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 magnus919/agent-skills --skill ffmpeggit clone --depth 1 https://github.com/magnus919/agent-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/magnus919/agent-skills/ffmpeg)<a href="https://agentmods.dev/skills/magnus919/agent-skills/ffmpeg"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/ffmpeg.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00116 | $0.01844 |
| Opus 5 | $0.00058 | $0.00922 |
| Sonnet 5 | $0.00023 | $0.00369 |
| Haiku 4.5 | $0.00012 | $0.00184 |
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 5d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FFmpeg Expert
Treat FFmpeg as a typed media pipeline and media editing as an evidence-driven workflow. Inspect the actual source, separate measurements from interpretations, make decisions reviewable, render to a new path, and verify at the intended boundary.
When Not to Use
- Do not use this skill for libav API programming, opaque whole-video semantic understanding, automatic publishing, rights clearance, DRM circumvention, professional broadcast/color certification, or HyperFrames-authored compositions.
- Route online media or transcript acquisition to the owning source skill, semantic frame interpretation to a vision-capable reviewer, and platform upload/API work to the platform skill.
Boundaries and Routing
- Use a YouTube/transcript capability to acquire online video or transcripts; return here only for local supplied media and transcript artifacts.
- Use HyperFrames for HTML-authored motion graphics or composition; use this skill to inspect and preprocess its media inputs or verify rendered outputs.
- Use the named platform skill for upload, publishing, account, or API operations.
- FFmpeg can extract bounded frames and audio segments but does not interpret their semantic content. Route visual interpretation to a vision-capable reviewer and preserve its observations as attributed evidence.
- Do not infer rights, consent, identity, intent, or whole-program meaning from technical metadata, sparse frames, silence intervals, or an unaligned transcript.
Evidence Classes
Label consequential claims so unlike evidence is not blended:
- Technical contract — behavior documented by an official FFmpeg or standards source.
- Observed artifact — probe output, measured signal result, extracted frame, listened segment, or downstream test from this source/output.
- Reproducible experiment — exact version, input identity/generator, command, result, and limits.
- Editorial heuristic — a reversible judgment that requires human review, not a fact established by FFmpeg.
- User requirement — the requested output contract, preservation policy, and acceptance threshold.
What ships with it
34 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.
- evals/evals.json 6.0 KB
- README.md 6.9 KB
- references/advanced-operations-and-safety.md 5.4 KB
- references/audio-and-podcast-editing.md 4.9 KB
- references/command-cookbook.md 1.9 KB
- references/core-model-and-command-anatomy.md 3.8 KB
- references/editorial-video-editing.md 4.9 KB
- references/ffmpeg-edit-decision-lists.md 4.6 KB
- references/filters-and-transformations.md 3.6 KB
- references/intermediate-workflows.md 6.1 KB
- references/learning-summary.md 3.4 KB
- references/local-verification.md 3.1 KB
- references/media-failure-modes.md 5.8 KB
- references/media-intake-and-manifest.md 4.6 KB
- references/media-research-source-index.md 5.0 KB
- references/media-verification-and-acceptance.md 4.6 KB
- references/source-inventory.md 6.2 KB
- references/video-inspection-and-visual-evidence.md 4.7 KB
- scripts/audio-inspect 1.7 KB
- scripts/extract-review-frames 11 KB
- scripts/ffmpeg-preflight 11 KB
- scripts/fixtures/ffmpeg-8.1.2-inventories.json 1.3 KB
- scripts/media-intake 8.1 KB
- scripts/media-verify 2.6 KB
- scripts/render-edl 1.9 KB
- scripts/test_ffmpeg_preflight.py 12 KB runs code
- scripts/test_media_workflows.py 5.9 KB runs code
- templates/edit-decision-list.json 695 B
- templates/media-acceptance-report.md 670 B
- templates/media-intake.json 856 B
- templates/podcast-edit-plan.md 598 B
- templates/research-experiment-record.md 433 B
- templates/video-inspection-report.md 806 B
- templates/visual-review-packet.md 480 B
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.
- 5d ago First seen · 108 lines · 116 tokens per session scan A e60f8354d96f
ffmpeg is a skill published in the GitHub repository magnus919/agent-skills (74 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 1,844 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
design
Professional design system - illustrations, UI mockups, social graphics, brochures, logos, infographics, and image editing. Routes to optimal pipeline (HTML Studio for layouts, Replicate AI for creative imagery, PPTX for presentations). Use when user asks to design, create visuals, generate graphics, make a mockup…
marp
Markdown-driven presentation pipeline producing PDF and HTML from MARP source with 31C branded theme. Four subcommands: new (prompt-to-deck), render (existing source), from (workspace markdown transform), watch (live preview). Internal decks, runbooks, state checks, knowledge renders. Do NOT use for editable PPTX…
image-prompt
Generate AI text-to-image prompts from written content. Use after creating any content (LinkedIn post, blog article, email, presentation copy, announcement) to produce a photorealistic image prompt for Midjourney, DALL-E, Stable Diffusion, or similar platforms. Trigger when the user asks for an image, visual…
music-video
Generate a 60-second 9:16 vertical music video (YouTube Shorts / TikTok / Reels format) from an operator-supplied music file plus mood keywords. Use when the user provides an audio file (mp3 / wav / m4a / aac) and wants a short-form vertical video with beat-aligned cuts, mood-matched Pexels B-roll, and optional…
info-short
A workflow for producing a sourced, narrated 60-second vertical explainer video from an evergreen topic. It passes the topic through research, production, legal review, and release steps.