chengfeng-videocut-skills is a Codex plugin that coordinates Chinese voiceover video editing through the chengfeng-videocut runtime, whose command-line tools and APIs perform the actual processing. It is for agents that need to edit and export narrated videos, while its catalogue skills handle decisions and workflow coordination around that runtime.
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 Agentchengfeng/chengfeng-videocut-skills --skill chengfeng-cutgit clone --depth 1 https://github.com/Agentchengfeng/chengfeng-videocut-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/agentchengfeng/chengfeng-videocut-skills/chengfeng-cut)<a href="https://agentmods.dev/skills/agentchengfeng/chengfeng-videocut-skills/chengfeng-cut"><img src="https://agentmods.dev/badge/skills/agentchengfeng/chengfeng-videocut-skills/chengfeng-cut/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/agentchengfeng/chengfeng-videocut-skills/chengfeng-cut"><img src="https://agentmods.dev/badge/skills/agentchengfeng/chengfeng-videocut-skills/chengfeng-cut.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00154 | $0.04744 |
| Opus 5 | $0.00077 | $0.02372 |
| Sonnet 5 | $0.00031 | $0.00949 |
| Haiku 4.5 | $0.00015 | $0.00474 |
Grade A, and why
chengfeng-cut 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
剪口播
从一条视频到一份人工复核过的删词账本（Cuts + EDL），不碰媒体文件。七步一线：
0 就绪 引用「检查更新」的就绪检查（本 Skill 不带环境逻辑）
1 建档 真实视频 → 云端逐词转录 → 产品建项目 → 起服务 → 读回状态
2 修字 词典把字改对（通用一本 + 用户一本）→ 出修字表
3 删词 读偏好与规则 → 五轮扫描，每轮只找一类，只记行
4 汇总 删词汇总表 + 重复句子表 → 按表自读校验
5 审核 全量提交 → 两张表呈给用户 → 打开 Studio 亲自复核
6 复盘交棒 对比提案与终版 → 归档三抽屉 → 报告四件事
不切媒体：账本改一次是几十毫秒，切一次是一个不可撤销的文件。到本 Skill 结束， 磁盘上没有任何新视频。Skill 做语义判断与编排；产品 Runtime 是项目、Cuts 和 Studio 状态的唯一写入者。
用户只在三处说话：同源项目选继续还是重来（仅剪过时）、Studio 复核、完成确认。 其余一律单向汇报，不停下等回复。每步的完成判据是它的产出物：没出表，不算完成。
先读取并执行 业务 Skill 的阶段合同。 本文步骤与合同阶段的对应：1=preflight+Product state readback，5=proposal+Product CAS， 审核=project-level review binding。合同后三个阶段（确认、执行、验收）属于导出 Skill。
各条规矩的事故来历在 事故簿——规矩在正文，故事在那边。
0. 就绪
先执行 检查更新 的「就绪检查」——skills 是否
最新、Runtime 是否配套；插件根也在那里定位（本文命令里的 <插件根> 都代入
那个字面路径）。只有拿到「就绪」才继续；「需新会话」或「停」都按它的处置执行
（含「禁止自制替代界面」禁令）。
若就绪结果为 runtime.kind=desktop-managed，它与 CLI 安装共用同一稳定入口和
launchd/windows-task 服务，直接继续；不要查找 Electron 安装目录、另装 Bun /
FFmpeg，或启动第二个 Runtime。
1. 建档：真实输入 → 转录 → 产品建项目
干什么：把用户的本地真实视频和云端逐词稿交给产品，原子建档，起服务，读回状态。
# 云端逐词转录（生成任务目录内的 transcript 候选）之后：
node "<插件根>/scripts/videocut-cli.cjs" project create "<项目目录>" --video "<任务目录内的视频文件>" --transcript "<任务目录内的逐词稿>" --json
node "<插件根>/scripts/ensure-running.cjs" --json # 产品声明式确保常驻服务（5190）
node "<插件根>/scripts/videocut-cli.cjs" workflow get "<项目目录>" --json # Product state readback
node "<插件根>/scripts/videocut-cli.cjs" cuts get "<项目目录>" --json
规矩：
- 只接受用户给出的真实口播视频或现有真实项目；没有真实媒体就停止，禁止用示例、 占位视频顶替
- 转录只用当前环境已获准的云端 ASR；禁止回退本地 ASR；没有可用云端 ASR 时报告
missing_cloud_transcription_adapter，不开 Studio、不伪造 transcript --video/--transcript必须是任务目录内的真实文件；画幅比不要传——产品会 从视频实际尺寸自动推导（Runtime 0.4.4+）。只有用户明确要求特殊画幅时才加--aspect-ratio W:H- 已有规范项目先
inspect确认并复用，不重复创建projectId；同一个视频剪过时 问用户：继续上次，还是重来（这是三个说话点之一）。project prepare是幂等 编译器，只在恢复中断或明确刷新时用，中断了直接重跑即可 project create是唯一入口：不经过素材库、上传会话或额外 Skill；Skill 不得先写project.json- 服务必须由脚本确认
healthy=true、runtimeMode=launchd（macOS）或runtimeMode=windows-task（Windows）、版本兼容、URL 为 canonical 5190 后才继续；失败透传结构化错误并停止，禁止回退 foreground、换端口、 杀未知进程 - 两份 readback 必须指向同一个
projectId，保存 workflow stage 与 Project / Cuts / EditList 三个 revision；缺失或不一致即停止
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.
- 12d ago First seen · 294 lines · 154 tokens per session scan A 56322f1f9887
chengfeng-cut is a skill published in the GitHub repository Agentchengfeng/chengfeng-videocut-skills (2,989 stars, last pushed 3d ago), licensed Apache-2.0. It adds 154 tokens to every session and 4,744 once invoked, about $0.0008 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 2026-08-30.
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.
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…
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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
meme-creator
A media-making workflow that places logos, avatars, or stickers on moving objects in a video, keeping them aligned frame by frame, and exports MP4 and GIF files. It also supports a single-frame image meme without motion tracking.