A skill for creating and checking draw.io diagrams, which are editable diagrams stored in XML files. It covers flowcharts, software architecture diagrams, and sequence diagrams, including layout and Japanese-text rules.

Use it to generate or validate draw.io files for processes, system designs, and step-by-step interactions.

It reduces broken diagrams and inconsistent layouts by checking the XML structure, connections, fonts, routing, and containers against defined rules.

draw-io — Skill for Claude Code by ekusiadadus/draw-mcp

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 ekusiadadus/draw-mcp --skill draw-io

Clone the repo

git clone --depth 1 https://github.com/ekusiadadus/draw-mcp

Made for: Claude Code.

Or install draw-io, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ekusiadadus/draw-mcp/draw-io/github.svg)](https://agentmods.dev/skills/ekusiadadus/draw-mcp/draw-io)

Your own site

<a href="https://agentmods.dev/skills/ekusiadadus/draw-mcp/draw-io"><img src="https://agentmods.dev/badge/skills/ekusiadadus/draw-mcp/draw-io/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ekusiadadus/draw-mcp/draw-io"><img src="https://agentmods.dev/badge/skills/ekusiadadus/draw-mcp/draw-io.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,251 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00055	$0.02251
Opus 5.5	$0.00022	$0.00900
Sonnet 5.5	$0.00011	$0.00450
Haiku 4.5	$0.00006	$0.00225

Measured 2mo ago against content hash 06f2e1bc0558, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

draw-io 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 2mo 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.

skills/draw-io/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

draw.io XML Generation Specification v2.0

1. Scope

This specification defines the rules for AI-generated draw.io XML files. It ensures consistent, high-quality output that renders correctly in draw.io desktop, web, and PNG export. Rules are categorized as:

MUST (Severity: ERROR) — Violations break rendering or structure
SHOULD (Severity: WARNING) — Violations degrade quality
INFORMATIONAL (Severity: INFO) — Suggestions for best practices

All rules are enforced by the draw-mcp-validate CLI tool with 23 validation rules.

2. Structural Rules (MUST)

2.1 File Hierarchy

mxfile > diagram > mxGraphModel > root > mxCell...

Every file MUST follow this hierarchy. The mxfile element is the root.

2.2 Root Cells

Two root cells MUST always be present:

<mxCell id="0"/>
<mxCell id="1" parent="0"/>

Cell id="0" is the invisible root. Cell id="1" is the default layer with parent="0".

2.3 Parent References

Every mxCell with a parent attribute MUST reference an existing cell id. Orphaned references cause rendering failures.

2.4 Vertex/Edge Exclusivity

A cell MUST NOT have both vertex="1" and edge="1". It is either a shape or a connection, never both.

2.5 Edge Geometry

Edge mxGeometry MUST have relative="1":

<mxCell id="e1" edge="1" parent="1" source="a" target="b"
  style="edgeStyle=orthogonalEdgeStyle;">
  <mxGeometry relative="1" as="geometry"/>
</mxCell>

2.6 Unique IDs

All mxCell elements MUST have unique id attributes.

2.7 XML Well-Formedness

MUST NOT use -- inside XML comments (illegal per XML spec)
MUST escape special characters in attribute values: &, <, >, "

3. Style String Rules (MUST)

3.1 Format

Style strings use key=value; pairs with a trailing semicolon:

style="rounded=1;whiteSpace=wrap;html=1;fontFamily=Noto Sans JP;fontSize=18;"

3.2 Boolean Values

Boolean style keys MUST use 0 or 1, never true or false:

Read the full file on GitHub · 298 lines

Files

What ships with it

3 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.

2mo ago First seen · 298 lines · 55 tokens per session scan A 06f2e1bc0558

Subscribe to this mod's changes

draw-io is a skill published in the GitHub repository ekusiadadus/draw-mcp (31 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 2,251 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 2026-08-30.

Claude Code Design and UX ai-agents architecture-diagrams developer-tools diagrams drawio

draw-io next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
draw-ioekusiadadus/draw-mcp	Skill	31	3mo ago	MIT	A	55	Claude Code
diagram-designcathrynlavery/diagram-design	Skill	65k	3d ago	MIT	A	214	Claude Code
recreate-scientific-figure-in-drawioicebird1998/drawio-scientific-illustrator	Skill	1.5k	3mo ago	MIT	A	118	Codex
FlowForgewentong2022-arch/flowforge-skill	Skill	139	4mo ago	MIT	A	153	Claude Code
VisioIntegrationCloudDaddyZA/VisioIntegration	Skill	2	4mo ago	MIT	A	0	Claude Code, Codex
AlphaEar Logic Visualizerwangfe/awesome-finance-skills	Skill	5	6mo ago	MIT	A	24	Claude Code, Codex
drawio-skillAgents365-ai/drawio-skill	Skill	11k	5d ago	MIT	A	107	Claude Code, Codex