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/nicepkg/ai-workflow/media-processingnpx skills add nicepkg/ai-workflow --skill media-processinggit clone --depth 1 https://github.com/nicepkg/ai-workflowWrote 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/nicepkg/ai-workflow/media-processing)<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/media-processing"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/media-processing.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 | $0.00202 | $0.02825 |
| Opus 5 | $0.00101 | $0.01412 |
| Sonnet 5 | $0.00040 | $0.00565 |
| Haiku 4.5 | $0.00020 | $0.00282 |
Grade B, and why
media-processing scanned grade B with 1 finding 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install ffmpeg imagemagick Copies of this mod
2 near-identical copies found in the catalogue:
- media-processing — 91% identical, 2 lines differ
- media-processing — 84% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Processing Skill
Process video, audio, and images using FFmpeg and ImageMagick command-line tools for conversion, optimization, streaming, and manipulation tasks.
When to Use This Skill
Use when:
- Converting media formats (video, audio, images)
- Encoding video with codecs (H.264, H.265, VP9, AV1)
- Processing images (resize, crop, effects, watermarks)
- Extracting audio from video
- Creating streaming manifests (HLS/DASH)
- Generating thumbnails and previews
- Batch processing media files
- Optimizing file sizes and quality
- Applying filters and effects
- Creating composite images or videos
Tool Selection Guide
FFmpeg: Video/Audio Processing
Use FFmpeg for:
- Video encoding, conversion, transcoding
- Audio extraction, conversion, mixing
- Live streaming (RTMP, HLS, DASH)
- Video filters (scale, crop, rotate, overlay)
- Hardware-accelerated encoding
- Media file inspection (ffprobe)
- Frame extraction, concatenation
- Codec selection and optimization
ImageMagick: Image Processing
Use ImageMagick for:
- Image format conversion (PNG, JPEG, WebP, GIF)
- Resizing, cropping, transformations
- Batch image processing (mogrify)
- Visual effects (blur, sharpen, sepia)
- Text overlays and watermarks
- Image composition and montages
- Color adjustments, filters
- Thumbnail generation
Decision Matrix
| Task | Tool | Why |
|---|---|---|
| Video encoding | FFmpeg | Native video codec support |
| Audio extraction | FFmpeg | Direct stream manipulation |
| Image resize | ImageMagick | Optimized for still images |
| Batch images | ImageMagick | mogrify for in-place edits |
| Video thumbnails | FFmpeg | Frame extraction built-in |
| GIF creation | FFmpeg or ImageMagick | FFmpeg for video source, ImageMagick for images |
| Streaming | FFmpeg | Live streaming protocols |
| Image effects | ImageMagick | Rich filter library |
Installation
macOS
brew install ffmpeg imagemagick
Ubuntu/Debian
sudo apt-get install ffmpeg imagemagick
What ships with it
14 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/ffmpeg-encoding.md 9.2 KB
- references/ffmpeg-filters.md 12 KB
- references/ffmpeg-streaming.md 9.3 KB
- references/format-compatibility.md 8.5 KB
- references/imagemagick-batch.md 12 KB
- references/imagemagick-editing.md 13 KB
- scripts/batch_resize.py 10.0 KB runs code
- scripts/media_convert.py 8.2 KB runs code
- scripts/requirements.txt 558 B
- scripts/tests/requirements.txt 32 B
- scripts/tests/test_batch_resize.py 11 KB runs code
- scripts/tests/test_media_convert.py 7.7 KB runs code
- scripts/tests/test_video_optimize.py 12 KB runs code
- scripts/video_optimize.py 13 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.
- yesterday First seen · 359 lines · 202 tokens per session scan B 047210fa8212
media-processing is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 202 tokens to every session and 2,825 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.