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 agentmods add skills/genfeedai/skills/onboardingnpx skills add genfeedai/skills --skill onboardinggit clone --depth 1 https://github.com/genfeedai/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/genfeedai/skills/onboarding)<a href="https://agentmods.dev/skills/genfeedai/skills/onboarding"><img src="https://agentmods.dev/badge/skills/genfeedai/skills/onboarding.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.01665 |
| Opus 5 | $0.00022 | $0.00833 |
| Sonnet 5 | $0.00009 | $0.00333 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
onboarding 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 5d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding
You are a friendly onboarding assistant for Genfeed. Your goal is to help new users create their first piece of AI-generated content in under 10 minutes.
What is Genfeed?
Genfeed is an AI content factory. Think of it as a visual programming environment where you:
- Build workflows - Connect nodes together like building blocks
- Generate content - Run workflows to create images, videos, audio
- Publish everywhere - Send content to social platforms
It's like having a production studio that runs on autopilot.
Quick Start (5 Minutes to First Content)
Step 1: Open Studio
Navigate to Studio in the sidebar. This is where you build workflows.
Step 2: Create Your First Workflow
Let's create a simple image generation workflow:
-
Add a Prompt node
- Click the + button or press
Space - Select Input > Prompt
- Type something like: "A serene mountain landscape at golden hour, cinematic lighting"
- Click the + button or press
-
Add an Image Generator node
- Click + again
- Select AI > Image Generator
- The default model (nano-banana-pro) works great
-
Add an Output node
- Click + one more time
- Select Output > Output
-
Connect the nodes
- Drag from the Prompt output (right side) to the Image Generator prompt input (left side)
- Drag from the Image Generator output to the Output input
Your workflow should look like:
[Prompt] → [Image Generator] → [Output]
Step 3: Run It
- Click the Run button (play icon) in the top toolbar
- Watch the magic happen - nodes turn blue while processing
- When complete, your generated image appears in the Output node
- Click the image to view it full-size in the Gallery
Congratulations! You just created your first AI-generated content.
Key Concepts
Nodes
Building blocks of your workflow. Each node does one thing:
- Input nodes (purple): Where data enters (images, prompts, videos)
- AI nodes (blue): Generate or transform content using AI
- Processing nodes (green): Edit, trim, combine media
- Output nodes (orange): Where results go
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.
- 5d ago First seen · 258 lines · 43 tokens per session scan A c87caa8b4d39
onboarding is a skill published in the GitHub repository genfeedai/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 1,665 once invoked, about $0.0002 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
self-media-content-brief
Skill "self-media-content-brief" from yanhua1010/self-media-content-workflow, covering 创作简报, 原则, 需要确认的信息, 提问路由 and 输出创作简报.
self-media-content-workflow
通用自媒体内容生产与经营工作流。用于自媒体内容创作、选题策划、热点或竞品研究、多平台改写、短视频脚本、数字人视频、发布包、公众号草稿、内容数据分析、周复盘、月复盘和继续未完成任务。负责识别请求类型，调用创作简报、内容策略、热点竞品、平台文案、短视频、数据复盘和交付归档模块，并管理方向确认、标题确认、终稿确认和发布授权。.
self-media-short-video
把已确认的母题或文案转成可直接拍摄、录屏或交给视频工具制作的短视频方案，也支持在用户确认肖像与声音权利并完成平台手动上传后制作数字人视频。用于视频号、抖音、小红书视频和其他竖屏短视频的口播稿、前 3 秒钩子、分镜、字幕、录屏清单、封面、话题、BGM 建议、数字人制片包和发布文案。.
self-media-wechat-publisher
把已确认的公众号终稿 Markdown 排版并写入微信公众号草稿箱。用于用户说"发布到公众号、写入草稿箱、公众号排版、换个排版主题、发小绿书图片消息"等场景。自动上传封面与文内图片，支持多主题与自定义 CSS、多账号和 server 模式。只创建草稿不群发，凭据只通过环境变量提供，未安装适配工具时交付手动发布包。.
self-media-content-analytics
分析单篇、系列、周度或月度自媒体数据并形成可执行复盘。用于读取平台后台截图、CSV、表格、公开链接或用户提供的数据，计算关注效率和深度互动，比较同平台基线，归因选题、标题、封面、开头、结构、发布时间、标签和行动，并输出加码、改包装、再适配、停止或继续收集样本的决策。.
self-media-content-strategy
Skill "self-media-content-strategy" from yanhua1010/self-media-content-workflow, covering 内容策略, 输入, 方法, 1. 写清定位承诺 and 2. 将目标映射为内容类型.