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.
git clone --depth 1 https://github.com/HuangYincan/VideoNote-MCPWrote 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/commands/huangyincan/videonote-mcp/videonote-setup)<a href="https://agentmods.dev/commands/huangyincan/videonote-mcp/videonote-setup"><img src="https://agentmods.dev/badge/commands/huangyincan/videonote-mcp/videonote-setup/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/commands/huangyincan/videonote-mcp/videonote-setup"><img src="https://agentmods.dev/badge/commands/huangyincan/videonote-mcp/videonote-setup.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 | $0.00036 | $0.01600 |
| Opus 5 | $0.00018 | $0.00800 |
| Sonnet 5 | $0.00007 | $0.00320 |
| Haiku 4.5 | $0.00004 | $0.00160 |
Grade A, and why
videonote-setup 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 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.
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VideoNote-MCP 配置向导
按顺序执行配置检查与引导。已就绪的步骤直接跳过，不要重复提问；每步做完汇报结果。
0. 前置：确认 MCP 工具已挂载（最重要，不满足则停下）
本命令的一切配置操作都依赖 videonote 的 MCP 工具（health_check / get_config 等，工具名可能带前缀如 mcp__videonote__* 或 mcp__plugin_videonote_videonote__*，按工具名判断，不按前缀）。
先确认本会话里是否挂载了它们。不要用 CLI / 读配置文件代替 MCP 工具，也不要自行判断「哪份配置权威」——server 返回的 data_dir 才是权威（不要像 diff 数据目录那样去猜）。
- 已挂载 → 继续第 1 步。
- 未挂载 → 立即停止并引导，不要继续后面的步骤、不要替代性跑 CLI/读文件：
- 最可能原因：插件装好后没重启会话，插件的 MCP server 尚未加载。请用户重启 Claude Code 会话（或
/reload-plugins），再重跑本命令。 - 若重启后仍没有：让用户在会话里跑
/mcp，看videonote是否 Connected、报什么错。若/mcp里根本看不到 videonote 条目（插件虽 enabled 但 server 没注册）→ 说明插件 manifest 的mcpServers没生效，让用户重装插件再重启：claude plugin marketplace update videonote+claude plugin disable videonote@videonote+claude plugin install videonote@videonote。 - 常见报错：uvx 首次从 git 拉包超时（默认 30s）。用
MCP_TIMEOUT=120000 claude重启会话再试。 - 可选 CLI 自检（只验证 CLI 可用，不等同 MCP 工具挂载）——让用户在终端跑：
uvx --from git+https://github.com/HuangYincan/VideoNote-MCP videonote providers list
- 最可能原因：插件装好后没重启会话，插件的 MCP server 尚未加载。请用户重启 Claude Code 会话（或
- 唯一允许的只读检查：FFmpeg 是否可用（
ffmpeg -version，health_check也会查，仅作提前确认）。其余一律等 MCP 工具。
1. 状态体检
调用 health_check，看 FFmpeg / 数据库 / 转写引擎 / whisper 模型就绪状态。
- FFmpeg 缺失 → 先让用户安装 FFmpeg（macOS
brew install ffmpeg，其他平台见官方包源），装完重跑。
2. LLM 供应商（API key，可选）
默认路径由当前对话 Agent 写笔记，不需要配置 LLM key。仅当 Agent 无法看图（走 generate_note 后备）时才需要。
调用 get_config()，看 providers 列表（id / 名称 / key 掩码）与 app_config.default_provider_id。
- 已有供应商填了 key → 跳过本步。
- 没有已填 key 的供应商 → 告诉用户这是后备 LLM 用的，需要时在本会话输入：
! videonote providers list（看供应商 id）! videonote providers set <provider_id> --api-key '...'（填 key）- API key 为隐藏输入，值不经过对话；这一步必须由用户亲手在终端完成，不要试图用其它方式获取 key。
- 也可以用内置中转站：
! videonote setup（全屏向导，独立终端更稳）。
3. 语音转写引擎
调用 get_config()，看 transcriber 段（引擎 / 模型尺寸 / 预处理 / 说话人分离 / 就绪状态）。
- 本地引擎（fast-whisper / mlx-whisper）模型未下载 → 让用户输
! videonote transcriber download <size>。 - 要切换引擎 / 尺寸 → 让用户输
! videonote transcriber set --engine fast-whisper|groq|bcut|kuaishou|mlx-whisper|funasr [--size <size>]。 - 云端引擎（groq / bcut / kuaishou）无需下载模型。
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 Changed · +2 lines b8fcc22a92a6
- 5d ago Changed 6c6085212a26
- 9d ago First seen · 70 lines · 36 tokens per session scan A 26c1f9771204
videonote-setup is a command published in the GitHub repository HuangYincan/VideoNote-MCP (55 stars, last pushed 5d ago), licensed MIT. It adds 36 tokens to every session and 1,600 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 2026-08-30.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
release
Git geçmişinden hedef kitleye uygun sürüm notları oluştur.
spec-forge
Use when generating software specifications — full chain (Idea→Decompose→Tech Design + Feature Specs) or individual documents.
dd-init
Initialize product documentation structure in current directory.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.