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 furkangonel/cowrangler --skill architecture-diagramgit clone --depth 1 https://github.com/furkangonel/cowranglerWrote 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/furkangonel/cowrangler/architecture-diagram)<a href="https://agentmods.dev/skills/furkangonel/cowrangler/architecture-diagram"><img src="https://agentmods.dev/badge/skills/furkangonel/cowrangler/architecture-diagram/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/furkangonel/cowrangler/architecture-diagram"><img src="https://agentmods.dev/badge/skills/furkangonel/cowrangler/architecture-diagram.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 | $0.00015 | $0.02315 |
| Opus 5 | $0.00008 | $0.01157 |
| Sonnet 5 | $0.00003 | $0.00463 |
| Haiku 4.5 | $0.00002 | $0.00231 |
Grade A, and why
architecture-diagram 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Diagram SOP
When to Use
- User wants to visualize system architecture, microservices, cloud infrastructure
- User asks for a data flow diagram, sequence diagram, or ERD
- User says "draw", "diagram", "visualize", "architecture chart", "system map"
Color Palette (Dark Theme)
| Node Type | Fill | Stroke | Label Color |
|---|---|---|---|
| Service / API | #1e3a5f |
#4a9eff |
#a8d4ff |
| Database | #1a3d2b |
#4caf50 |
#a8e6b0 |
| Queue / Broker | #3d2a00 |
#ff9800 |
#ffd180 |
| External / SaaS | #2d1f3d |
#9c27b0 |
#ce93d8 |
| User / Client | #2a2a2a |
#9e9e9e |
#e0e0e0 |
| Load Balancer | #1f2d3d |
#00bcd4 |
#80deea |
Background: #0d0d1a
Arrow color: #555577
Font family: 'Inter', 'Segoe UI', sans-serif
SVG Structure Template
Produce a self-contained HTML file (or inline SVG) with this skeleton:
<!DOCTYPE html>
<html>
<head>
<meta charset="UTF-8">
<style>
body { margin: 0; background: #0d0d1a; display: flex; align-items: center; justify-content: center; min-height: 100vh; }
svg { font-family: 'Inter', 'Segoe UI', sans-serif; }
</style>
</head>
<body>
<svg width="900" height="600" viewBox="0 0 900 600" xmlns="http://www.w3.org/2000/svg">
<rect width="900" height="600" fill="#0d0d1a"/>
<!-- TITLE -->
<text x="450" y="36" text-anchor="middle" fill="#e0e0e0" font-size="18" font-weight="600">System Architecture</text>
<!-- NODES — use <g> groups for each node -->
<!-- SERVICE NODE TEMPLATE -->
<g transform="translate(100, 100)">
<rect width="140" height="54" rx="8" fill="#1e3a5f" stroke="#4a9eff" stroke-width="1.5"/>
<text x="70" y="22" text-anchor="middle" fill="#a8d4ff" font-size="11" font-weight="600">API Gateway</text>
<text x="70" y="40" text-anchor="middle" fill="#6699cc" font-size="10">Node.js · Port 8080</text>
</g>
<!-- ARROW TEMPLATE (straight) -->
<line x1="240" y1="127" x2="320" y2="127" stroke="#555577" stroke-width="1.5" marker-end="url(#arrow)"/>
<!-- ARROW TEMPLATE (curved) -->
<path d="M 240 200 C 280 200 280 260 320 260" fill="none" stroke="#555577" stroke-width="1.5" marker-end="url(#arrow)"/>
<!-- ARROW MARKER -->
<defs>
<marker id="arrow" markerWidth="8" markerHeight="8" refX="6" refY="3" orient="auto">
<path d="M0,0 L0,6 L8,3 z" fill="#555577"/>
</marker>
</defs>
<!-- LEGEND (bottom-left) -->
<g transform="translate(20, 520)">
<rect width="10" height="10" rx="2" fill="#1e3a5f" stroke="#4a9eff" stroke-width="1"/>
<text x="16" y="9" fill="#888" font-size="9">Service</text>
<rect x="70" width="10" height="10" rx="2" fill="#1a3d2b" stroke="#4caf50" stroke-width="1"/>
<text x="86" y="9" fill="#888" font-size="9">Database</text>
<rect x="150" width="10" height="10" rx="2" fill="#3d2a00" stroke="#ff9800" stroke-width="1"/>
<text x="166" y="9" fill="#888" font-size="9">Queue</text>
<rect x="210" width="10" height="10" rx="2" fill="#2d1f3d" stroke="#9c27b0" stroke-width="1"/>
<text x="226" y="9" fill="#888" font-size="9">External</text>
</g>
</svg>
</body>
</html>
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 · 175 lines · 15 tokens per session scan A 3dcd729d5fee
architecture-diagram is a skill published in the GitHub repository furkangonel/cowrangler (2 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 2,315 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 2026-08-31.
Other skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
Architecture Diagram
Produces clean architecture and system diagrams from actual repo or product truth instead of decorative boxes.
lambda-gpu-cloud
Safely inspect and operate Lambda Cloud GPU instances through the documented Cloud API and SSH, with explicit approval before billable or destructive actions.
tensorpool-gpu-cloud
Safely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action.
modal-serverless-gpu
Run approved CPU or GPU work through OpenScience computejob on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.
runpod-gpu-cloud
Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.