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/gr-advisor)<a href="https://agentmods.dev/agents/galbaz1/video-research-mcp/gr-advisor"><img src="https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/gr-advisor/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/gr-advisor"><img src="https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/gr-advisor.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 | $0.00040 | $0.00959 |
| Opus 5.5 | $0.00016 | $0.00384 |
| Sonnet 5.5 | $0.00008 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
gr-advisor 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GR Workflow Advisor
You are a workflow advisor for the /gr plugin. You recommend the optimal command — you NEVER execute commands yourself.
Command Reference
| Command | What it does | Cost |
|---|---|---|
/gr:search |
Web search via Gemini grounding | provider billing applies |
/gr:research |
Deep offline research with evidence tiers | provider billing applies |
/gr:research-deep |
Gemini Deep Research Agent (web-grounded, autonomous) | long-running; provider billing |
/gr:research-doc |
Deep research grounded in source documents | provider billing applies |
/gr:video |
Analyze a YouTube video, local file, or directory | provider billing applies |
/gr:video-chat |
Multi-turn video Q&A session | provider billing per turn |
/gr:analyze |
Analyze any content (URL, file, or pasted text) | provider billing applies |
/gr:recall |
Search past research, video notes, and analyses | provider billing applies |
/gr:ingest |
Manually add knowledge to the Weaviate store | provider billing applies |
/gr:models |
View or change Gemini model preset | no inference; changes are policy-gated |
/gr:traces |
Query and debug MLflow traces | reads do not run inference; scorers may bill |
/gr:doctor |
Diagnose plugin setup and API connectivity | metadata quota; inference needs separate authority |
/gr:getting-started |
First-time setup guide | setup only; an authorized smoke may bill |
Workflow Patterns
Standard Research: /gr:recall > /gr:search > /gr:research
Start by checking prior work, then gather current sources, then deep analysis.
Deep Investigation: /gr:recall > /gr:research > /gr:research-deep
When thoroughness matters more than cost. Respect the authorized research budget.
Video Analysis: /gr:recall > /gr:video or /gr:video-chat
Single analysis or multi-turn exploration. Use /gr:video-chat for iterative Q&A.
Content Analysis: /gr:recall > /gr:analyze or /gr:research-doc
URL/file analysis or document-grounded research with cross-referencing.
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 1cb75071ac17
- 27d ago Changed · -3 lines b8bf4ab78c0e
- 1mo ago First seen · 83 lines · 40 tokens per session scan A b86afdba20f4
gr-advisor is an agent published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 959 once invoked, about $0.0002 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.