uml-mcp: Skill for Claude Code

.github/skills/uml-mcp-stack-diagram/SKILL.md

uml-mcp-stack-diagram is a skill for Claude Code, Codex from antoinebou12/uml-mcp. It costs 25 tokens per session (627 once invoked), scanned A, original, MIT.

A tool guide for drawing stack and cloud architecture diagrams with service icons, nested groups, and labelled connections. A stack diagram shows how an application is built from technologies and services.

In plain words
What is it for?
Use it to map web apps, APIs, databases, authentication, payments, hosting, and deployment services in one architecture view.
Why use it?
It helps present a complicated system layout in a readable diagram instead of a plain list of tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is antoinebou12/uml-mcp's own configuration. It tells Claude Code and Codex how to work on uml-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything uml-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to antoinebou12/uml-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/antoinebou12/uml-mcp/main/.github/skills/uml-mcp-stack-diagram/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/antoinebou12/uml-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for uml-mcp-stack-diagram

README.md
[![agentmods](https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-mcp-stack-diagram/github.svg)](https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-mcp-stack-diagram)
Your own site
<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-mcp-stack-diagram"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-mcp-stack-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.

agentmods 80×15 button for uml-mcp-stack-diagram

Your own site · 80×15
<a href="https://agentmods.dev/skills/antoinebou12/uml-mcp/uml-mcp-stack-diagram"><img src="https://agentmods.dev/badge/skills/antoinebou12/uml-mcp/uml-mcp-stack-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 627 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00627
Opus 5.5 $0.00010 $0.00251
Sonnet 5.5 $0.00005 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured yesterday against content hash 16a7da925e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uml-mcp-stack-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 yesterday.

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.

.github/skills/uml-mcp-stack-diagram/SKILL.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stack diagrams

Follow skill://uml-mcp-diagrams/SKILL.md. Icon tiles on engineered paper, nested vendor and region groups and labelled right-angled edges, laid out for you left to right, right to left, top down or bottom up.

Types

Type Use for Example prompt
stack_diagram a stack or cloud diagram with icon tiles, nested vendor and region groups Draw my stack: Next.js and Hono on Vercel, Neon Postgres, Clerk for auth, Stripe for payments, GitHub Actions deploys. Left to right.

Steps

  1. Check the live catalog (list_diagram_types or uml://types); the bundled plugins are on by default, but a server may turn them off with plugins.bundled: false.
  2. Read the type's example from uml://examples and keep its field names.
  3. Call validate_uml; an error names the field and, for a bad reference, lists the known ids, so fix it and validate again.
  4. Render with generate_uml_image for a chat image, or generate_uml with output_format: "html" for the interactive page in the MCP App viewer. Clients without MCP Apps still get the PNG and SVG.
  5. Pass theme (auto, dark, light) rather than editing colours.

Example

{"title":"SaaS stack","direction":"LR","theme":"dark","groups":[{"id":"vercel","name":"Vercel","style":"plain","icon":"vercel"},{"id":"github","name":"GitHub","style":"vendor","tone":"blue","icon":"github"}],"nodes":[{"id":"user","name":"User","role":"browser","icon":"user"},{"id":"web","name":"Next.js","role":"frontend","icon":"browser","group":"vercel"},{"id":"api","name":"Hono","role":"api routes","icon":"function","group":"vercel"},{"id":"db","name":"Neon","role":"serverless postgres","icon":"database"},{"id":"auth","name":"Clerk","role":"auth","icon":"lock"},{"id":"pay","name":"Stripe","role":"payments","icon":"payments"},{"id":"ci","name":"GitHub Actions","role":"ci","icon":"github","group":"github"}],"edges":[{"from":"user","to":"web","label":"HTTPS"},{"from":"web","to":"api","label":"RPC"},{"from":"api","to":"db","label":"SQL"},{"from":"api","to":"auth","label":"session","tone":"neutral"},{"from":"api","to":"pay","label":"checkout","tone":"neutral"},{"from":"ci","to":"web","label":"deploy","style":"dashed"}]}

Read the full file on GitHub · 29 lines

Changes

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.

  1. yesterday First seen · 29 lines · 25 tokens per session scan A 16a7da925e74

Subscribe to this mod's changes

uml-mcp-stack-diagram is a skill published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 627 once invoked, about $0.0001 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.

Related

uml-mcp-stack-diagram compared with skills from other repositories

uml-mcp-stack-diagram next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
uml-mcp-stack-diagramantoinebou12/uml-mcpSkill109yesterdayMITA25Claude Code, Codex
dstack-prototypingdstackai/dstackSkill2.3kyesterdayMPL-2.0A80Claude Code, Codex
aws-architecture-diagramawslabs/agent-pluginsSkill937yesterdayApache-2.0A110Claude Code
architecture-diagrammateaix/mateclawSkill1.2kyesterdayApache-2.0A15Claude Code, Codex
nvaf-architecture-diagramsNVIDIA/nvcfSkill2534d agoApache-2.0A70Claude Code, Codex
aws-architecture-diagramautomateyournetwork/netclawSkill715yesterdayApache-2.0A43Claude Code, Codex
architecture-diagramsexcalimate/excalimateSkill1005d agoMITA59Claude Code, Codex