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 nwdiaggit 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/nwdiag)<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/nwdiag"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/nwdiag/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/nwdiag"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/nwdiag.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 | $0.00054 | $0.00587 |
| Opus 5.5 | $0.00022 | $0.00235 |
| Sonnet 5.5 | $0.00011 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
nwdiag 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 14d 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.
What it actually says
nwdiag diagram (uml-mcp)
diagram_type: nwdiag
Backend: nwdiag
Output formats: png, svg, pdf
Network diagrams (blockdiag family)
Load the workflow skill uml-mcp-diagrams for URL-first replies, progressive discovery, and which MCP tool to call. This file is notation only; it does not add an MCP tool.
Notation tips
- Declare
network name { address = "…"; node [address = "…"]; }blocks. - Reuse the same node id in two networks to draw a gateway between them.
- Prefer short node ids (
mcp,gateway); put detail inaddress/description. - Two networks (DMZ + internal) with a shared gateway is the clearest default layout.
Styling
- Network bars + short node ids read best on dark Kroki backgrounds.
- No MCP
theme— structure is the styling.
Starter template
nwdiag {
network internet {
address = "0.0.0.0/0"
}
network internal {
address = "192.168.1.0/24"
server [address = "192.168.1.1"];
}
}
Example
nwdiag {
network dmz {
address = "210.x.x.x/24"
web01 [address = "210.x.x.1"];
web02 [address = "210.x.x.2"];
}
network internal {
address = "172.x.x.x/24";
web01 [address = "172.x.x.1"];
web02 [address = "172.x.x.2"];
db01;
db02;
}
}
Render with uml-mcp
- Set
diagram_typetonwdiagexactly. - Call
validate_umlwhen the source is untrusted (preferstrict: truefor Mermaid sequence). - Call
generate_uml,generate_uml_image(chat PNG), orgenerate_uml_batch. - Pass
themewhen this skill's Themes section lists supported values. - Surface the returned
url/playground(see the workflow skill).
Confirm formats with uml://formats or list_diagram_types when unsure.
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.
- 14d ago First seen · 71 lines · 54 tokens per session scan A 57d04d9900ad
nwdiag is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 587 once invoked, about $0.0002 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 2026-10-24.
nwdiag compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nwdiagantoinebou12/uml-mcp | Skill | 109 | yesterday | MIT | A | 54 | Claude Code, Codex |
| detailed-designpan94u/forge | Skill | 40 | 5d ago | none | A | 27 | Claude Code |
| writing-skillstakaakit/superpowers-uml | Skill | 12 | 1mo ago | none | A | 20 | Claude Code |
| brainstormingtakaakit/superpowers-uml | Skill | 12 | 1mo ago | none | A | 37 | Claude Code |
| finishing-a-development-branchtakaakit/superpowers-uml | Skill | 12 | 1mo ago | none | A | 27 | Claude Code |
| systematic-debuggingtakaakit/superpowers-uml | Skill | 12 | 1mo ago | none | A | 21 | Claude Code |
| test-driven-developmenttakaakit/superpowers-uml | Skill | 12 | 1mo ago | none | A | 17 | Claude Code |