Borrowing it
Nothing to install: this file belongs to traikdude/enhanced-multimedia-analysis-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/traikdude/enhanced-multimedia-analysis-mcp/master/.claude/commands/aiv.mdgit clone --depth 1 https://github.com/traikdude/enhanced-multimedia-analysis-mcpWrote 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/commands/traikdude/enhanced-multimedia-analysis-mcp/aiv)<a href="https://agentmods.dev/commands/traikdude/enhanced-multimedia-analysis-mcp/aiv"><img src="https://agentmods.dev/badge/commands/traikdude/enhanced-multimedia-analysis-mcp/aiv.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00683 |
| Opus 5 | $0.00006 | $0.00342 |
| Sonnet 5 | $0.00002 | $0.00137 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
aiv 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 7d 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.
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.
🎬 Enhanced Multimedia Analysis Activated
You are now operating in Enhanced Multimedia Analysis Mode using the MCP video analysis tools.
Your Task
Analyze the user's visual content description and generate a professional AI video/image generation prompt using the systematic hotkey-based analysis framework.
Process
-
Parse the user's input and extract:
- Core visual description
- Any options provided (depth, platform, focus, format, hotkeys, style)
-
Determine content type:
- Image description → use
video_analysis_analyze_image - Video description → use
video_analysis_analyze_video - Both image and video → use
video_analysis_analyze_multimedia
- Image description → use
-
Extract options from input:
--depth [quick|standard|deep|comprehensive](default: standard)--platform [TikTok|Instagram|YouTube|Cinema]--focus [comma-separated areas]--format [markdown|json](default: markdown)--hotkeys [comma-separated list]--style "reference style"
-
Call the appropriate MCP tool with parameters:
{ "content_description": "[extracted description]", "analysis_depth": "[extracted or default]", "target_platform": "[if specified]", "focus_areas": "[if specified]", "hotkeys": "[if specified]", "reference_style": "[if specified]", "response_format": "[extracted or default]" } -
Return the optimized prompt directly to the user
Option Parsing Examples
Input: /aiv sunset over mountains --depth quick
- description: "sunset over mountains"
- depth: "quick"
Input: /aiv product video --platform Instagram --focus camera movement, color grading
- description: "product video"
- platform: "Instagram"
- focus_areas: ["camera movement", "color grading"]
Input: /aiv character scene --hotkeys K1,K2,C1 --format json
- description: "character scene"
- hotkeys: ["K1", "K2", "C1"]
- format: "json"
Default Behavior
If no options specified:
- Use
analysis_depth: "standard" - Use
response_format: "markdown" - Let the MCP determine appropriate hotkeys
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.
- 7d ago First seen · 99 lines · 12 tokens per session scan A 9512fb6a6a7c
aiv is a command published in the GitHub repository traikdude/enhanced-multimedia-analysis-mcp (0 stars, last pushed 10mo ago), licensed MIT. It adds 12 tokens to every session and 683 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 2026-08-31.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.
transcribe
Transcribe the file at $ARGUMENTS into Markdown using the Frenchie MCP server.
varyshop-carousel
Create a Varyshop multi-slide carousel (LIGHT style, hook → CTA).
imperium:create-video
Create startup video content. Supports pitch videos, product demos, social clips, investor updates, and hiring videos. Bridges to Remotion for rendering.