图层。支持图片工具（Midjourney、gpt-image、DALL-E、SD、SeaDream）和视频工具（Seedance、Sora、Runway、Kling 等）。当用户说"帮我优化 prompt"、"把这个需求改成 MJ prompt"、"生成 Seedance 提示词"、"prompt battle"、"这张图哪里不好"、"二选一"、"我想做一张/一个视频..."时触发。.