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 Aaryan-Kapoor/video-production-skill --skill video-productiongit clone --depth 1 https://github.com/Aaryan-Kapoor/video-production-skillWrote 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/aaryan-kapoor/video-production-skill/video-production)<a href="https://agentmods.dev/skills/aaryan-kapoor/video-production-skill/video-production"><img src="https://agentmods.dev/badge/skills/aaryan-kapoor/video-production-skill/video-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/aaryan-kapoor/video-production-skill/video-production"><img src="https://agentmods.dev/badge/skills/aaryan-kapoor/video-production-skill/video-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 | $0.00085 | $0.01766 |
| Opus 5 | $0.00043 | $0.00883 |
| Sonnet 5 | $0.00017 | $0.00353 |
| Haiku 4.5 | $0.00009 | $0.00177 |
Grade A, and why
video-production scanned grade A 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Then run the printed server command in the background, verify with `curl -I`, and send the URL. Host only the intended video file. How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Production
Core Rule
Treat a video request as a finished deliverable, not a plan. Research, script, produce, render, verify, archive, and deliver or host unless blocked by missing access, missing dependencies, or an explicit user constraint.
When the user gives broad creative freedom, preserve the "go all out" standard: polished visuals, clear narrative, source-grounded claims, animated diagrams/charts, narration, caveats, and a strong takeaway.
Compatibility
Requires Python 3.10+ and ffmpeg/ffprobe. Recommended optional tools: Manim, Kokoro or another TTS stack, poppler-utils, Pillow, and Tailscale for private hosting. Kokoro can be wired portably with KOKORO_PYTHON, KOKORO_TTS_DIR, KOKORO_VOICE, and KOKORO_LANG_CODE; do not hardcode user-specific install paths.
Workspace Contract
Use a durable workspace. By default the helper scripts use:
$VIDEO_PRODUCTION_ROOT if set, otherwise ~/video-productions/
├── jobs/<YYYY-MM-DD-HHMM-slug>/
│ ├── assets/ # durable source figures, crops, tables, screenshots
│ ├── audio/ # narration segments + final voiceover
│ ├── frames/ # QC preview frames
│ ├── src/ # Manim/Python scripts, storyboard, segments.json
│ ├── renders/ # intermediate renders
│ ├── exports/ # final videos for this job
│ ├── logs/
│ └── manifest.json
├── backups/<YYYY-MM-DD>/ # copy every finished video here
├── serve/<slug>/ # one-file hosting dirs
└── current -> jobs/latest
For OpenClaw, run scripts with {baseDir}. For other agents, resolve scripts/... relative to this skill folder.
Initialize every non-trivial video job:
python {baseDir}/scripts/init_video_job.py "Topic or title" --prompt "original user prompt" [--source URL_OR_PATH]
Archive every completed MP4:
python {baseDir}/scripts/archive_video.py path/to/final.mp4 --job "$VIDEO_PRODUCTION_ROOT/current"
Use /tmp/video-production-<slug>/ only for disposable intermediates. Keep durable sources, scripts, final renders, and QC frames in the job folder.
What ships with it
6 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.
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.
- 13d ago First seen · 149 lines · 85 tokens per session scan A 9e2428efb6f0
video-production is a skill published in the GitHub repository Aaryan-Kapoor/video-production-skill (15 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 1,766 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
narrator-ai-cli
A command-line client for creating AI-narrated movie and short-drama videos. It can guide a workflow from selecting source material, templates, music, and voices to writing narration and combining the video.
narrator-ai-cli
Create AI-narrated film/drama commentary videos via CLI. Two workflow paths (Original & Adapted narration), 93 movies, 146 BGM tracks, 63 dubbing voices in 11 languages, 90+ narration templates. Use when creating narration videos, film commentary, short drama dubbing, or video production.
remotion
Use when creating, rendering, and managing programmatic videos using Remotion (React-based video framework). Covers compositions, frame-driven animation, transitions, effects, captions, audio, voiceover, FFmpeg post-production, and professional SaaS-grade motion design.
video-editor
Use when professional video post-production using FFmpeg — color grading, audio design, kinetic typography, transitions, motion effects, captions, brand overlays, and platform-optimized export for promotional and marketing videos. Use when editing videos, adding captions, color grading, or creating promo content.
watch2
Use when analyzing a video URL or local video with transcript and selected frames.
mediakit-cli
A command-line tool for MediaKit that covers both local FFmpeg editing and cloud-based AI media processing. FFmpeg is a widely used tool for converting and editing audio and video from the command line.