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 antoinebou12/uml-mcp --skill d3_architecturegit clone --depth 1 https://github.com/antoinebou12/uml-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/antoinebou12/uml-mcp/d3_architecture)<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/d3_architecture"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/d3_architecture/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/antoinebou12/uml-mcp/d3_architecture"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/d3_architecture.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 | $0.00075 | $0.00755 |
| Opus 5.5 | $0.00030 | $0.00302 |
| Sonnet 5.5 | $0.00015 | $0.00151 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
d3_architecture 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 2d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
d3_architecture diagram (uml-mcp plugin d3)
diagram_type: d3_architecture
Backend: plugin:d3 (bundled with uml-mcp, on by default)
Output formats: html, svg
System or cloud architecture (D3): boxes in nested groups with AWS, Azure, GCP and Kubernetes style icons, input/output ports, A*-routed straight arrows and draggable boxes. JSON; html or svg
Load the workflow skill uml-mcp-diagrams and the focused guide skill://uml-mcp-guides/d3-plugins/SKILL.md. This file is notation only; it does not add an MCP tool.
Example prompt
Our AI app: Cloudflare in front of a Vercel app, a LangChain agent calling Claude, OpenAI and Gemini, Postgres for data.
Notation tips
- Node
servicekeys draw real logos:aws:s3,gcp:run,tech:claude,tech:github,tech:vercel... groupsnest (region>vpc>subnet);provideris a top-level field, never a node field.- Call
d3_catalog(when enabled) for every service key before writing source.
Styling
Pass theme (auto, dark or light) to generate_uml / generate_uml_image, or set it in the source. auto follows the reader's system in the HTML page and is dark in static SVG and PNG.
Example source
{"title":"Orders service on AWS","provider":"aws","groups":[{"id":"region","label":"eu-west-1","type":"region"},{"id":"vpc","label":"VPC 10.0.0.0/16","type":"vpc","parent":"region"},{"id":"private","label":"Private subnets","type":"subnet","parent":"vpc"}],"nodes":[{"id":"users","label":"Users","kind":"user"},{"id":"cdn","label":"CDN","service":"aws:cloudfront"},{"id":"api","label":"API","service":"aws:apigateway","group":"vpc","inputs":["https"],"outputs":["invoke"]},{"id":"orders","label":"Orders","service":"aws:lambda","group":"private","inputs":["invoke"],"outputs":["rows","events"]},{"id":"db","label":"Orders table","service":"aws:dynamodb","group":"private"},{"id":"queue","label":"Order events","service":"aws:sqs","group":"private"},{"id":"mail","label":"Notifier","service":"aws:lambda","group":"private"}],"links":[{"from":"users","to":"cdn","label":"HTTPS"},{"from":"cdn","to":"api:https"},{"from":"api:invoke","to":"orders:invoke"},{"from":"orders:rows","to":"db","label":"read / write"},{"from":"orders:events","to":"queue","style":"dashed"},{"from":"queue","to":"mail","style":"dashed"}]}
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.
- 2d ago First seen · 36 lines · 75 tokens per session scan A f75382490e63
d3_architecture is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 755 once invoked, about $0.0003 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 2026-11-05.
d3_architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| d3_architectureantoinebou12/uml-mcp | Skill | 109 | yesterday | MIT | A | 75 | Claude Code, Codex |
| dstack-prototypingdstackai/dstack | Skill | 2.3k | yesterday | MPL-2.0 | A | 80 | Claude Code, Codex |
| aws-architecture-diagramawslabs/agent-plugins | Skill | 937 | yesterday | Apache-2.0 | A | 110 | Claude Code |
| architecture-diagrammateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| nvaf-architecture-diagramsNVIDIA/nvcf | Skill | 253 | 4d ago | Apache-2.0 | A | 70 | Claude Code, Codex |
| aws-architecture-diagramautomateyournetwork/netclaw | Skill | 715 | yesterday | Apache-2.0 | A | 43 | Claude Code, Codex |
| architecture-diagramsexcalimate/excalimate | Skill | 100 | 5d ago | MIT | A | 59 | Claude Code, Codex |