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 Galbaz1/video-research-mcp --skill ffmpeg-productiongit clone --depth 1 https://github.com/Galbaz1/video-research-mcpWrote 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/galbaz1/video-research-mcp/ffmpeg-production)<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/ffmpeg-production"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/ffmpeg-production/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.
<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/ffmpeg-production"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/ffmpeg-production.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.02605 |
| Opus 5.5 | $0.00017 | $0.01042 |
| Sonnet 5.5 | $0.00008 | $0.00521 |
| Haiku 4.5 | $0.00004 | $0.00261 |
Grade A, and why
ffmpeg-production 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 20d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FFmpeg Production
FFmpeg recipes for video post-production. Covers the operations you reach for daily: format conversion, scaling, trimming, concatenation, compression, and AI video post-processing.
For platform-specific export presets (YouTube, TikTok, Instagram, Twitter), see references/platform-presets.md.
Post-Processing Filter Order
Use this order when these filters are needed. Compare against the original; unnecessary processing can remove detail or introduce artifacts.
[1] Temporal denoise — remove inter-frame shimmer before any processing
[2] Scale — scale before sharpening avoids halos
[3] Sharpen — recover edge detail lost in generation/upscale
[4] Color grade (LUT) — normalize over-saturated AI palette
[5] Curves/EQ — fine-tune contrast and shadow lift
[6] Film grain — LAST before encode; grain before denoising destroys it
[7] Encode — libx265 -tune grain or AV1 FGS
Denoising can remove added grain, and interpolation can distort it. Add grain after those operations.
Full chain as a single filtergraph:
ffmpeg -i input.mp4 \
-vf "hqdn3d=2:2:3:3,\
scale=1920:1080:flags=lanczos,\
unsharp=5:5:0.8:5:5:0.4,\
lut3d=grade.cube,\
curves=r='0/0 0.5/0.52 1/1':b='0/0.03 1/0.97',\
noise=alls=6:allf=t+u" \
-c:v libx265 -crf 18 -preset slow -tune grain \
-c:a copy output.mp4
Hald CLUT Color Grading
For iterative grading, export a Hald CLUT, edit it in Photoshop/GIMP, and re-import. LUT edits leave the source untouched; rendering the graded video still encodes it.
ffmpeg -i input.mp4 -i hald_clut_graded.png \
-filter_complex "[0:v][1:v] haldclut" \
-c:v libx265 -crf 18 output.mp4
Format Conversion
Codec Selection
| Target | Codec | When to use |
|---|---|---|
| Web/streaming | libx264 | Universal compatibility |
| Compact retained copy | libx265 | Compare quality/size for the actual material; CRF encoding is lossy |
| Modern distribution | libsvtav1 | Compare compression, encode time, and target-player support |
| Browser embed | libvpx-vp9 | WebM container, good compression |
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.
- 20d ago Changed a92451375055
- 1mo ago First seen · 241 lines · 42 tokens per session scan A 8e9d3e1adf32
ffmpeg-production is a skill published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 2,605 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 2026-08-30.
Other skills, from other repositories
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
b123d-edit
Use this skill when the task is to change an existing build123d model or script: "make this bracket 5 mm taller", "move the holes inward", "add a counterbore", "remove this rib", "make it fit this mating part", or "repair the code so the intended edit remains parametric".
browser-forms
Fill a whole web form, post a comment or reply, or read a long thread in Safari or Chrome with the fewest Mac MCP browser calls.
local-delegation
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…
tool-description-check
Self-check a new or edited MCP tool description/field .describe() text before committing — verify every behavioral claim against live testing or source, check for contradictions with sibling tools, and score against Glama's Tool Definition Quality Score (TDQS) rubric. Use whenever a tool description or schema field…
workflows
Knowledge about ComfyUI workflow API format, node connections, and common patterns. Use when helping users build, modify, or understand workflows.