media-extract-frames

media-extract-frames is a command for coding agents from bybren-llc/safe-agentic-workflow. It costs 18 tokens per session (600 once invoked), scanned A, original, MIT.

A video command that selects visually important moments and describes them as storyboard entries. A storyboard is a sequence of visual notes used to plan or review an edit.

In plain words
What is it for?
Use it to prepare a storyboard from key frames, choose moments around scene changes or actions, and export prose or JSON descriptions.
Why use it?
It helps locate the moments worth reviewing without scanning the video at fixed time intervals.

Command

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/bybren-llc/safe-agentic-workflow/media-extract-frames
Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

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.

agentmods badge for media-extract-frames

README.md
[![agentmods](https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/media-extract-frames.svg)](https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/media-extract-frames)
Your own site
<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/media-extract-frames"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/media-extract-frames.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 600 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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.00600
Opus 5 $0.00009 $0.00300
Sonnet 5 $0.00004 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured yesterday against content hash 9de3f19deb2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

media-extract-frames 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 yesterday.

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/knowledge-vault/commands/media-extract-frames.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/media:extract-frames

Read the name carefully before reaching for this one. It extracts no images. It finds the moments that matter in a video and writes them up as a storyboard, for edit decision support.

Overview

Gemini-only. Selects key frames on visual significance rather than fixed intervals, then describes each in text. NAMING DRIFT: nothing is written to disk — there is no ffmpeg call, no image write and no output path anywhere in the source, so "extract" means "describe" here. If you need scene boundaries instead, use /media:scene-detect.

Invocation

  • /media:extract-frames <path> — default --storyboard.
  • --detailed or --json — prose or machine-readable variants.
  • --max N — caps the frame count; the default is 20 key frames.
  • Preconditions: Gemini 3+ for video; MP4, MOV, AVI, MKV or WEBM; up to 100MB.

What It Does

  • Verifies the target with a pre-executed !{file {{args}} 2>/dev/null || echo "File not found"} — the stderr redirect is what makes the echo branch the observable failure path.
  • Identifies key frames on five signals: scene changes, significant moments (key actions, reactions, events), composition shifts, text appearances (title cards, lower thirds, captions), and subject changes.
  • Per frame, records a precise timestamp, a detailed visual description, subjects and objects, composition and framing notes, and narrative relevance.
  • Renders either the markdown Key Frame Report or the Storyboard table with columns for number, timestamp, visual, action, and audio or dialogue.
  • Sends video contents to the Gemini API — stated as an explicit privacy note.

Provider Parity

  • Gemini — the only implementation. No .claude/commands counterpart, so zero Claude parity.
  • Frame selection is significance-based and the source states the count varies by content complexity, so two runs over the same input are not guaranteed to agree.

Citations

Read the full file on GitHub · 57 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.

  1. yesterday First seen · 57 lines · 18 tokens per session scan A 9de3f19deb2f

Subscribe to this mod's changes

media-extract-frames is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 600 once invoked, about $0.0001 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 2026-09-03.