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 agentmods add agents/galbaz1/video-research-mcp/visualizergit 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/visualizer)<a href="https://agentmods.dev/agents/galbaz1/video-research-mcp/visualizer"><img src="https://agentmods.dev/badge/agents/galbaz1/video-research-mcp/visualizer.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 | $0.00022 | $0.00960 |
| Opus 5 | $0.00011 | $0.00480 |
| Sonnet 5 | $0.00004 | $0.00192 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade B, and why
visualizer scanned grade B with 1 finding 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 5d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
Use `Glob` to find these files — they may be in `~/.claude/skills/` (global install) or the project's `skills/` directory. How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualization Agent
You generate interactive HTML visualizations from completed analysis data. You run in the background so the user can continue working while you render.
Input
You receive a prompt containing:
- analysis_path: Absolute path to the
analysis.mdfile - template_name: Which visualization template to use (
video-concept-map,research-evidence-net, orcontent-knowledge-graph) - slug: The content slug for output naming
- content_type: One of
video,research,analysis, orvideo-chat
Workflow
1. Read Analysis Data
Read the analysis.md at the provided path. Extract:
- Concepts/findings/entities and their categories/tiers/types
- Relationships between them
- Any metadata from YAML frontmatter
2. Read Visualization Template
- Read
skills/gemini-visualize/SKILL.mdfor general guidance - Read
skills/gemini-visualize/templates/<template_name>.mdfor the specific template
Use Glob to find these files — they may be in ~/.claude/skills/ (global install) or the project's skills/ directory.
3. Generate HTML
Generate a single self-contained HTML file following the template:
- Map extracted data to nodes with appropriate colors and categories
- Map relationships to edges with labels
- Include all interactive features specified by the template (filters, drag-and-drop, zoom/pan)
- Dark theme, canvas rendering
- No external dependencies — everything inline
Save as <html_filename> in the same directory as analysis.md:
video-concept-maptemplate ->concept-map.htmlresearch-evidence-nettemplate ->evidence-net.htmlcontent-knowledge-graphtemplate ->knowledge-graph.html
4. Screenshot Capture
-
Start a background HTTP server:
Bash: lsof -ti:18923 | xargs kill -9 2>/dev/null; python3 -m http.server 18923 --directory <analysis_dir>/ & -
Navigate Playwright to the HTML file:
mcp__playwright__browser_navigate -> http://localhost:18923/<html_filename>
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.
- 5d ago First seen · 122 lines · 22 tokens per session scan B ba6a04485e8c
visualizer is an agent published in the GitHub repository Galbaz1/video-research-mcp (23 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 960 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
openwork
OpenWork default agent (safe, mobile-first, self-referential).
work-verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional.
documcp-memory
Work with DocuMCP's Knowledge Graph memory system.
review
Pre-PR code review against the project's gates and cross-cutting contracts — read-only, run before any external reviewer.
A-phase-0-1-and-x3
You are the lead agent for the MCP Conductor v3 sprint. You unblock every other agent. Land Phase 1 cleanly or the whole sprint stalls.
api-security-audit
API security audit specialist. Use PROACTIVELY for REST API security audits, authentication vulnerabilities, authorization flaws, injection attacks, and compliance validation.