safe-agentic-workflow: Command for Gemini CLI

.gemini/commands/media/analyze-video.toml

analyze-video is a command for Gemini CLI from bybren-llc/safe-agentic-workflow. It costs 0 tokens per session (624 once invoked), scanned A, original, MIT.

A video-analysis command that breaks a video into scenes and describes the setting, people, objects, actions, dialogue, text, and visual style in each one.

In plain words
What is it for?
Use it to create reports about locations, subjects, camera movement, lighting, colors, spoken words, and on-screen text.
Why use it?
It provides a scene-by-scene record of a video without requiring you to watch and document it manually.

Command for Gemini CLI

Written for Gemini CLI: installed under .gemini/.

This is bybren-llc/safe-agentic-workflow's own configuration. It tells Gemini CLI how to work on safe-agentic-workflow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything safe-agentic-workflow configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bybren-llc/safe-agentic-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/bybren-llc/safe-agentic-workflow/main/.gemini/commands/media/analyze-video.toml
Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

Made for: Gemini CLI.

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 analyze-video

README.md
[![agentmods](https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/analyze-video.svg)](https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/analyze-video)
Your own site
<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/analyze-video"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/analyze-video.svg" alt="Measured on agentmods" height="20"></a>
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 624 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00624
Opus 5 $0.00000 $0.00312
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00062

Measured 3d ago against content hash dd2951f9300d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

analyze-video 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.gemini/commands/media/analyze-video.toml · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

description = "Analyze video content scene by scene"

prompt = """

Analyze Video Command

Analyze video content scene by scene using Gemini's multimodal video capabilities.

Target: {{args}}

Supported Formats

MP4, MOV, AVI, MKV, WEBM

Workflow

1. Detect Video File

Verify the target video file exists and identify its format:

!{file {{args}} 2>/dev/null || echo "File not found"}

2. Analyze Scenes

Process the video through Gemini's multimodal input:

  • Identify distinct scenes and transitions
  • Describe visual content in each scene
  • Detect objects, people, actions, and settings
  • Note camera movements and composition
  • Transcribe any dialogue or on-screen text

3. Describe Content

For each scene, capture:

  • Setting: Location, time of day, environment
  • Subjects: People, objects, animals present
  • Actions: What is happening in the scene
  • Dialogue: Any spoken words or on-screen text
  • Visual Style: Lighting, color palette, camera angle

4. Generate Report

## Video Analysis Report

### File Info
- **File**: [filename]
- **Format**: [detected format]
- **Duration**: [estimated duration]
- **Total Scenes**: [count]

### Scene Breakdown

#### Scene 1 (00:00:00 - 00:00:15)
- **Setting**: [description]
- **Subjects**: [people, objects]
- **Actions**: [what happens]
- **Dialogue**: [spoken words]
- **Visual Style**: [lighting, camera, color]
- **Transition**: [cut/fade/dissolve to next]

#### Scene 2 (00:00:15 - 00:00:42)
...

### Summary
[Overall video description and narrative arc]

### Visual Style Notes
- **Dominant Colors**: [color palette]
- **Camera Work**: [static, handheld, tracking, etc.]
- **Editing Pace**: [fast, moderate, slow]

Output Options

  • --summary - Brief overview with scene count (default)
  • --detailed - Full scene-by-scene breakdown
  • --json - Structured JSON output
  • --timestamps - Scene list with timestamps only

Usage Examples

/media:analyze-video ./presentation.mp4
/media:analyze-video ~/footage/interview.mov --detailed
/media:analyze-video ./tutorial.webm --json
/media:analyze-video ./clip.mkv --timestamps

Read the full file on GitHub · 99 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. 3d ago First seen · 99 lines · 0 tokens per session scan A dd2951f9300d

Subscribe to this mod's changes

analyze-video is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 624 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 2026-09-03.