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 gemini-visualizegit 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/gemini-visualize)<a href="https://agentmods.dev/skills/galbaz1/video-research-mcp/gemini-visualize"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/gemini-visualize/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/gemini-visualize"><img src="https://agentmods.dev/badge/skills/galbaz1/video-research-mcp/gemini-visualize.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 | $0.00047 | $0.01251 |
| Opus 5 | $0.00023 | $0.00626 |
| Sonnet 5 | $0.00009 | $0.00250 |
| Haiku 4.5 | $0.00005 | $0.00125 |
Grade A, and why
gemini-visualize 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 11d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Visualize — Interactive Analysis Visualization
Generate a single-file interactive HTML visualization after every /gr:* analysis, then capture a Playwright screenshot. The agent decides enrichment depth autonomously but respects user steering ("skip visualization", "deeper on X").
Template Selection
| Source Command | Template | Visualization Type |
|---|---|---|
/gr:video, /gr:video-chat |
video-concept-map |
Concept map with knowledge states |
/gr:research |
research-evidence-net |
Evidence network with tier filtering |
/gr:analyze |
content-knowledge-graph |
Knowledge graph with entity types |
Read the appropriate template from skills/gemini-visualize/templates/ before generating.
Core HTML Requirements
Every generated visualization MUST be a single self-contained HTML file with:
- No external dependencies — all CSS, JS, SVG/Canvas inline
- Dark theme — background
#0a0a0f, nodes/text in light colors, high-contrast edges - Canvas or SVG rendering — prefer
<canvas>for large graphs,<svg>for smaller ones - State object pattern — all app state in a single
state = {...}object at the top of<script> - Responsive layout — works in both full-page browser and embedded views
- Smooth animations — transitions on hover, click, filter changes (200-300ms)
Data Mapping (Agent Decisions)
The agent autonomously decides:
- Concept hierarchy depth — based on content richness (3-8 top-level nodes typical, 15-25 total with children)
- Which concepts become nodes vs. which are properties of nodes — major themes → nodes, supporting details → node metadata
- Relationship types — derived from context (e.g., "enables", "contradicts", "builds on", "example of")
- Initial knowledge states — default to
unknownunless the user has indicated familiarity - Category assignment — cluster nodes by topic/theme, assign colors per category
Visualization Features (All Templates)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 110 lines · 47 tokens per session scan A cc6749c369a7
gemini-visualize is a skill published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,251 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
prompt-decorators-usage
Use when a user's prompt would clearly benefit from a reasoning, structure, tone, or verification decorator - or when they ask "what decorators should I use?". Teaches when and how to suggest inline ::Name(params) sigils instead of repeating verbose prompt-engineering instructions manually.
business-model-validator
Use when a prospect, new customer, or existing operator wants to know whether Zooza fits their business, or which Zooza features map to how they operate. No Zooza account required — works as a pure knowledge interview.
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.
openclaw-prompt-enhancer
Remote prompt engineering MCP server with 6 tools that turn weak prompts into powerful ones. Use when: (1) 'improve this prompt' or 'make my prompt better', (2) 'score this prompt' or 'rate prompt quality', (3) 'convert prompt to Claude format' or 'translate for Gemini', (4) 'generate system prompt' or 'create…
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.
add-prompt
Scaffold a new MCP prompt template. Use when the user asks to add a prompt, create a reusable message template, or define a prompt for LLM interactions.