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/commands/galbaz1/video-research-mcp/advisor)<a href="https://agentmods.dev/commands/galbaz1/video-research-mcp/advisor"><img src="https://agentmods.dev/badge/commands/galbaz1/video-research-mcp/advisor.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.00738 |
| Opus 5 | $0.00006 | $0.00369 |
| Sonnet 5 | $0.00002 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
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 8d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Advisor: $ARGUMENTS
Last updated: 2026-03-07 12:34 CET
Recommend the optimal /gr command for this task. Do NOT execute anything.
Step 1: Check Prior Work
Call knowledge_search(query="$ARGUMENTS", limit=3) to find existing research, video notes, or analyses.
If results are found, report:
PRIOR WORK FOUND: <count> results for "$ARGUMENTS"
Top match: <title> (<collection>, <date>)
SUGGESTION: Review existing work with /gr:recall "$ARGUMENTS" before starting new research
If knowledge_search fails (Weaviate not configured), skip this step silently.
Step 2: Categorize Intent
Determine which category best fits "$ARGUMENTS":
| Category | Signals |
|---|---|
| research | topic, question, "how does X work", "what is X" |
| video | YouTube URL, "this video", "analyze video" |
| content | URL, file path, "this article", "this PDF" |
| knowledge | "find", "recall", "what did I research", "past work" |
| system | "setup", "config", "models", "traces", "doctor" |
Step 3: Recommend
Use this quick-reference to select the right command:
| I want to... | Use | Cost |
|---|---|---|
| Quick web lookup | /gr:search |
free, instant |
| Deep topic research | /gr:research |
free, instant |
| Thorough web-grounded research | /gr:research-deep |
$2-5, 10-20 min |
| Research grounded in documents | /gr:research-doc |
free, instant |
| Analyze a video | /gr:video |
free, instant |
| Multi-turn video Q&A | /gr:video-chat |
free, per-turn |
| Analyze a URL/file/text | /gr:analyze |
free, instant |
| Find past work | /gr:recall |
free, instant |
| Save to knowledge store | /gr:ingest |
free, instant |
| Check setup | /gr:doctor |
free, instant |
| View/change model preset | /gr:models |
free, instant |
| Debug MLflow traces | /gr:traces |
free, instant |
| First-time setup guide | /gr:getting-started |
free, instant |
Present your recommendation in this format:
RECOMMENDED: /gr:<command> "<args>"
WHY: <one sentence>
ALTERNATIVE: /gr:<other>
COST: free|$2-5 | TIME: instant|10-20 min
NEXT STEP: <follow-up action>
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.
- 8d ago First seen · 75 lines · 12 tokens per session scan A 929b292b4f74
advisor is a command published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 738 once invoked, about $0.0001 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 commands, from other repositories
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
eg-new-feature
Build a new feature using the elephant/goldfish workflow — design doc, goldfish design check, implement, review, validate.
eg-fix-bug
Fix a bug using the elephant/goldfish workflow — problem doc, goldfish diagnosis check, failing test, fix, review, validate.
mem-prune
Removes old low-importance memories.
mem-last
Prints latest memory cards for the current project.
hybrid
Your tokens cost $15/million. Gemini is FREE.