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 znlgis/opengis-skills --skill ffmpeggit clone --depth 1 https://github.com/znlgis/opengis-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/znlgis/opengis-skills/ffmpeg)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/ffmpeg"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/ffmpeg/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/znlgis/opengis-skills/ffmpeg"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/ffmpeg.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 | $0.00122 | $0.05132 |
| Opus 5.5 | $0.00049 | $0.02053 |
| Sonnet 5.5 | $0.00024 | $0.01026 |
| Haiku 4.5 | $0.00012 | $0.00513 |
Grade B, and why
ffmpeg scanned grade B with 1 finding 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 today.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install ffmpeg How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
官方文档: https://ffmpeg.org/ffmpeg.html(滤镜 https://ffmpeg.org/ffmpeg-filters.html,封装格式 https://ffmpeg.org/ffmpeg-formats.html)
下载: https://ffmpeg.org/download.html(源码与各平台静态构建)
包管理器:
apt install ffmpeg/brew install ffmpeg/winget install Gyan.FFmpeg/ 官方静态包(最新 9.0.2,截至 2026-10)版本: 9.0.2(
release/9.0分支的最新补丁版);上一分支 8.1.3,更早 7.1.x | 上游无 GitHub Release tag,版本以 https://ffmpeg.org/releases/ 与 RELEASE_NOTES 为准许可证: LGPL-2.1-or-later(默认);若构建启用了
--enable-gpl且实际用到 GPL 部分(如 libx264/libx265),整个 FFmpeg 转为 GPL-2.0-or-later——多数发行版与「full build」静态包属于后者,商用集成前先看ffmpeg -version的构建配置
概述
FFmpeg 是一套处理音视频的命令行工具与库:ffmpeg 转码/裁剪/拼接/推流,ffprobe 只读探测,ffplay 预览。它不做创意编辑,而是把「解码 → 滤镜链 → 编码」这条流水线暴露成参数,适合放进脚本、CI 与批处理。对 GIS/三维场景而言,它最常见的角色是把视频变成「可以计算的东西」:帧序列、纹理、切片、时间戳对齐的影像源。
核心概念只有四个:
- 输入输出:
-i声明输入,其余裸参数是输出文件;一个命令可以有多个输入与输出 - 流选择:
-map决定哪些流进入哪个输出(默认每种类型只取一路) - 滤镜链:
-vf(视频)/-af(音频)/-filter_complex(多输入),用逗号串联 - 编解码参数:
-c:v/-crf/-preset/-pix_fmt决定画质与体积
安装
包管理器(推荐,最省事)
# Debian / Ubuntu
sudo apt install ffmpeg
# macOS
brew install ffmpeg
# Windows(winget)
winget install Gyan.FFmpeg
官方静态构建 / 源码
# 下载页提供各平台静态包(含完整编码器),解压后把 bin 加入 PATH
# https://ffmpeg.org/download.html
# 源码编译(裁剪出自定义编解码集)
./configure --prefix=/usr/local --enable-gpl --enable-libx264 --enable-libx265
make -j$(nproc) && sudo make install
验证
ffmpeg -version # 第一行含版本与构建配置
ffprobe -version
ffmpeg -hide_banner -encoders 2>/dev/null | grep -E 'libx264|libx265|aac'
ffmpeg -hide_banner -hwaccels # 列出本机可用的硬件加速后端
核心命令
探测:先 ffprobe 再动手
批处理前永远先探测,避免用错帧率、色彩或时长:
# 一行摘要(分辨率/编码/帧率/时长)
ffprobe -v error -select_streams v:0 \
-show_entries stream=width,height,r_frame_rate,codec_name,duration \
-of default=noprint_wrappers=1 input.mp4
# JSON(便于脚本消费)
ffprobe -v error -print_format json -show_format -show_streams input.mp4
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.
- today First seen · 295 lines · 122 tokens per session scan B 6fc0ebd3b573
ffmpeg is a skill published in the GitHub repository znlgis/opengis-skills (75 stars, last pushed today), licensed MIT. It adds 122 tokens to every session and 5,132 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-28.
Other skills, from other repositories
video-streaming-expert
Expert in video streaming technologies, HLS, DASH, adaptive bitrate streaming, CDN delivery, DRM protection, and video encoding/transcoding. Use when the user mentions video, streaming, media, WebRTC, multimedia, or HLS, or when the task involves Streaming Protocols, Adaptive Bitrate Streaming, FFmpeg Video…
c-video
Download videos, extract audio, convert formats, and clip segments using yt-dlp and ffmpeg. Supports YouTube, Vimeo, and hundreds of other sites.
mediago
A tool for downloading videos from direct links, m3u8 or HLS streams, and Bilibili through a running MediaGo service. HLS is a common format for streamed video.
claude-real-video
Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.
claude-real-video-for-agents
Install and use crv (claude-real-video) — a tool that lets any AI agent watch videos by extracting scene-aware keyframes, deduplicating them, and transcribing audio. Use when the user shares a video URL or file and wants it analyzed, summarized, or discussed.
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.