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/heristop/leclap/cross-platform-ffmpegnpx skills add heristop/leclap --skill cross-platform-ffmpeggit clone --depth 1 https://github.com/heristop/leclapWrote 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/heristop/leclap/cross-platform-ffmpeg)<a href="https://agentmods.dev/skills/heristop/leclap/cross-platform-ffmpeg"><img src="https://agentmods.dev/badge/skills/heristop/leclap/cross-platform-ffmpeg.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 5.1 | $0.00045 | $0.00689 |
| Opus 5 | $0.00023 | $0.00345 |
| Sonnet 5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00005 | $0.00069 |
Grade A, and why
cross-platform-ffmpeg 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 6d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Platform FFmpeg
Overview
The core never calls FFmpeg directly — it goes through an AbstractFFmpeg adapter chosen by the runtime. PlatformBridge detects the environment and wires the right adapter; the Node path additionally auto-detects an FFmpeg binary with a fallback chain. Full detail: docs/architecture.md.
- Bridge:
packages/ffmpeg-video-composer/src/platform/PlatformBridge.ts - Adapters:
packages/ffmpeg-video-composer/src/platform/ffmpeg/(AbstractFFmpeg,FFmpegNodeAdapter,FFmpegStaticAdapter,FFmpegWasmAdapter,FFmpegDetector, plus*Music*adapters)
Adapter selection by runtime
| Runtime | FFmpeg | Filesystem | Logger |
|---|---|---|---|
| Node.js | FFmpegNodeAdapter → FFmpegStaticAdapter |
FilesystemNodeAdapter |
PinoLogAdapter |
| Browser | FFmpegWasmAdapter (@ffmpeg/ffmpeg) |
BrowserFilesystemAdapter (IndexedDB) |
console logger |
| React Native | FFmpegLeclapAdapter (on-device engine) |
FilesystemExpoAdapter |
ReactNativeLogger |
Node detection / fallback chain
FFmpegDetector resolves, in order:
- System FFmpeg (
ffmpeg -versionon PATH) →FFmpegNodeAdapter(fluent-ffmpeg). ffmpeg-staticbundled binary →FFmpegStaticAdapter.@ffmpeg/ffmpegWASM →FFmpegWasmAdapter.- None found → throws with platform-specific install instructions.
Installing system FFmpeg (e.g. via mise) is the fastest Node path.
Entry points
- Node:
packages/ffmpeg-video-composer/src/index.tsregisters Node adapters into the tsyringecontainer. - Browser/WASM:
packages/ffmpeg-video-composer/src/browser.tsregisters WASM + IndexedDB + browser event manager.
Keep the two bundles separate — anything imported by browser.ts must be browser-safe (no Node built-ins).
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.
- 6d ago First seen · 53 lines · 45 tokens per session scan A 38f60ba7c587
cross-platform-ffmpeg is a skill published in the GitHub repository heristop/leclap (24 stars, last pushed 10d ago), licensed MIT. It adds 45 tokens to every session and 689 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 skills, from other repositories
qiaomu-cut
把一句话需求转成可复现、可验收视频工程的乔木智能剪辑导演。Use when the user asks to create, plan, edit, remix, explain, narrate, subtitle, animate, composite, or render a video; build English-learning movie mixes, person profiles, explainers, product launch videos, cinematic shorts, social clips, course/PPT videos, AI…
uniwind
Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or debugging components in a React Native project that uses Uniwind classNames. Covers setup, Metro config, global.css, theming, className props, accent- color props, platform/data/state/responsive variants, CSS variables, custom utilities…
upgrading-react-native-storybook
Incrementally upgrade React Native Storybook across the supported migration paths. Use when upgrading @storybook/react-native projects from 5.3.x to 6.5.x, 6.5.x to 7.6.x, 7.6.x to 8.3.x, 8.x to 9.x, or 9.x to 10.x. Detect the currently installed Storybook version, choose only the next migration step, update…
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
videohub-beat-editor
根据一段音频、歌曲或参考视频的节拍，为一个长视频、多个视频或素材目录自动建立镜头候选库，生成卡点剪辑计划，并批量渲染 16:9、3:4、4:3、9:16 等多画幅成片。支持固定镜头数量、强拍切换、歌词字幕、镜头替换、封面、标题、caption、hashtags 和完整 QA。用于“按音乐卡点剪视频”“给音频和素材批量做卡点视频”“检测强拍并自动选镜头”“同一计划输出多个画幅”等任务。.
videohub-cover-designer
为 VideoHub 的影视解说、连续剧、电影、卡点视频和短视频制作可在个人主页小缩略图中辨认的封面。输入剧照、视频帧或已有底图，突出剧名、集数和简短看点，统一生成 9:16、3:4、4:3、16:9 封面与缩略图预览。用于“做封面”“修改封面”“加大集数”“生成横版和竖版封面”“沿用上一集封面模板”“制作抖音或视频号缩略图”等任务。.