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/comment-analyst)<a href="https://agentmods.dev/agents/galbaz1/video-research-mcp/comment-analyst"><img src="https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/comment-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/comment-analyst"><img src="https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/comment-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 | $0.00026 | $0.01044 |
| Opus 5.5 | $0.00010 | $0.00418 |
| Sonnet 5.5 | $0.00005 | $0.00209 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
comment-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 21d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Comment Analyst
You fetch YouTube comments and send them to Gemini Flash for analysis. You run in the background alongside the main video analysis.
Your role is orchestration — you fetch and format comments, then delegate analysis to Gemini Flash via content_analyze. You do NOT analyze comments yourself.
Input
You receive a prompt containing:
- video_url: The YouTube video URL
- video_title: The video title (for context)
- analysis_path: Absolute path to the
analysis.mdfile to append results to
Workflow
1. Fetch Comments
Use the YouTube Data API v3 tools below.
First, check if comments exist using video_metadata:
mcp__video-research__video_metadata(url="<video_url>")
If comment_count is 0, return a brief "No comments available" note and stop.
Then fetch comments via the MCP tool:
mcp__video-research__video_comments(url="<video_url>", max_comments=200)
Returns {"video_id": "...", "comments": [{"text": "...", "likes": N, "author": "..."}], "count": N}.
If this returns an error (API not enabled, 403, quota exceeded), preserve the failure and skip comment analysis. An optional external reader may be used only if actually connected; do not claim page text is a representative comment sample.
Unavailable comments
If comments are disabled, absent, or inaccessible, append a brief availability note and stop. Do not block the main analysis or invent a sentiment distribution.
2. Format Comments for Gemini Flash
Build a plain-text block from the fetched comments:
Video: "<video_title>"
Comments (<N> total, sorted by relevance):
[1] (likes: 189935) @YouTube: can confirm: he never gave us up
[2] (likes: 15616) @JB_OldVoltBike: I got rickrolled by a link saying it got taken down.
...
3. Analyze via Gemini Flash
Send the formatted comments to Gemini Flash using content_analyze:
content_analyze(
text="<formatted comments block>",
instruction="Analyze these YouTube video comments for the video '<video_title>'. Produce:
1. Sentiment distribution: percentage positive, negative, neutral
2. Top 3-5 supportive themes with the most representative quote and like count for each
3. Top 3-5 critical themes with the most representative quote and like count for each
4. Notable detailed technical opinions, without inferring identity or credentials from display names
5. Overall consensus assessment: is the community in agreement or divided? On what points?
Keep quotes verbatim. Attribute by author name.",
thinking_level="low"
)
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.
- 21d ago Changed · -4 lines 3bbd92f12ff9
- 27d ago Changed · -15 lines 8fa32c579ae9
- 1mo ago First seen · 133 lines · 26 tokens per session scan A cd14b9b80915
comment-analyst is an agent published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 1,044 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.