A diagramming tool that works with AI coding agents such as Claude, Cursor, GitHub Copilot, and Windsurf. The available description does not specify which diagram formats or operations it supports.

Use it for diagram-related work inside supported AI coding-agent workflows.

It may connect diagram work to coding agents, but the supplied information is too limited to identify a more specific problem it solves.

draw-io — Skill for Claude Code by saajunaid/caddis-plugin

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 saajunaid/caddis-plugin --skill draw-io

Clone the repo

git clone --depth 1 https://github.com/saajunaid/caddis-plugin

Made for: Claude Code.

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/saajunaid/caddis-plugin/draw-io/github.svg)](https://agentmods.dev/skills/saajunaid/caddis-plugin/draw-io)

Your own site

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

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,491 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.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.01491
Opus 5.5	$0.00013	$0.00596
Sonnet 5.5	$0.00007	$0.00298
Haiku 4.5	$0.00003	$0.00149

Measured 1mo ago against content hash 1ecaa646bc47, 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 1mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/convert-drawio-to-png.sh, scripts/find_aws_icon.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.

.github/skills/media/draw-io/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

draw.io Diagram Skill

Works with: Any AI coding agent (Claude, Cursor, GitHub Copilot, Windsurf, etc.)

Quick Reference

Task	Command
Convert to PNG	`bash scripts/convert-drawio-to-png.sh file.drawio`
Find AWS icon	`python scripts/find_aws_icon.py ec2`
List all icons	`python scripts/find_aws_icon.py --list-all`
Direct export	`drawio -x -f png -s 2 -t -o out.png in.drawio`

Core Rules

File Handling

Edit only .drawio files (XML format)
Never edit .drawio.png directly
Always verify PNG output after changes
After edits, validate XML structure before handing off

Fonts

Set defaultFontFamily in <mxGraphModel> tag
Set fontFamily in each text element's style
Use 18px+ for presentations, 14px minimum

Background

Remove background="#ffffff" attribute
Use page="0" for transparent background

Arrows

Critical: Place arrows after title, before other elements
Maintain 20px clearance from labels
Use explicit coordinates for text element connections
For flow edges, set explicit arrowheads and stroke styling:
- endArrow=block;endFill=1
- strokeColor=<visible color>;strokeWidth>=1

XML Structure (Critical)

Never nest mxCell inside another mxCell; all mxCell entries must be direct children of <root>.
Edge labels must be separate sibling mxCell nodes with parent set to the edge id.
Keep only geometry/content tags (for example mxGeometry) inside a given mxCell.

Viewport and Coordinates

Use sane viewport defaults: keep dx/dy near 0.
Ensure page dimensions cover the full drawing bounds (pageWidth/pageHeight large enough).
Keep nodes/points in positive in-canvas coordinates unless there is an explicit reason not to.
If a diagram opens off-screen, normalize coordinates and reset dx/dy before finalizing.

Container Margins

Must: 30px minimum margin from frame boundaries
Calculate: element top ≥ frame.y + 30
Calculate: element bottom ≤ frame.y + frame.height - 30

Read the full file on GitHub · 163 lines

Files

What ships with it

6 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.

1mo ago First seen · 163 lines · 33 tokens per session scan A 1ecaa646bc47

Subscribe to this mod's changes

draw-io is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 1,491 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 2026-09-03.

Design and UX agent-framework agentic-ai agentic-automation agentic-workflow ai-agents automation

goga-define-experience

Define the user experience required to achieve the established product goals and solve the identified problem.

qarium/goga · 6 tokens

render-html-page

Convert a finished trip plan into a polished, self-contained HTML page using the design system.

mochow13/keen-agent · 22 tokens

anti-slop-image-direction

Opt-in, paid reference images for marketing or new-site work: plan one image per section, confirm count, backend and cost, generate with pi-nano-banana, then distill a written direction brief for the mockup loop. Images are direction, never source. Never for product UI. Triggers: "generate design references", "image…

BlackBeltTechnology/pi-agent-dashboard · 86 tokens

vectorcraft

Headless vector illustration with VectorCraft (Illustrator-style paths, shapes, type, fills/strokes), provisioned on demand by pi-craft - draw shapes and export svg, pdf or png, or convert between vector formats. Use for "draw a logo as an svg", "export this illustration as a pdf", "convert this svg to a png at 2x"…

BlackBeltTechnology/pi-agent-dashboard · 88 tokens

goga-define-challenge

Challenge the complete product definition before the PRD is generated.