Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/onedro1d/dark-factory/df-video-intake)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/df-video-intake"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/df-video-intake/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/onedro1d/dark-factory/df-video-intake"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/df-video-intake.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 | $0.00114 | $0.01662 |
| Opus 5 | $0.00057 | $0.00831 |
| Sonnet 5 | $0.00023 | $0.00332 |
| Haiku 4.5 | $0.00011 | $0.00166 |
Grade A, and why
df-video-intake 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 10d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dark Factory — Video Intake
Overview
Claude cannot read video or audio natively (the Read tool handles images, PDFs, and
notebooks only). This skill decomposes a video into things Claude can read — a
timestamped transcript and sampled frames — then guides turning that into
Dark Factory requirements via df-product-owner and df-data-transform-lens.
Two phases: Intake (mechanical, a script) → Extract (judgment, you + the DF skills).
When to Use
- The user hands you a video/recording/demo/walkthrough and wants it summarized, documented, or turned into requirements.
- "Can you watch / process / consume / transcribe this video?"
- "Extract requirements from this demo recording for the dark factory build."
- A screen-recorded SME/customer walkthrough that should become a PO requirements package.
Prerequisites
ffmpeg(+ffprobe) —brew install ffmpeg(macOS) /apt install ffmpeg(Debian).whisper-cpp—brew install whisper-cpp(provides thewhisper-clibinary). The ggml model auto-downloads to~/.cache/whisper-cppon first run and is reused after.- On Apple Silicon whisper-cli uses Metal/GPU automatically (≈24 s for a 9-min clip).
If a tool is missing the script prints the exact install command and exits — install, then re-run.
Phase 1 — Intake (run the script)
One command does probe → audio → transcript → frames:
bash "${CLAUDE_PLUGIN_ROOT:-$HOME/.claude/skills/df-video-intake}/scripts/extract-video.sh" "<path/to/video.mp4>" [interval_seconds] [model]
interval_seconds(default 12) — one frame every N seconds. ~9 min → ~45 frames.model(default small.en) —base.en(faster, ~148 MB) ·small.en(best quality/speed) ·medium.en(slower, more accurate).
Output lands in <video-dir>/<video-basename>-extract/:
probe.txt, audio.wav, transcript.txt, transcript.srt (timestamped), frames/iv_NNNN.jpg.
Frame ↔ time: iv_NNNN.jpg ≈ (NNNN-1) × interval seconds in. This is the join key
back to the SRT.
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.
- 10d ago First seen · 114 lines · 114 tokens per session scan A 1b6433259730
df-video-intake is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 114 tokens to every session and 1,662 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 2026-09-01.
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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.