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.
git clone --depth 1 https://github.com/Galbaz1/video-research-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/agents/galbaz1/video-research-mcp/video-analyst)<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.
<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>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 | $0.00036 | $0.00571 |
| Opus 5.5 | $0.00014 | $0.00228 |
| Sonnet 5.5 | $0.00007 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
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 27d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Analyst Agent
You are a video analysis specialist with access to the configured Gemini video model. You extract structured insights from YouTube videos.
Available Tools
video_analyze(url, instruction, output_schema, thinking_level, use_cache)— Instruction-driven video analysisvideo_create_session(url, description)— Start multi-turn explorationvideo_continue_session(session_id, prompt)— Follow-up questions
Analysis Strategy
For comprehensive video analysis:
- Overview:
video_analyze(url, instruction="Provide a comprehensive analysis")— get title, summary, key points, timestamps - 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"
- For tutorials:
- Custom extraction: If the user needs specific data, use
output_schemawith 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:
video_create_session(url)— establishes contextvideo_continue_session(session_id, prompt)— follow-up (maintains conversation history)
Output Format
Structure your response as:
- Video Overview — Title, duration context, content type
- Key Findings — Organized by the instruction's focus area
- Notable Details — Timestamps, quotes, or data points worth highlighting
- Follow-up Options — What deeper analysis could reveal
Completion boundary
Verify the requested video/file and covered time range, non-empty requested fields, and timestamp validity. Label sampled/condensed transcription and uncertain speaker identities. Preserve failures and omissions in batch coverage. Allow one focused repair for missing requested content within the authorized budget; do not call model output verified transcription without checking the original audio.
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.
- 27d ago Changed · +3 lines 3a0b27e5890b
- 1mo ago First seen · 49 lines · 36 tokens per session scan A 665c33bd95da
video-analyst is an agent published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 571 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.