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.
npx skills add Galbaz1/video-research-mcp --skill video-researchgit 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/skills/galbaz1/video-research-mcp/video-research)<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/video-research"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/video-research/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/skills/galbaz1/video-research-mcp/video-research"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/video-research.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 | $0.00049 | $0.03502 |
| Opus 5 | $0.00024 | $0.01751 |
| Sonnet 5 | $0.00010 | $0.00700 |
| Haiku 4.5 | $0.00005 | $0.00350 |
Grade A, and why
video-research 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 12d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Research MCP — Tool Usage Guide
You have access to the video-research-mcp MCP server, which exposes 28 tools powered by Gemini 3.1 Pro and the YouTube Data API. These tools are instruction-driven — you write the instruction, Gemini returns structured JSON. Three tools (video_metadata, video_comments, video_playlist) use the YouTube Data API directly for fast metadata retrieval without Gemini inference.
Core Principle
Tools accept an instruction parameter instead of fixed modes. Write specific, actionable instructions. The more precise your instruction, the better the structured output.
Tool Selection Guide
| I want to... | Use this tool |
|---|---|
| Get video title, stats, duration, tags | video_metadata |
| List videos in a YouTube playlist | video_playlist |
| Analyze a YouTube video | video_analyze |
| Have a multi-turn conversation about a video | video_create_session + video_continue_session |
| Research a topic in depth | research_deep |
| Plan a research strategy | research_plan |
| Verify a specific claim | research_assess_evidence |
| Launch long-running web-grounded deep research | research_web |
| Poll status of a running deep-research job | research_web_status |
| Ask follow-up questions on a completed deep-research report | research_web_followup |
| Cancel a running deep-research job | research_web_cancel |
| Analyze a URL, file, or text | content_analyze |
| Batch-analyze a folder of documents | content_batch_analyze |
| Extract structured data from content | content_extract |
| Deep research grounded in documents | research_document |
| Search the web for current info | web_search |
| Check or clear the cache | infra_cache |
| Change model/thinking/temperature | infra_configure |
| Find past analyses and research | /gr:recall "topic" (semantic search when Weaviate configured) |
| Get AI answer from past work | /gr:recall ask "question" (requires Weaviate + weaviate-agents) |
| Browse knowledge gaps | /gr:recall fuzzy or /gr:recall unknown |
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.
- 12d ago First seen · 354 lines · 49 tokens per session scan A 0862955b6612
video-research is a skill published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 3,502 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.
Other skills, from other repositories
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
b123d-edit
Use this skill when the task is to change an existing build123d model or script: "make this bracket 5 mm taller", "move the holes inward", "add a counterbore", "remove this rib", "make it fit this mating part", or "repair the code so the intended edit remains parametric".
hmem-release
Pre-publish checklist for hmem: skills synced, version bumped, tests green, nothing forgotten. Use before npm publish or when the user says 'release', 'publish', 'push a release', or 'neue Version'.
workflows
Knowledge about ComfyUI workflow API format, node connections, and common patterns. Use when helping users build, modify, or understand workflows.
class-management
Use when the user wants to create a new class, group, or course in Zooza — e.g. "set up a Monday yoga class", "add a new group", "schedule a course". Guides through programme selection, venue, trainer, session pattern, and commits.
hmem-context
Load specific context from hmem based on what is needed RIGHT NOW. Use when loadproject output is not enough for the current question.