What is video-deep-understanding?

A video-analysis tool that combines spoken words from a transcript with selected video frames. It can work from an online video link or a local video file.

Use it to summarize or transcribe videos, find moments by topic, inspect interfaces, answer timestamped questions, or compare a video with local code and documents.

It helps answer questions about both what is said and what appears on screen, instead of relying on only audio or only images.

video-deep-understanding — Skill for Claude Code by valtterimelkko

Install

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.

Any agent

npx skills add valtterimelkko/agent-workflow-skills --skill video-deep-understanding

Clone the repo

git clone --depth 1 https://github.com/valtterimelkko/agent-workflow-skills

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/video-deep-understanding/github.svg)](https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/video-deep-understanding)

Your own site

<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/video-deep-understanding"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/video-deep-understanding/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/valtterimelkko/agent-workflow-skills/video-deep-understanding"><img src="https://agentmods.dev/badge/skills/valtterimelkko/agent-workflow-skills/video-deep-understanding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,269 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00099	$0.01269
Opus 5	$0.00049	$0.00634
Sonnet 5	$0.00020	$0.00254
Haiku 4.5	$0.00010	$0.00127

Measured 11d ago against content hash 9057467ff6df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

video-deep-understanding 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 11d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/download.py, scripts/frames.py, scripts/setup.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/video-deep-understanding/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Deep Understanding

This skill gives the agent a video input. It can:

download a remote video or use a local file
pull native captions when available
fall back to OpenAI transcription when needed
extract frames for visual inspection
search the transcript for named concepts before burning image tokens
reuse a cached local copy of a previously downloaded URL on follow-up runs

Progressive disclosure

Read these only when needed:

references/quickstart.md — default workflow and key flags
references/troubleshooting.md — sharp edges, failure interpretation, and when to inspect scripts

Do not read bundled scripts by default. Inspect them only if setup/download/transcription fails repeatedly, output looks suspicious, or the user asks about internals.

Step 0 — silent preflight

On macOS/Linux use python3. On Windows use python instead.

Run:

python3 scripts/setup.py --check

If it exits 0, say nothing and continue.

If it exits non-zero:

2 → missing binaries; run python3 scripts/setup.py
3 → missing OpenAI key; run installer and ask the user for the key if they want transcription fallback
4 → both missing; run installer, then ask for the key if needed

If you need more detail, use:

python3 scripts/setup.py --json

Useful fields include:

status
missing_binaries
has_api_key
has_proxy
js_runtimes
cookies_available

Default invocation rule

For long videos, UI demos, or concept-finding tasks, prefer a transcript-first pass:

python3 scripts/watch.py "$URL" --transcript-only --find 'keyword|other keyword'

Then zoom into the relevant section:

python3 scripts/watch.py "$URL" --start 4:32 --end 5:16 --resolution 1024 --contact-sheet

For short videos where the user wants a broad summary, a direct full scan is fine:

python3 scripts/watch.py "$URL"

If you already watched the same video in this session and still have the relevant transcript/frames in context, answer directly instead of re-running.

Read the full file on GitHub · 158 lines

Files

What ships with it

13 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.

Changes

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.

11d ago First seen · 158 lines · 99 tokens per session scan A 9057467ff6df

Subscribe to this mod's changes

video-deep-understanding is a skill published in the GitHub repository valtterimelkko/agent-workflow-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 1,269 once invoked, about $0.0005 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 2026-08-31.

Creative and media

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.

nexu-io/open-design · 41 tokens

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…

heygen-com/hyperframes · 92 tokens

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.

nexu-io/open-design · 53 tokens

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).

nexu-io/open-design · 78 tokens

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.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens