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 godot-fun/godot-framework --skill video-merge-gpugit clone --depth 1 https://github.com/godot-fun/godot-frameworkWrote 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/godot-fun/godot-framework/video-merge-gpu)<a href="https://agentmods.dev/skills/godot-fun/godot-framework/video-merge-gpu"><img src="https://agentmods.dev/badge/skills/godot-fun/godot-framework/video-merge-gpu/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/godot-fun/godot-framework/video-merge-gpu"><img src="https://agentmods.dev/badge/skills/godot-fun/godot-framework/video-merge-gpu.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00144 | $0.01193 |
| Opus 5 | $0.00072 | $0.00596 |
| Sonnet 5 | $0.00029 | $0.00239 |
| Haiku 4.5 | $0.00014 | $0.00119 |
Grade A, and why
video-merge-gpu 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 9d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Merge GPU
Same merge as video-merge: concatenate every video in a folder (filename sort) into one high-quality MP4, random FFmpeg xfade (0.5s) + matching acrossfade, freeze-pad so output length equals the sum of source durations.
GPU encode only. Probe hevc_nvenc �?hevc_amf �?hevc_qsv (HEVC Main10). If none work, fail �?do not fall back to libx265. Use video-merge when CPU encode is wanted.
xfade / scale / pad still run on CPU; only the H.265 encode is hardware.
Rules
When this skill applies, read and follow skill-dependency-manager �?run scripts as documented, install missing tools into .dependency/.
- Run
merge.pythrough.dependency/python/python.exe. Never use hostpython/ffmpeg. - Never overwrite sources. Outputs go under
video-merge-gpu/. - Use the bundled script �?do not hand-write equivalent FFmpeg commands.
- Folder input only �?pass
--folderwith a directory of clips (top-level files; no recurse).
Quick Start
.dependency/python/python .ai/video-merge-gpu/merge.py --folder path/to/clips
Example:
assets/shots/
01.mp4
02.mp4
03.mp4
�?assets/shots/video-merge-gpu/shots.mp4
Output Spec (fixed)
| Setting | Value |
|---|---|
| Resolution | 3840×2160 (scale + letterbox pad) |
| Frame rate | 60 fps |
| Video | H.265 Main10 (GPU: hevc_nvenc / hevc_amf / hevc_qsv, p010le) @ 40 Mbps |
| Audio | AAC 320 kbps, 48 kHz stereo |
| Transition | 0.5 s, random from the pool below (freeze-pad; duration preserved) |
| Container | .mp4 (hvc1 tag) |
Transition Pool (random per cut)
fade · dissolve · wipeleft · wiperight · wipeup · wipedown · slideleft · slideright · circlecrop · pixelize · distance · radial · smoothleft · smoothright · circleopen · circleclose · diagtl · diagtr · hblur · zoomin
Each cut independently samples one transition. Printed in the run log.
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.
- 9d ago First seen · 94 lines · 144 tokens per session scan A 74e55a95a642
video-merge-gpu is a skill published in the GitHub repository godot-fun/godot-framework (116 stars, last pushed 9d ago), licensed MIT. It adds 144 tokens to every session and 1,193 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
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…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.