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 andrewii23/ii23-skills --skill video-understandgit clone --depth 1 https://github.com/andrewii23/ii23-skillsWrote 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/andrewii23/ii23-skills/video-understand)<a href="https://agentmods.dev/skills/andrewii23/ii23-skills/video-understand"><img src="https://agentmods.dev/badge/skills/andrewii23/ii23-skills/video-understand/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/andrewii23/ii23-skills/video-understand"><img src="https://agentmods.dev/badge/skills/andrewii23/ii23-skills/video-understand.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 | $0.00265 | $0.04171 |
| Opus 5.5 | $0.00106 | $0.01668 |
| Sonnet 5.5 | $0.00053 | $0.00834 |
| Haiku 4.5 | $0.00026 | $0.00417 |
Grade C, and why
video-understand scanned grade C 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
Clean up the work dir with `rm -rf` when the user is unlikely to follow up. How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Understand
Read a video the way a person does: see every shot, hear the words, notice what moves and what goes quiet, tie it all to the clock. Three scripts produce that; you do the understanding.
scripts/index.py— one cheap pass: every shot (with its motion, light and sharpest moment), loudness hits, silences, and with--ocrthe on-screen text over time. Text you can read and grep.scripts/frames.py— one frame per shot (never skips a shot), extra frames through long takes, packed into timestamp-labelled grid images.scripts/transcript.py— a timestamped transcript (ElevenLabs by default).
The transcript is required whenever there is speech. A grid shows what is on
screen and never what was said. On a 24-minute episode the grid alone gives the
arc (someone is accused, a gadget appears, a shadow chases them) while every
fact that matters — what was stolen, the gadget's name and rule, how it
resolves — lives entirely in the audio. Skipping the transcript produces
confident, plausible, wrong summaries. Skip it only when the video has no
speech, or the user explicitly asks for visuals only. When there is no speech,
index.py --ocr is what carries the words instead: captions, signs, title cards.
Resolve SKILL_DIR first
Every command below runs a script under SKILL_DIR/scripts/. Set SKILL_DIR to
the absolute path of the directory holding THIS SKILL.md (your harness reported
it when you read this file). Scripts are always a direct sibling of this file.
On Windows substitute python for python3.
For a URL, download it first (yt-dlp -f 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best' -o video.mp4 "<url>")
and pass the local file.
Pick the recipe by the job
| Job | Run |
|---|---|
| Short clip (under ~5 min): what happens, explain it | transcript (background) + index.py --ocr + frames.py --index |
| Film with burned-in subtitles | index.py --ocr --ocr-lang <lang> IS the transcript; skip the paid one |
| Silent / no-speech: sight gags, room tours, b-roll | index.py --ocr + frames.py --index; transcript only if there is speech |
| Long video / film: recap, spoiler, pick scenes | transcript (background) + index.py + frames.py --index, read every grid; then zoom |
| One moment ("what happens at 1:02:10") | frames.py --start --end --cells 16 over that window |
| Choosing footage from many clips | cull.py --text — one ranked table + one contact sheet |
| Which clips have burned-in text | text_check.py |
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.
- 1mo ago Changed · +118 lines · +74 tokens per session f8694c4128af
- 2mo ago First seen · 177 lines · 191 tokens per session scan C c012949459a6
video-understand is a skill published in the GitHub repository andrewii23/ii23-skills (11 stars, last pushed 3d ago), licensed MIT. It adds 265 tokens to every session and 4,171 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
video-understand compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| video-understandandrewii23/ii23-skills | Skill | 11 | 3d ago | MIT | C | 265 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |