Unsloth is a desktop application for running and training language, diffusion, embedding, audio, and related machine-learning models locally. It is for people who want to use local models, fine-tune them, connect them to agents, or serve them through an OpenAI-compatible API. The catalogue skill helps coding agents work with Unsloth and its local models.
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 unslothai/unsloth --skill image-promptinggit clone --depth 1 https://github.com/unslothai/unslothWrote 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/unslothai/unsloth/image-prompting)<a href="https://agentmods.dev/skills/unslothai/unsloth/image-prompting"><img src="https://agentmods.dev/badge/skills/unslothai/unsloth/image-prompting/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/unslothai/unsloth/image-prompting"><img src="https://agentmods.dev/badge/skills/unslothai/unsloth/image-prompting.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 | $0.00023 | $0.00269 |
| Opus 5.5 | $0.00009 | $0.00108 |
| Sonnet 5.5 | $0.00005 | $0.00054 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
image-prompting 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 2d 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.
What it actually says
Write an image or video prompt
Use this skill when the user asks for an image or a video and their request is short or vague.
- Read the generate_image or generate_video tool description: when it carries a tip for the model loaded in Unsloth Studio and that tip disagrees with a step below, follow the tip.
- Name the subject first, with the details that must stay the same across shots.
- Add the setting: place, time of day and weather.
- Pick a style: photo, illustration, painting or 3D render, plus the lens or medium when it matters.
- Describe the light and the mood.
- Set the composition: framing and camera angle, and for a video how the camera and the subject move.
- Put any words that must appear in the picture in quotes.
- For more shots of the same character, repeat the subject's details word for word.
Keep the user's own words and intent. Add no people, brands or text they did not ask for, and leave steps and guidance out unless the user asks, so the model's own defaults apply.
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.
- 2d ago First seen · 21 lines · 23 tokens per session scan A aeeca7734e18
image-prompting is a skill published in the GitHub repository unslothai/unsloth (78,377 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 269 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-20.
Other skills, from other repositories
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.
unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization.
llama-factory
Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.