ChatCut is an AI video editor that lets coding agents edit footage, add captions, remove silences, generate media, and export editable timelines. It is used by people who want agents such as Claude Code, Codex, or Cursor to perform video-editing work, and the catalogue entries connect those agents to ChatCut.
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 ChatCut-Inc/agent-plugin --skill chatcut-video-editorgit clone --depth 1 https://github.com/ChatCut-Inc/agent-pluginWrote 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/chatcut-inc/agent-plugin/chatcut-video-editor)<a href="https://agentmods.dev/skills/chatcut-inc/agent-plugin/chatcut-video-editor"><img src="https://agentmods.dev/badge/skills/chatcut-inc/agent-plugin/chatcut-video-editor/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/chatcut-inc/agent-plugin/chatcut-video-editor"><img src="https://agentmods.dev/badge/skills/chatcut-inc/agent-plugin/chatcut-video-editor.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 | $0.00070 | $0.03051 |
| Opus 5.5 | $0.00028 | $0.01220 |
| Sonnet 5.5 | $0.00014 | $0.00610 |
| Haiku 4.5 | $0.00007 | $0.00305 |
Grade A, and why
chatcut-video-editor 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 yesterday.
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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatCut 视频剪辑专家
通过 ChatCut Desktop,在用户当前打开的真实项目里完成剪辑。用户的原始创作 要求始终是主任务;安装和连接只是首次使用的准备步骤。优先由本专家完成, 需要用户授权或点击时简明说明,恢复后继续原任务。 不要用本地 FFmpeg 合成、网页编辑器或托管 ChatCut 连接器冒充可编辑的 Desktop 时间线。
先判断当前状态
- 若当前已有 ChatCut Desktop 连接器提供的
get_active_project,先调用它确认 项目,再按下方“发现并调用编辑操作”继续用户原本的要求。连接器前缀可能是chatcut_desktop、chatcut_desktop_npx等,按实际工具名称识别同一个连接器。 成功连接后不重复安装、改连接器或检查本地配置,也不通过 shell/自写客户端 绕开宿主工具。 - 若当前 Agent 正运行在 ChatCut Desktop 内,不使用本 Skill。应用内置的 项目绑定 MCP 和 Skills 是权威来源。
- 若工具缺失,先判断正式版 ChatCut Desktop 是否已经安装并运行:未安装时 协助安装,已安装时只需打开,然后按“恢复豆包连接”检查连接器和工具发现。 工具暂未出现不等于连接器没有绑定。Skill 只能使用豆包已经加载到任务中的 Connector,不能给当前任务注册或挂载缺失的 Connector;不要通过 shell 启动独立连接进程,也不要要求普通用户理解或填写 MCP 配置。
发现并调用编辑操作
本 Skill 和后续工作流 Skill 中的“调用 push_asset、submit_image、
create_project 等”指执行对应的 ChatCut 操作;实际调用方式取决于当前
连接器暴露的入口。适用于生图、剪辑、字幕、MG、进度查询和导出等所有操作。
新版 Desktop:三个入口
顶层只有 get_active_project、get_guidelines、execute 是正常设计,
不能据此判断生图或剪辑能力缺失。
-
直接调用
get_active_project,入参为{}。确认项目后,直接调用同一 连接器的get_guidelines,入参也为{}。这两个入口本身不通过execute。 -
从返回的
operations中查找需要的操作,读取其准确name、说明和inputSchema。若宿主把长结果保存为文件,读取所需操作的完整条目。 操作清单是编辑说明,读取后不会新增一批顶层 MCP 工具。 -
调用同一连接器的
execute,把操作名放入name,操作参数对象放入arguments。例如,清单确认支持push_asset后,向execute传入:{ "name": "push_asset", "arguments": { "filePath": "<用户素材的绝对路径>" } }这里
name是不带宿主前缀的操作名,arguments是 JSON 对象,不能将其 转成字符串,也不能把filePath放在execute的最外层。宿主若另有通用 MCP 调用工具,其外层参数遵循宿主自身 schema,不与上述操作参数混用。 -
生图同样先从清单查找对应操作(例如
submit_image),按实际 schema 准备 参数,再用execute执行;生成后的进度查询和素材放入时间线也走同一路径。 不要因为顶层找不到submit_image,就判定无法生图或切换到别的服务。 -
正常情况下复用已读清单;切换项目或收到“操作不可用”时重新确认项目并 获取清单。只有成功读取完整操作清单、按名称和用途仍找不到所需能力时,才 报告当前项目未提供该操作;读取清单本身失败时报告实际错误,不推断能力缺失。
旧版 Desktop:操作直接暴露
同一连接器没有上述三个入口、但直接提供 push_asset 等具体工具时,按该
工具的实际 schema 直接调用,参数无需包一层 name / arguments。不要调用
不存在的 execute。若同时存在新旧入口,优先使用新版流程。
安装正式版 Desktop
根据系统和 CPU 架构只使用匹配的官方地址:
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.
- yesterday First seen · 172 lines · 70 tokens per session scan A acd258a432bf
chatcut-video-editor is a skill published in the GitHub repository ChatCut-Inc/agent-plugin (1,006 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 3,051 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 2026-11-06.
chatcut-video-editor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chatcut-video-editorChatCut-Inc/agent-plugin | Skill | 1.0k | yesterday | Apache-2.0 | A | 70 | Codex |
| cukaimax-tax-authorityjakzaizzat/cukaimax-agent | Skill | 0 | 2mo ago | MIT | A | 102 | Codex |
| 9router-sttdecolua/9router | Skill | 32k | 9d ago | MIT | A | 63 | Claude Code, Codex |
| 9router-web-fetchdecolua/9router | Skill | 32k | 9d ago | MIT | A | 67 | Claude Code, Codex |
| 9router-web-searchdecolua/9router | Skill | 32k | 9d ago | MIT | A | 74 | Claude Code, Codex |
| 9routerdecolua/9router | Skill | 32k | 9d ago | MIT | A | 84 | Claude Code, Codex |
| writing-livekit-scenariosfcakyon/claude-codex-settings | Skill | 1.2k | yesterday | Apache-2.0 | A | 178 | Claude Code |