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 thewolffish/wolffish-app --skill ffmpeggit clone --depth 1 https://github.com/thewolffish/wolffish-appWrote 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/thewolffish/wolffish-app/ffmpeg)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/ffmpeg"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/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 | $0.00011 | $0.01138 |
| Opus 5 | $0.00005 | $0.00569 |
| Sonnet 5 | $0.00002 | $0.00228 |
| Haiku 4.5 | $0.00001 | $0.00114 |
Grade A, and why
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.
What it actually says
FFmpeg
Usage
Use ffmpeg_check to verify ffmpeg is installed before running commands.
If not installed, call ffmpeg_install (requires user approval).
ffmpeg_install is managed-first and needs no admin rights: it reuses a global
ffmpeg if present, otherwise downloads a static build into ~/.wolffish/bin/ffmpeg
— no package manager, no password. Don't fall back to ad-hoc shell downloads —
just call ffmpeg_install. ffmpeg_check and ffmpeg_run resolve that managed
copy directly, so a freshly installed ffmpeg works immediately without an app
restart.
The managed install provides ffmpeg only. If you need ffprobe (e.g. to read
video metadata) or a globally-visible ffmpeg, call ffmpeg_install_system, which
installs both via the OS package manager (admin on Linux) and falls back to the
no-root copy if that's unavailable.
Use ffmpeg_run with the arguments you'd pass after ffmpeg on the command line.
Output files
Save all output files in the workspace files/ directory — the same parent directory where uploads/ lives, but use files/ instead. For example if the input is at …/uploads/conv-…/video.mp4, save output to …/files/output.mp3. Never use /tmp/ or any path outside the workspace.
Common patterns
- Compress video:
-i input.mp4 -crf 28 -preset medium output.mp4 - Extract audio:
-i input.mp4 -vn -acodec copy output.aac - Convert format:
-i input.avi -c:v libx264 -c:a output.mp4 - Resize video:
-i input.mp4 -vf scale=1280:720 output.mp4 - Get info:
-i input.mp4(prints metadata to stderr)
What ships with it
1 file 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.
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 · 158 lines · 11 tokens per session scan A 3554693e0c63
ffmpeg is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,138 once invoked, about $0.0001 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
make-viral-video
Build a short news-explainer video tuned for shareability. One striking moment per video; real fetched assets; self-heal validation; pluggable TTS (Gemini-free default, OpenAI fallback).
gemini-tts
Render text to mp3 via Google Gemini Flash TTS. Free-tier eligible (1500 req/day). Use for video narration, demo voiceovers, audio notes. Parallels openai-tts; default for make-viral-video.
image-generation
Generate and edit images using Gemini Flash Image, and generate videos using Veo. Supports text-to-image, image editing, text-to-video, and image-to-video.
audio-transcribe
Transcribes audio files and voice notes to text via Gemini 2.5-flash. Integrates with Slack, Discord, and Telegram bridges so voice clips surface as readable text in tasks.
screen-record
Start or stop a screen recording of the Mac via ffmpeg. Use when the user asks to record/capture their screen to a video file (a demo, a repro, a walkthrough) — not for a single still screenshot (use macos-tools screen capture for that).
openai-tts
Render text to mp3 via OpenAI's tts-1-hd. Use for video narration, demo voiceovers, audio notes.