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 Songzhi-lab/sloth-assets --skill free-asset-selectorgit clone --depth 1 https://github.com/Songzhi-lab/sloth-assetsWrote 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/songzhi-lab/sloth-assets/free-asset-selector)<a href="https://agentmods.dev/skills/songzhi-lab/sloth-assets/free-asset-selector"><img src="https://agentmods.dev/badge/skills/songzhi-lab/sloth-assets/free-asset-selector/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/songzhi-lab/sloth-assets/free-asset-selector"><img src="https://agentmods.dev/badge/skills/songzhi-lab/sloth-assets/free-asset-selector.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 | $0.00242 | $0.01090 |
| Opus 5 | $0.00121 | $0.00545 |
| Sonnet 5 | $0.00048 | $0.00218 |
| Haiku 4.5 | $0.00024 | $0.00109 |
Grade A, and why
free-asset-selector 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 12d 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
懒鬼素材库（Free Asset Selector）
🦥 懒鬼系列 Sloth Series · 懒得找，懒得挑，懒得踩坑。
为设计任务找合规、好看、下载得动的平面素材。三条铁律：
- 授权先行：商用场景只用 T0（免费商用无需署名）或 T1（免费但需署名，标注清楚）。
- 只指路，不搬运：绝不下载、打包、转存素材文件再发给用户；输出的是搜索关键词 + 直达链接 + 授权备注。
- 中国可访问性必须标注：很多免费图库在国内访问不稳定，推荐时必须区分。
工作流程
- 定位素材类型：摄影图 / 插画 / 图标 / 样机 Mockup / 纹理背景 / 视频片段。
- 定位使用场景：印刷（产品册）需要高分辨率 ≥3000px 或矢量；屏幕用（小红书/网页）≥1500px 即可。
- 查库选站：在
references/asset-database.md按类型 × 授权等级选 2-3 个站点。 - 给搜索策略：按
references/search-playbook.md给出英文搜索关键词（免费图库搜英文词命中率远高于中文）+ 直达搜索链接。 - 输出交付格式：每个推荐 = 站点 + 直达搜索链接 + 授权说明 + 是否需要署名 + 国内访问情况。
懒鬼模式：素材筛选图（默认输出方式）
用户是来省事的，不是来点开 10 个链接做调研的。默认必须输出"素材筛选图"： 一张带缩略图的选品单（HTML 页面），每格包含：缩略图预览 + 编号 + 来源站点 + 授权标注 + 下载链接。
执行规则：
- 用 AI 的搜图能力先搜 6-10 张候选图作为方向预览（搜图结果可能来自付费站，仅作预览参考，必须标注）
- 每个预览图配 1-2 个 T0 站点的同款直达搜索链接（"去这里下免费可商用的同款"）
- 用户回复编号即可，然后只针对选中的编号给精确下载指引
- 绝不让用户"一个个点开链接自己找"——那是没装这个 skill 的 AI 才干的事
平台适配（双模输出）：
- 若平台支持对话内网页预览（如 Kimi）→ 直接生成可预览的 HTML 筛选图
- 若是终端/编辑器类 Agent（Claude Code、Codex、Cursor 等）→ 生成 HTML 文件保存到本地并告知路径（用户在浏览器打开），同时在对话里输出 markdown 表格版清单作为兜底
输出模板
【素材类型】如：商务场景摄影图，用于产品册第 3 页
1. Pexels — 搜 "students studying abroad campus"
链接：https://www.pexels.com/search/students%20studying%20abroad/
授权：免费商用无需署名 | 国内可直接访问 ✅ | 分辨率：原图下载可达 5000px+
2. ...
【避坑提醒】如：这张要印刷，别用 Freepik 免费版（需署名且分辨率受限）
站点库与搜索技巧见 references/ 目录。
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.
- 12d ago First seen · 59 lines · 242 tokens per session scan A a290ceb683ec
free-asset-selector is a skill published in the GitHub repository Songzhi-lab/sloth-assets (3 stars, last pushed 25d ago), licensed MIT. It adds 242 tokens to every session and 1,090 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
understand-figma
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…