video-frames

A video utility built around ffmpeg, a command-line program for processing video and audio files. It extracts individual pictures from videos or creates quick thumbnails for inspection.

In plain words
What is it for?
It helps inspect a video’s first frame, capture a frame at a specific time or frame number, and make still images for sharing or review.
Why use it?
It avoids manually searching through a video when you need to see one moment or check what a clip contains.

Skill for Claude CodeCodex

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 skills/the-open-agent/openagent/video-frames
Any agent
npx skills add the-open-agent/openagent --skill video-frames
Clone the repo
git clone --depth 1 https://github.com/the-open-agent/openagent

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 307 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 $0.00015 $0.00307
Opus 5 $0.00008 $0.00153
Sonnet 5 $0.00003 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 3d ago against content hash cec8c93a6f8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

video-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 3d 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.

skills/video-frames/SKILL.md · 53 lines

What it actually says

Video Frames (ffmpeg)

Extract a single frame from a video, or create quick thumbnails for inspection.

Quick start

First frame:

ffmpeg -hide_banner -loglevel error -y \
  -i /path/to/video.mp4 \
  -vf "select=eq(n\,0)" \
  -vframes 1 \
  /tmp/frame.jpg

At a timestamp:

ffmpeg -hide_banner -loglevel error -y \
  -ss 00:00:10 \
  -i /path/to/video.mp4 \
  -frames:v 1 \
  /tmp/frame-10s.jpg

By frame index:

ffmpeg -hide_banner -loglevel error -y \
  -i /path/to/video.mp4 \
  -vf "select=eq(n\,42)" \
  -vframes 1 \
  /tmp/frame42.jpg

Notes

  • Prefer -ss + timestamp for "what is happening around here?".
  • Use .jpg for quick sharing; use .png for crisp UI frames.
  • Use -hide_banner -loglevel error to suppress verbose ffmpeg output.
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. 3d ago First seen · 53 lines · 15 tokens per session scan A cec8c93a6f8f

Subscribe to this mod's changes

video-frames is a skill published in the GitHub repository the-open-agent/openagent (5,596 stars, last pushed yesterday), licensed Apache-2.0. It adds 15 tokens to every session and 307 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 2026-08-30.