A command that finds slide-like scene changes in a YouTube video, video URL, or local video file and saves the selected frames as PNG images. It can also use OCR, which reads text from images, to save text files beside them.

Use it to extract presentation slides, lecture screens, or other slide-shaped frames from videos. You can limit the number of images, choose an output folder, and optionally extract visible text.

It saves you from manually pausing a video and taking screenshots of each slide. It can use bundled tools when system video tools are unavailable, while warning you when a required tool is missing.

slides — Command by steipete

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.

agentmods

npx agentmods add commands/steipete/summarize/slides

Clone the repo

git clone --depth 1 https://github.com/steipete/summarize

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 924 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00000	$0.00924
Opus 5	$0.00000	$0.00462
Sonnet 5	$0.00000	$0.00185
Haiku 4.5	$0.00000	$0.00092

Measured 2d ago against content hash 7d29b807b23b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slides 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 2d 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.

docs/commands/slides.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

`summarize slides`

summarize slides <source> [flags]

Extracts slide-shaped keyframes from a YouTube URL, direct video URL, or local video file using FFmpeg scene detection. Native ffmpeg is preferred; bundled FFmpeg WebAssembly is used when native ffmpeg/ffprobe are unavailable. Output is a directory of PNGs (and optional OCR text). This is the standalone form of the --slides flag on the main command — useful when you only want the slides without a summary.

Synopsis

summarize slides "https://youtu.be/..."
summarize slides "https://youtu.be/..." --render auto
summarize slides "https://youtu.be/..." --slides-ocr -o ./out
summarize slides "https://example.com/lecture.mp4" --slides-max 12
summarize slides ./lecture.mp4 --slides-max 12

Requirements

Bundled FFmpeg WebAssembly, or native ffmpeg on PATH for faster extraction and broader codec support.
yt-dlp on PATH for YouTube URLs.
tesseract on PATH for --slides-ocr.

If a required tool is missing, summarize prints a clear warning and exits non-zero.

Flags

--slides-ocr : Run OCR on every extracted slide. Saves a .txt next to each PNG.

--slides-dir <dir> : Output base directory. Default: ./slides. A per-video subfolder is created inside.

-o, --output <dir> : Alias for --slides-dir.

--slides-scene-threshold <value> : Scene detection threshold, 0.1–1.0. Default 0.3. Lower values detect more scenes (more slides); higher values are stricter.

--slides-max <count> : Cap on extracted slides. Default 6.

--slides-min-duration <seconds> : Minimum gap between slides. Default 2.

--render <mode> : Inline render of thumbnails: auto, kitty, iterm, none. Default none — paths are printed instead.

--theme <name> : Pick a CLI theme.

--timeout <duration> : Cap the download + extraction. Default 2m.

--no-cache : Force re-download and re-extraction (bypasses both caches).

--json : JSON envelope on stdout. Disables inline rendering.

Read the full file on GitHub · 122 lines

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.

2d ago First seen · 122 lines · 0 tokens per session scan A 7d29b807b23b

Subscribe to this mod's changes

slides is a command published in the GitHub repository steipete/summarize (6,588 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 924 tokens. 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.

Creative and media ai cli summarize

slides

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

`summarize slides`

Synopsis

Requirements

Flags

What this file has done since we first saw it

Other commands, from other repositories

brand-generate

stt

audition-voices

search

love

speckit.tasks