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 nexus-research-lab/nexus --skill imagegengit clone --depth 1 https://github.com/nexus-research-lab/nexusWrote 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/nexus-research-lab/nexus/imagegen)<a href="https://agentmods.dev/skills/nexus-research-lab/nexus/imagegen"><img src="https://agentmods.dev/badge/skills/nexus-research-lab/nexus/imagegen.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.00886 |
| Opus 5 | $0.00032 | $0.00443 |
| Sonnet 5 | $0.00013 | $0.00177 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
imagegen 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 8d 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
Image Generation Skill
为当前 workspace 生成或编辑位图资产。只使用 nexus.generate_image 与 nexus.edit_image;Provider、鉴权、接口兼容和响应解析全部由 Go 服务负责。
快路径
普通单图生成必须走内置工具快路径。
- 调用
generate_image,不要调用 Bash。 - 不读取 references。
- 不创建 prompt 文件。
- 不读取输出图片。
- 不做目录探测。
- 不使用 Write、Read、LS、Glob、TaskOutput。
- 不主动用 high quality。
工具入参模板:
{
"prompt": "A concise production prompt",
"size": "1024x1024",
"quality": "low",
"output_format": "png",
"file_name": "stable-name"
}
如果用户明确要横幅、封面或宽图,使用 size=1792x1024,仍保持 quality=low。如果图片服务返回 429/过载,最多再调用 1 次工具,降低尺寸或保持 low 重试。
工具返回的 item.path 和 item.markdown 是结果真相源。不要打开生成后的 PNG/JPG/WebP 文件验证,这会把二进制或 base64 塞回上下文。
不要在工具入参里选择 Provider 或模型,让 Settings 里的默认生图模型决定。用户需要切换默认生图模型时,使用 nexus-configuration;当前 authority 不允许时,引导用户到 Settings 或主智能体完成。
判断
- 没有输入图片:默认
generate。 - 用户要求改图、局部替换、合成、mask:使用
edit。 - 用户提供图片只是做风格或构图参考:仍使用
generate,除非明确要求编辑原图。 - 多个不同资产使用多次
generate_image调用,每个资产一条 prompt;不要把多资产塞进一个 prompt。 - 需求更适合 SVG、HTML/CSS、Canvas 或现有矢量源时,不用本 skill。
生成
把用户描述整理成一条不超过 600 字符的 prompt。用户描述已经具体时不要读取任何 reference。
{
"prompt": "Nexus AI assistant promotional banner, futuristic dark blue background, glowing neural network core, large clean NEXUS text, premium technology style",
"size": "1024x1024",
"quality": "low",
"output_format": "png",
"file_name": "nexus-promo-banner"
}
编辑
{
"image_path": "input.png",
"mask_path": "mask.png",
"prompt": "Make this black and white",
"output_format": "png",
"file_name": "edited-image"
}
调用 edit_image;image_path 和 mask_path 使用 workspace 相对路径。只有路径不明确时才做一次必要的文件查找。
回复
最终回复保持极简,只给工具返回的 markdown 和路径。不要输出尺寸、大小、配色说明、过程说明或下一步建议,除非用户明确询问。
已生成:`output/imagegen/nexus-promo-banner.png`

复杂任务参考
普通单图生成不要读取 references。只有复杂多资产、透明背景、强文字约束或编辑失败排查时再打开对应文件:
references/prompting.mdreferences/sample-prompts.mdscripts/remove_chroma_key.py
What ships with it
3 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.
- 8d ago First seen · 95 lines · 65 tokens per session scan A f5d4a4592e46
imagegen is a skill published in the GitHub repository nexus-research-lab/nexus (144 stars, last pushed yesterday), licensed Apache-2.0. It adds 65 tokens to every session and 886 once invoked, about $0.0003 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
deck-obsidian-claude
A visual design template for presentation slides with a dark GitHub-like background, colored lighting, gradient headings, and code-style formatting.
wegent-image-generation
Use this skill when the user asks to generate, draw, create, or revise an image. Supports text-to-image and image-reference generation.
blender-headless
Build, render, and visually verify 3D models with Blender's Python API in headless mode, using the image tool to inspect renders and iterate.
template-fidelity-system
Use this skill when Boss provides a PPT/PPTX template and expects the new deck to follow that template's layout, fonts, backgrounds, master rhythm, and page patterns rather than merely taking loose visual inspiration.
visual-style-system
Use this skill to extract or design a PPT style system that can be encoded into stylespec.json.
dynamic-archify
Create professional architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as standalone animated HTML files with SVG graphics, flowing animation effects, a built-in dark/light theme toggle, and one-click export to PNG / JPEG / WebP / SVG / GIF / WebM. Accepts plain-language descriptions or pasted…