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 tranfu-labs/tranfu-skills --skill black-line-icon-stylegit clone --depth 1 https://github.com/tranfu-labs/tranfu-skillsWrote 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/tranfu-labs/tranfu-skills/black-line-icon-style)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/black-line-icon-style"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/black-line-icon-style/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/tranfu-labs/tranfu-skills/black-line-icon-style"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/black-line-icon-style.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 | $0.00143 | $0.03207 |
| Opus 5 | $0.00072 | $0.01604 |
| Sonnet 5 | $0.00029 | $0.00641 |
| Haiku 4.5 | $0.00014 | $0.00321 |
Grade A, and why
black-line-icon-style 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.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill：black-line-icon-style
极简黑白线性图标风｜透明底｜粗黑圆角线条｜无文字｜非 3D
0. 默认行为
你的任务是：根据用户输入的主题或概念，直接生成一张极简黑白线性图标。
默认行为：
直接调用图像生成能力出图
默认透明背景；运行时不支持透明时使用纯白背景
默认不出现文字、字母或数字
默认使用粗黑色圆角线条
默认单主体居中
默认不使用彩色、阴影、渐变、3D、纹理或复杂背景
不要先输出大段分析
不要只输出 Prompt
只有用户明确要求：
只要方案
只要 Prompt
先分析
不生成图
才输出文字方案。
0.1 适用边界与重定向
触发范围：
icon / 图标 / 符号 / 线性图标 / UI 功能入口图标 / 空状态图标 / 抽象科技符号 / logo-like 辅助图形
不触发范围：
彩色插画 / 写实图 / 摄影风图像 → 转到对应插画或写实图工作流
3D 质感 / C4D / 立体渲染 → 转到 3D 或立体图像工作流
复杂海报 / 文章封面 / 带标题横版图 → 转到 article-cover-image
带文字的信息图 / 知识卡片 / 流程说明图 → 转到专门的信息图或图表工作流
品牌正式 Logo 定稿 → 转到 logo 设计工作流或人工设计
意图歧义处理：
用户说“logo-like”但只是要辅助符号或概念标记 → 使用本 Skill。
用户说“Logo 定稿 / 品牌 Logo / 商标 / VI 主标识” → 不触发本 Skill，转到 logo 设计工作流或人工设计。
用户说“只要 Prompt”且目标是黑白线性图标 → 使用文字模式，输出图像生成 Prompt，不调用图像生成。
用户说“只要 Prompt”但目标不是图标视觉 → 不触发本 Skill。
ownership：
默认 ownership = edit/generate image：直接调用图像生成能力产出图标。
仅当用户显式说“只要 Prompt / 不生成图 / 先给方案”时，ownership = rewrite inline：只输出完整图标生成 Prompt，不生成图片。
完成标准：
done = 产出一张图标图像，且 §5.1 生成前 Prompt 自检与 §5.2 生成后成品验证全部通过。
若用户只要 Prompt，done = 输出 §6 中文 Prompt 或 §7 英文 Prompt + §8 负面 Prompt，且不调用图像生成。
0.2 主流程
CREATE A TODO LIST FOR THE TASKS BELOW（内部执行，不向用户展示）：
1. 读取用户输入。若没有主题、概念或使用场景 → 向用户索要图标主题并退出。
2. 判断任务边界。若用户要彩色插画、写实图、3D、复杂海报、文章封面、信息图或正式 Logo → 按 §0.1 重定向并结束。
3. 识别输出模式。若用户显式要求“只要 Prompt / 不生成图 / 先分析” → 输出文字方案并结束；否则继续出图。
4. 提取核心概念。若主题包含多个对象 → 选择一个最能覆盖整体语义的单一符号；否则使用主题关键词。
5. 选择图形隐喻：目标 / 节点 / 连接线 / 循环箭头 / 文档卡片 / 勾选 / 星标 / 抽象 AI 核心 / 系统结构线。
6. 拼接 Prompt：使用 §6 或 §7，并附加 §8 负面 Prompt。
7. 跑 §5.1 生成前 Prompt 自检。若任一项不通过 → 补全或收紧 Prompt 后回到第 6 步；若仍无法得到合格 Prompt → 简短说明失败原因并结束，不宣称 done。
8. 调用图像生成能力产出图标。
8.1 跑 §5.2 生成后成品验证。若任一项不通过 → 按 §10 纠偏后回到第 6 步；若同一失败连续 2 次出现 → 改为更简单的单主体几何符号后再试一次；仍失败 → 简短说明失败原因并结束，不宣称 done。
9. 成品验证通过后，简短回复结果并结束。
1. 适用场景
尤其适合：
Prompt 多轮评审
目标驱动拆解
AI 工作流
多步骤流程
任务分解
审核 / 反馈 / 评分
数据分析 / 结果确认
系统结构 / 流程编排
UI 功能入口
空状态图标
2. 风格目标
生成一种极简、现代、抽象、黑白线性图标风格的视觉图形。
整体像手绘科技符号，但保持干净、克制、几何化，适合用于 UI、产品、品牌辅助图形或视觉系统。
What ships with it
5 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 · 289 lines · 143 tokens per session scan A 65edde8d24ee
black-line-icon-style is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 143 tokens to every session and 3,207 once invoked, about $0.0007 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.