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/sun-guannan/vectcutapi/skillnpx skills add sun-guannan/VectCutAPI --skill skillgit clone --depth 1 https://github.com/sun-guannan/VectCutAPIWrote 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/sun-guannan/vectcutapi/skill)<a href="https://agentmods.dev/skills/sun-guannan/vectcutapi/skill"><img src="https://agentmods.dev/badge/skills/sun-guannan/vectcutapi/skill.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 | $0.00000 | $0.03205 |
| Opus 5 | $0.00000 | $0.01603 |
| Sonnet 5 | $0.00000 | $0.00641 |
| Haiku 4.5 | $0.00000 | $0.00320 |
Grade B, and why
vectcut-api scanned grade B with 2 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 4d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
response = requests.post("http://localhost:9001/create_draft", json={ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
response = requests.post("http://localhost:9001/create_draft", json={ How it starts
The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VectCutAPI 视频剪辑 API
概述
VectCutAPI 是一款强大的云端视频剪辑 API 工具，通过编程方式控制剪映/CapCut 进行专业视频编辑。它填补了 AI 生成素材与专业视频编辑之间的空白，提供精确的编辑控制能力。
核心优势
- 双协议支持 - HTTP REST API 和 MCP 协议
- 实时预览 - 网页预览无需下载
- 可二次编辑 - 导入剪映/CapCut 精修
- 云端处理 - 全云端操作生成视频
系统要求
- Python 3.10+
- 剪映 或 CapCut 国际版
- FFmpeg (可选，用于某些视频处理)
快速启动
# 安装依赖
pip install -r requirements.txt # HTTP API 基础依赖
pip install -r requirements-mcp.txt # MCP 协议支持 (可选)
# 配置文件
cp config.json.example config.json
# 启动服务
python capcut_server.py # HTTP API 服务器 (端口: 9001)
python mcp_server.py # MCP 协议服务器
工作流程
标准视频制作流程
1. 创建草稿 (create_draft)
- 设置分辨率: 1080x1920 (竖屏) / 1920x1080 (横屏) / 1080x1080 (方形)
- 获取 draft_id
2. 添加素材轨道
- add_video: 添加视频轨道
- add_audio: 添加音频轨道
- add_image: 添加图片素材
3. 添加文字元素
- add_text: 添加标题、说明文字
- add_subtitle: 导入 SRT 字幕文件
4. 应用特效
- add_effect: 添加视频特效
- add_sticker: 添加贴纸素材
- add_video_keyframe: 添加关键帧动画
5. 保存草稿
- save_draft: 生成可导入剪映的草稿文件
AI 视频生成工作流
AI 文案生成
↓
TTS 文字转语音 → audio_url
↓
图生视频 → video_url
↓
VectCutAPI 组合草稿
↓
导出或二次编辑
批量视频处理
使用 auto_video_editor.py 处理 Excel 表格驱动的批量视频制作。
API 接口
核心操作
| 接口 | 方法 | 功能 |
|---|---|---|
/create_draft |
POST | 创建新草稿项目 |
/save_draft |
POST | 保存草稿并生成 URL |
/query_draft_status |
POST | 查询草稿状态 |
/query_script |
POST | 查询草稿脚本内容 |
/generate_draft_url |
POST | 生成草稿预览 URL |
素材添加
| 接口 | 方法 | 功能 |
|---|---|---|
/add_video |
POST | 添加视频轨道 |
/add_audio |
POST | 添加音频轨道 |
/add_image |
POST | 添加图片素材 |
/add_text |
POST | 添加文字元素 |
/add_subtitle |
POST | 添加 SRT 字幕 |
/add_sticker |
POST | 添加贴纸 |
/add_effect |
POST | 添加视频特效 |
/add_video_keyframe |
POST | 添加关键帧动画 |
查询接口 (GET)
| 接口 | 功能 |
|---|---|
/get_intro_animation_types |
获取入场动画类型 |
/get_outro_animation_types |
获取出场动画类型 |
/get_transition_types |
获取转场效果类型 |
/get_mask_types |
获取蒙版类型列表 |
/get_audio_effect_types |
获取音频特效类型 |
/get_font_types |
获取字体类型列表 |
/get_video_scene_effect_types |
获取场景特效类型 |
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.
- 4d ago First seen · 391 lines · 0 tokens per session scan B 31cb88ecc6af
vectcut-api is a skill published in the GitHub repository sun-guannan/VectCutAPI (2,199 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,205 tokens. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-cut
剪辑中文口播原素材：逐词转录、词典修字出修字表、五轮扫描找口误与重复、汇总表与重复句子表、打开 Studio 让用户复核、复盘沉淀用户偏好与词典。只产出一份已复核的删词账本，不切媒体、不做字幕、不做分镜动画。用户说剪口播、处理口误、生成口播基础素材、继续剪口播，或确认卡回传 action=returncutreview 时使用。不要用于执行物理剪切、导出剪后视频、单独安装、单独打开工作台或口播分镜成片。.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.