drawio-diagramming

drawio-diagramming is a skill for Claude Code from Goodsmileduck/claude-registry. It costs 73 tokens per session (3,219 once invoked), scanned A, original, MIT.

Instructions for creating and opening draw.io diagrams, including architecture, cloud and Kubernetes layouts, network maps, and flowcharts. Draw.io is a tool for making editable diagrams.

In plain words
What is it for?
Use it to document systems, cloud infrastructure, Kubernetes clusters, network topology, processes, and other technical relationships in .drawio files.
Why use it?
It gives agents a defined way to turn source code and infrastructure details into consistent diagrams instead of drawing disconnected or inaccurate shapes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the diagramming-skills plugin — 1 skill shipped together

Good fit Use it to document systems, cloud infrastructure, Kubernetes clusters, network topology, processes, and other technical relationships in .drawio files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/goodsmileduck/claude-registry/drawio-diagramming
Install

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.

Any agent
npx skills add Goodsmileduck/claude-registry --skill drawio-diagramming
Clone the repo
git clone --depth 1 https://github.com/Goodsmileduck/claude-registry

Made for: Claude Code.

Or install diagramming-skills, the plugin that ships this one along with the rest of its 1 skill.

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 drawio-diagramming

README.md
[![agentmods](https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/drawio-diagramming/github.svg)](https://agentmods.dev/skills/goodsmileduck/claude-registry/drawio-diagramming)
Your own site
<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/drawio-diagramming"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/drawio-diagramming/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 drawio-diagramming

Your own site · 80×15
<a href="https://agentmods.dev/skills/goodsmileduck/claude-registry/drawio-diagramming"><img src="https://agentmods.dev/badge/skills/goodsmileduck/claude-registry/drawio-diagramming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,219 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 $0.00073 $0.03219
Opus 5 $0.00036 $0.01610
Sonnet 5 $0.00015 $0.00644
Haiku 4.5 $0.00007 $0.00322

Measured 10d ago against content hash 593742ef02c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

drawio-diagramming 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/gen_arch_drawio.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/diagramming-skills/skills/drawio-diagramming/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draw.io MCP Server

Architecture / HLA diagrams (infra, Kubernetes, topology)

For polished architecture / High-Level-Architecture diagrams (cloud infra, GKE/k8s clusters, network topology) — not generic flowcharts — follow the dedicated method: read references/architecture-diagrams.md and generate with scripts/gen_arch_drawio.py (box / icon / note / edge / write_mxfile helpers).

Headline rules (full detail in the reference): derive every node from real source code (Terraform/Helm/manifests) before drawing; generate via the Python helper (consistent coords, edges by ID) rather than hand-XML; 64×54 stencil icons (mxgraph.kubernetes.icon / mxgraph.gcp2.*) colored by role; semantic edge colors with a legend; always set explicit exit/entry anchors + waypoints (never target box centers); comb-bus a hub into a single adjacent column; ladder/rail parallel edges ≥13px apart; short centered container titles with qualifiers pushed into dashed notes; keep notes/legend out of edge channels; leave ~40px breathing room at container bottoms. The rest of this file covers the underlying MCP tools and XML mechanics those diagrams build on.

The official draw.io MCP (Model Context Protocol) server that enables LLMs to open and create diagrams in the draw.io editor.

Repository Structure

  • mcp-app-server/ — MCP App server (renders diagrams inline in chat via iframe). Hosted at https://mcp.draw.io/mcp. Can also be self-hosted via Node.js or Cloudflare Workers.
  • mcp-tool-server/ — Original MCP tool server (stdio-based, opens browser). Published as @drawio/mcp on npm.
  • project-instructions/ — Claude Project instructions (no MCP required, no install).
  • skill-cli/ — Claude Code skill (generates native .drawio files, opens in desktop app). No MCP required.

Each subdirectory has its own CLAUDE.md with implementation details.

MCP App Server Tool

create_diagram

Read the full file on GitHub · 252 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 252 lines · 73 tokens per session scan A 593742ef02c5

Subscribe to this mod's changes

drawio-diagramming is a skill published in the GitHub repository Goodsmileduck/claude-registry (1 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 3,219 once invoked, about $0.0004 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.