What is ffmpeg-render-pipeline?

A rendering workflow for FFmpeg, a tool that converts and processes video and audio files. It supports parallel jobs, hardware encoding, audio mixing, checkpoints, dashboards, optical-flow frame creation, colour work, and YouTube-ready output.

Use it to render videos or audio, combine sound, encode with a GPU, create smoother motion with optical flow, apply colour adjustments, and prepare files for YouTube.

It organises demanding media renders and helps continue interrupted jobs while producing consistent output.

How beeswaxpat/ffmpeg-render-pro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to beeswaxpat/ffmpeg-render-pro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/beeswaxpat/ffmpeg-render-pro/main/.claude/skills/ffmpeg-render-pipeline/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/beeswaxpat/ffmpeg-render-pro

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/beeswaxpat/ffmpeg-render-pro/ffmpeg-render-pipeline/github.svg)](https://agentmods.dev/skills/beeswaxpat/ffmpeg-render-pro/ffmpeg-render-pipeline)

Your own site

<a href="https://agentmods.dev/skills/beeswaxpat/ffmpeg-render-pro/ffmpeg-render-pipeline"><img src="https://agentmods.dev/badge/skills/beeswaxpat/ffmpeg-render-pro/ffmpeg-render-pipeline/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/beeswaxpat/ffmpeg-render-pro/ffmpeg-render-pipeline"><img src="https://agentmods.dev/badge/skills/beeswaxpat/ffmpeg-render-pro/ffmpeg-render-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,651 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00055	$0.03651
Opus 5.5	$0.00022	$0.01460
Sonnet 5.5	$0.00011	$0.00730
Haiku 4.5	$0.00006	$0.00365

Measured 2mo ago against content hash 7caa3f3777e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ffmpeg-render-pipeline 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 2mo 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.

.claude/skills/ffmpeg-render-pipeline/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ffmpeg Render Pipeline - Complete Reference

You are an expert video/audio render engineer. This skill covers the ffmpeg-render-pro toolkit - a parallel rendering system optimized for YouTube Shorts and long-form videos.

Toolkit location: The user may have ffmpeg-render-pro installed globally (npm install -g ffmpeg-render-pro provides the ffmpeg-render-pro CLI) or as a local dependency. Check with ffmpeg-render-pro version or node -e "require('ffmpeg-render-pro')". In a repo checkout, node bin/ffmpeg-render-pro.js is equivalent to the installed CLI.

Prerequisites

Before any render task, verify:

Node.js >= 18 - node --version
ffmpeg available - ffmpeg -version. If ffmpeg is installed but not on PATH, set FFMPEG_RENDER_PRO_FFMPEG to its full path (a sibling ffprobe is auto-derived; FFMPEG_RENDER_PRO_FFPROBE overrides it explicitly). Both are read at call time.
If ffmpeg is missing entirely, tell the user: "Install ffmpeg from https://ffmpeg.org/download.html and ensure it's on your PATH, or set FFMPEG_RENDER_PRO_FFMPEG to its full path."

Quick Start (for any render task)

The shortest path to a first render is three commands. Use it whenever the user has no worker script yet:

# 1. Prove the setup: 5s test render, dashboard opens
ffmpeg-render-pro benchmark

# 2. Write the starter worker (only renderFrame() needs editing; --force overwrites)
ffmpeg-render-pro init my-worker.js

# 3. Render it (output.mp4)
ffmpeg-render-pro render my-worker.js --duration=5

Without a global install, prefix each command with npx (npx ffmpeg-render-pro init). Over MCP the same path is get_worker_template (save starterSource to a file, edit renderFrame) then render_video.

# Check system capabilities
ffmpeg-render-pro info

# Render a YouTube Short shape (vertical, 60s) with the bundled test worker
ffmpeg-render-pro benchmark --width=1080 --height=1920 --fps=30 --duration=60

# Render with your own worker script
ffmpeg-render-pro render my-worker.js --duration=60 --output=video.mp4

# Force CPU or GPU encoding during detection
ffmpeg-render-pro detect-gpu --cpu
ffmpeg-render-pro detect-gpu --gpu

Read the full file on GitHub · 309 lines

Changes

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.

2mo ago Changed · +12 lines 7caa3f3777e3
2mo ago First seen · 297 lines · 55 tokens per session scan A 21e611099368

Subscribe to this mod's changes

ffmpeg-render-pipeline is a skill published in the GitHub repository beeswaxpat/ffmpeg-render-pro (3 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 3,651 once invoked, about $0.0002 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 2026-08-31.

Creative and media ai-agents claude cli ffmpeg mcp mcp-server

ffmpeg-render-pipeline next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ffmpeg-render-pipelinebeeswaxpat/ffmpeg-render-pro	Skill	3	2mo ago	MIT	A	55	Claude Code
claude-real-videoHUANGCHIHHUNGLeo/claude-real-video	Skill	2.3k	21d ago	MIT	A	61	Claude Code
gate-controlOrkas-AI/Orkas-VideoStudio	Skill	349	9d ago	MIT	A	81	Claude Code, Codex
stage-editOrkas-AI/Orkas-VideoStudio	Skill	349	9d ago	MIT	A	62	Claude Code, Codex
video-perceptionjordanrendric/claude-video-vision	Skill	1.5k	1mo ago	MIT	A	51	Claude Code
orchestrationOrkas-AI/Orkas-VideoStudio	Skill	349	9d ago	MIT	A	99	Claude Code, Codex
stage-assembleOrkas-AI/Orkas-VideoStudio	Skill	349	9d ago	MIT	A	0	Claude Code, Codex

ffmpeg-render-pro: Skill for Claude Code