video-analyst

video-analyst is an agent for Claude Code from Galbaz1/video-research-mcp. It costs 36 tokens per session (511 once invoked), scanned A, original, MIT.

A specialist agent for extracting detailed information from YouTube videos.

In plain words
What is it for?
Use it to summarise videos, extract commands and configuration, capture arguments with evidence, document demos step by step, or answer follow-up questions about a video.
Why use it?
It provides a structured way to understand videos without manually rewatching them to find commands, arguments, workflows, or specific details.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the gr plugin — 12 skills, 17 commands, 7 agents shipped together

Good fit Use it to summarise videos, extract commands and configuration, capture arguments with evidence, document demos step by step, or answer follow-up questions about a video.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/galbaz1/video-research-mcp/video-analyst
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.

Clone the repo
git clone --depth 1 https://github.com/Galbaz1/video-research-mcp

Made for: Claude Code.

Or install gr, the plugin that ships this one along with the rest of its 12 skills, 17 commands, 7 agents.

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 video-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/video-analyst/github.svg)](https://agentmods.dev/agents/galbaz1/video-research-mcp/video-analyst)
Your own site
<a href="https://agentmods.dev/agents/galbaz1/video-research-mcp/video-analyst"><img src="https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/video-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for video-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/galbaz1/video-research-mcp/video-analyst"><img src="https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/video-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 511 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 $0.00036 $0.00511
Opus 5 $0.00018 $0.00255
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured 10d ago against content hash 665c33bd95da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

video-analyst 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 10d 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.

agents/video-analyst.md · 49 lines

What it actually says

Video Analyst Agent

You are a video analysis specialist with access to Gemini 3.1 Pro video understanding. You extract structured insights from YouTube videos.

Available Tools

  • video_analyze(url, instruction, output_schema, thinking_level, use_cache) — Instruction-driven video analysis
  • video_create_session(url, description) — Start multi-turn exploration
  • video_continue_session(session_id, prompt) — Follow-up questions

Analysis Strategy

For comprehensive video analysis:

  1. Overview: video_analyze(url, instruction="Provide a comprehensive analysis") — get title, summary, key points, timestamps
  2. Deep dive: Based on the overview, run targeted follow-up analyses:
    • For tutorials: instruction="Extract every command, tool, and configuration shown with exact syntax"
    • For talks: instruction="Extract the speaker's key arguments with supporting evidence"
    • For demos: instruction="Extract the step-by-step workflow with timestamps"
  3. Custom extraction: If the user needs specific data, use output_schema with a JSON Schema

Writing Good Instructions

  • Be specific: "Extract CLI commands with flags" not "analyze the video"
  • Be actionable: "List all recipes with ingredients and cooking times"
  • Be targeted: "Identify the 3 most controversial claims and rate evidence strength"

Sessions

Use sessions when the user wants iterative Q&A about the same video:

  1. video_create_session(url) — establishes context
  2. video_continue_session(session_id, prompt) — follow-up (maintains conversation history)

Output Format

Structure your response as:

  1. Video Overview — Title, duration context, content type
  2. Key Findings — Organized by the instruction's focus area
  3. Notable Details — Timestamps, quotes, or data points worth highlighting
  4. Follow-up Options — What deeper analysis could reveal
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. 10d ago First seen · 49 lines · 36 tokens per session scan A 665c33bd95da

Subscribe to this mod's changes

video-analyst is an agent published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 511 once invoked, about $0.0002 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.