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 LZheng0411/Lzheng-fitness --skill lzheng-video-lessonsgit clone --depth 1 https://github.com/LZheng0411/Lzheng-fitnessWrote 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/lzheng0411/lzheng-fitness/lzheng-video-lessons)<a href="https://agentmods.dev/skills/lzheng0411/lzheng-fitness/lzheng-video-lessons"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-video-lessons/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/lzheng0411/lzheng-fitness/lzheng-video-lessons"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-video-lessons.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 | $0.00074 | $0.01089 |
| Opus 5.5 | $0.00030 | $0.00436 |
| Sonnet 5.5 | $0.00015 | $0.00218 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
lzheng-video-lessons 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 1mo 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
Lzheng 分段视频教学
用户给链接或本地视频并要求“分段讲解、知识库教学、接入健身系统”时使用。沿用当前用户的素材、目标与发布授权,不要求重新确认已有决定。创建 Skill 本身不代表发布新课程。
1. 获取并核对来源
优先复用已核对的媒体、转写和时间戳;有 lzheng-video-learning 时用它的获取/转写工具,个人环境也可用已安装的 douyin-question-distiller。没有这些工具时接收用户本地视频和转写,保留同样数据契约。不要绕过登录、验证码、付费或访问限制;同一临时媒体地址失败最多重新获取一次,失败条目记录原因,继续可独立完成部分。
在用户 workspace 中保存来源 URL、作品 ID、讲者/上传者、时长、媒体哈希、转写和关键帧。运行材料不得进入 Skill 或公开仓库。逐段核对时间、数字、单位、动作版本与否定词;只做过机器转写/抽帧就如实写明,不声称逐字听校。
2. 编写章节
读取 讲解与数据契约。章节必须有精确 start/end、稳定 ID、目标、详细步骤与步骤时间点。分段按教学意义,不固定章节数、不等分时间。允许未收录片段,但要在 coverage_note 说明;章节不能重叠、越界。
正文直接讲“你怎么准备、怎么做、为什么、怎样判断、哪里容易错”,不用“作者演示了/他说了”代替解释。署名和证据放来源区。不要补造片中没有的组数、重量或通用结论;来源建议与额外解释分开标注,存疑处保留待核对。
3. 生成可试用课程
python scripts/lesson.py validate --input <lesson.json>
核对通过后:python scripts/lesson.py build --input <lesson.json> --out <新课程目录> [--media <mp4> --poster <jpg>]
工具只接受新输出目录,避免覆盖已有课程和学习笔记。更新使用同一 lesson.id/chapter.id 并生成新版本目录,验收后替换注册入口,保留旧版便于回退。默认只链接原视频;复制媒体需要 lesson.json 记录 media_rights_basis。开源包不附带原视频、截图、完整转写或私人资料。
播放器保持黑白、单列浮动目录、编号步骤、原片起止时间、到终点暂停、重播/循环、步骤跳转、按课程保存本机笔记。缺少媒体明确显示“仅原视频链接”,不留假播放器。真实媒体必须验证可解码、非黑屏、拖动与片段终点;浏览器后台限流时不承诺逐帧剪辑精度。需要独立片段文件时可由 ffmpeg 导出,但默认复用单原片的时间窗口,避免重复占用空间。
4. 接入与复用
python scripts/lesson.py integrate --html <工作台.html> --lesson <课程目录> --backup-dir <备份目录> [--apply]
先预检,已获接入授权再 apply。课程必须位于工作台目录树内。只按稳定 ID 更新 knowledge-lessons-data;支持现有个人工作台 UI,其他模板安装通用知识库对话框。保留 workbench-data、账号配置和已有知识;不自动匹配相似动作,精确动作联动交给现有适配器,需逐个核对变式。
5. 验收与发布
读取 接入与发布。先完成本地检查与可审阅页面。已授权发布就继续现有发布器;未授权仅给预览,不把“入库”推断成上传许可。媒体再分发范围与代码许可分别判断。
发布需包含课程 HTML、chapters.js 和授权媒体/海报;以依赖清单为准。不得让公开匿名工作台夹带私人课程。上线后逐文件 HTTP/哈希核验,并实际打开知识库、选段、播放/终点、返回。分别记录 source_verified、lesson_built、integrated、release_prepared、deployed、online_verified;脚本完成不等于用户已学会或练过。
What ships with it
7 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.
- 1mo ago First seen · 43 lines · 74 tokens per session scan A 6a0f1e3bc12f
lzheng-video-lessons is a skill published in the GitHub repository LZheng0411/Lzheng-fitness (140 stars, last pushed 6d ago), licensed MIT. It adds 74 tokens to every session and 1,089 once invoked, about $0.0003 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 2026-09-24.
lzheng-video-lessons compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lzheng-video-lessonsLZheng0411/Lzheng-fitness | Skill | 140 | 6d ago | MIT | A | 74 | Codex |
| hr-onboardingnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | today | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | yesterday | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 2d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | today | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.5k | today | Apache-2.0 | A | 25 | Claude Code, Codex |