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 desirecore/market --skill image-to-imagegit clone --depth 1 https://github.com/desirecore/marketWrote 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/desirecore/market/image-to-image)<a href="https://agentmods.dev/skills/desirecore/market/image-to-image"><img src="https://agentmods.dev/badge/skills/desirecore/market/image-to-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/desirecore/market/image-to-image"><img src="https://agentmods.dev/badge/skills/desirecore/market/image-to-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 | $0.00115 | $0.03103 |
| Opus 5 | $0.00057 | $0.01551 |
| Sonnet 5 | $0.00023 | $0.00621 |
| Haiku 4.5 | $0.00012 | $0.00310 |
Grade A, and why
image-to-image scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. **Use Bash curl throughout** — do not use the HttpRequest tool or Python (except for the b64 extraction script) How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
image-to-image Skill
Mandatory Rules (violations cause failure)
- STRICTLY follow the execution steps below — do NOT improvise, explore alternative endpoints, or try models not listed in this document
- Must access agent-service over HTTPS — the API address is already provided in the system prompt under "本机 API" section (e.g.
https://127.0.0.1:PORT); use it directly with-kto skip certificate verification - Must upload to media-store via
/api/media/upload—/tmpis only a transient download/decode location, never use a local path as the final output - Must use the
dc-media://protocol to display images — the only form the frontend can render correctly - Use Bash curl throughout — do not use the HttpRequest tool or Python (except for the b64 extraction script)
- Use
/images/generationsendpoint withimagefield — same endpoint as text-to-image, theimagefield triggers image-to-image mode - Only use
gpt-image-2model — do NOT try dall-e-3, wan2.7-image, or any other model for image-to-image
Provider & Default Compute
This skill uses the gpt-image-2 model through the DesireCore Cloud provider. You do NOT need to specify a provider — just pass "serviceType": "image_gen" and the system will automatically route to the correct provider.
- DesireCore Cloud (default, always available): The built-in compute provider supports
gpt-image-2for image-to-image. Users can use it immediately without any configuration.
Never try to query provider lists, read compute.json, or explore available models through API calls. The model listed above is guaranteed to work.
When to Use This Skill
This skill should be triggered when the user:
- Sends an image and asks to modify/edit/transform it
- Asks to change the style, background, or content of an existing image
- Wants to use a reference image to generate a new image
- Uses keywords like "图生图", "修改图片", "编辑图片", "基于这张图", "img2img"
Do NOT use this skill when the user simply asks to "generate an image" or "draw something" without providing a reference image — use the dashscope-image-gen skill instead.
What ships with it
2 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 · 264 lines · 115 tokens per session scan A d5ef2f8dbd7e
image-to-image is a skill published in the GitHub repository desirecore/market (2 stars, last pushed today), licensed MIT. It adds 115 tokens to every session and 3,103 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gemini-image-generator
Use when generating professional posed product images for e-commerce using Gemini AI with optimized prompts.
image-gen
Use when aI image generation — Stable Diffusion, Midjourney, DALL-E, ComfyUI. Prompt engineering for images, inpainting, outpainting, ControlNet. Use when working with image gen.
decor-cli
Use decor-cli to decorate screenshots, images, and videos with backgrounds, gradients, templates, annotations, arrows, shapes, counters, and spotlight effects from CLI or MCP.
nano-banana-pro
Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when you need to: (1) generate images from text descriptions, (2) edit existing images with AI, (3) compose multiple images into one scene. Supports 1K/2K/4K resolutions and up to 14 input images for composition.
image-editor
An image-processing tool for common file and layout changes. It supports resizing, compression, format conversion, thumbnails, rotation, cropping, and watermarks.
media-metadata
Extract and display metadata from images, audio, and video files.