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/iofold/ainative-claude-plugins/ffmpeg-gemininpx skills add iofold/ainative-claude-plugins --skill ffmpeg-geminigit clone --depth 1 https://github.com/iofold/ainative-claude-pluginsWrote 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/iofold/ainative-claude-plugins/ffmpeg-gemini)<a href="https://agentmods.dev/skills/iofold/ainative-claude-plugins/ffmpeg-gemini"><img src="https://agentmods.dev/badge/skills/iofold/ainative-claude-plugins/ffmpeg-gemini.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 | $0.00076 | $0.01765 |
| Opus 5 | $0.00038 | $0.00882 |
| Sonnet 5 | $0.00015 | $0.00353 |
| Haiku 4.5 | $0.00008 | $0.00177 |
Grade A, and why
ffmpeg-gemini 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FFmpeg + Gemini Video Workflows
Recipes for splitting, extracting, analyzing, and assembling video with FFmpeg and Google Gemini.
Supporting files (read the one matching your task before starting):
references/verified-analysis-pipeline.md— the trust-nothing analysis methodology: proving effective fps via token accounting, two-pass video+audio analysis (video passes mishear speech!), the snip-verify loop for frame-accurate cuts, AI-audit scoping rubric, operational pitfalls table.references/montage-editing.md— conform treatments (cover-crop vs blur-pad), xstack grid walls, zoompan pans/zooms, letterbox removal, loudness normalization, concat assembly, pre-ship QC rubric.references/prompt-templates.md— proven prompts: per-clip inventory, cross-clip mapping, timestamped transcripts, word disambiguation, phrase boundaries, snip verification, structural + technical-only audits.scripts/— runnable Bun scripts:analyze-video.ts(single video @ explicit fps, retries, USAGE logging),analyze-multi.ts(N labeled videos, one request),gemini-audio.ts(prompt over audio files),verify-snips.ts(batch ground-truth of cut boundaries). Runbun installinscripts/once first — Bun inline-versioned imports corrupt their cache under parallel first runs.
1. Split Long Videos into Segments
# Lossless split (fast, no re-encode)
ffmpeg -ss 00:10:00 -i input.mp4 -t 00:10:00 -c copy -avoid_negative_ts make_zero segment.mp4
# Auto-split into 10-min chunks
ffmpeg -i input.mp4 -c copy -map 0 -segment_time 600 -f segment -reset_timestamps 1 segment_%03d.mp4
# Optimize for Gemini (downscale to 720p)
ffmpeg -i input.mp4 -vf scale=-2:720 -c:v libx264 -crf 23 -c:a aac -b:a 128k optimized.mp4
Key: -ss before -i = fast keyframe seek; after = frame-accurate decode. With re-encode output, -ss before -i IS frame-accurate. -c copy = no re-encode.
2. Extract Screenshots
# Single frame
ffmpeg -ss 01:23:45 -i input.mp4 -frames:v 1 frame.png # PNG (best quality)
ffmpeg -ss 01:23:45 -i input.mp4 -frames:v 1 -q:v 2 frame.jpg # JPEG (smaller)
# One frame every 30 seconds
ffmpeg -i input.mp4 -vf "fps=1/30" -q:v 2 frames/frame_%04d.jpg
What ships with it
9 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.
- references/montage-editing.md 4.5 KB
- references/prompt-templates.md 5.4 KB
- references/verified-analysis-pipeline.md 5.7 KB
- scripts/analyze-multi.ts 2.7 KB runs code
- scripts/analyze-video.ts 3.1 KB runs code
- scripts/bun.lock 8.2 KB
- scripts/gemini-audio.ts 1.3 KB runs code
- scripts/package.json 165 B
- scripts/verify-snips.ts 1.7 KB runs code
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 First seen · 105 lines · 76 tokens per session scan A 75f88445bace
ffmpeg-gemini is a skill published in the GitHub repository iofold/ainative-claude-plugins (3 stars, last pushed 16d ago), licensed MIT. It adds 76 tokens to every session and 1,765 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-cut
剪辑中文口播原素材：逐词转录、词典修字出修字表、五轮扫描找口误与重复、汇总表与重复句子表、打开 Studio 让用户复核、复盘沉淀用户偏好与词典。只产出一份已复核的删词账本，不切媒体、不做字幕、不做分镜动画。用户说剪口播、处理口误、生成口播基础素材、继续剪口播，或确认卡回传 action=returncutreview 时使用。不要用于执行物理剪切、导出剪后视频、单独安装、单独打开工作台或口播分镜成片。.
chengfeng-check-updates
剪辑环境的唯一管理者：就绪检查（skills 是否最新 → Runtime 是否配套）、Skills 更新激活、Runtime 安装与体检。用户说检查更新、安装剪辑环境、装播放器、检查剪辑环境、剪辑环境就绪了吗、配置转录凭证时使用；业务 Skill（剪口播/字幕/画面/导出）第 0 步也引用本 Skill 的就绪检查。不用于剪辑、字幕、画面、导出本身或项目数据迁移。.
infographic-template-updater
Update template catalogs and UI prompts after adding new infographic templates (src/templates/.ts), including SKILL.md template list, site gallery template mappings, and the AIPlayground prompt list.
moq
Build live video, audio, and real-time data apps with Media over QUIC (MoQ). Use when adding live streaming, conferencing, voice AI, or real-time pub/sub to an app; when integrating the @moq/ npm packages, moq- Rust crates, or the Python/Kotlin/Swift/Go/C bindings; or when running a moq-relay server or a gateway…