excalidraw-diagrams

excalidraw-diagrams is a skill for Claude Code from sammcj/agentic-coding. It costs 30 tokens per session (1,739 once invoked), scanned A, original, Apache-2.0.

A guide for creating or updating Excalidraw diagrams, which are hand-drawn-style visual diagrams made in a browser.

In plain words
What is it for?
Creating saved Excalidraw flowcharts and other diagrams when the required diagram tool is available.
Why use it?
It helps keep diagram layouts, colors, text, and connections clear and consistent.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/samm/.claude/skills/excalidraw-diagrams/scripts.

Good fit Creating saved Excalidraw flowcharts and other diagrams when the required diagram tool is available.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

agentmods badge for excalidraw-diagrams

README.md
[![agentmods](https://agentmods.dev/badge/skills/sammcj/agentic-coding/excalidraw-diagrams.svg)](https://agentmods.dev/skills/sammcj/agentic-coding/excalidraw-diagrams)
Your own site
<a href="https://agentmods.dev/skills/sammcj/agentic-coding/excalidraw-diagrams"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/excalidraw-diagrams.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,739 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 $0.00030 $0.01739
Opus 5 $0.00015 $0.00870
Sonnet 5 $0.00006 $0.00348
Haiku 4.5 $0.00003 $0.00174

Measured 4d ago against content hash ccd2663996d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

excalidraw-diagrams 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_excalidraw.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.

Skills/excalidraw-diagrams/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creating Excalidraw Diagrams

When creating Excalidraw diagrams, ensure you:

  • Generate the layout with correct spacing
  • Make consistent and logical use of colours, fonts, and shapes
  • Text is correctly added within shapes, not as separate text elements (unless desired)
  • Arrows and lines are correctly anchored / connected to shapes (not floating) so that when objects are moved any connections remain intact
  • You save the Excalidraw diagram content to a file and link the file path
  • Call read_me before your first create_view call each session - it provides the colour palette, camera sizes, layout rules, and element format reference.
  • If the user has asked you to create Excalidraw diagrams but you do not have the Excalidraw MCP enabled, you should ask them to add it for you, they can configured it by using the HTTP MCP URL of: https://excalidraw-mcp-app.vercel.app/mcp and they can view the MCP documentation here: https://github.com/excalidraw/excalidraw-mcp

Choose your workflow

Pick one based on what the user needs. Do not default to doing both.

Inline preview only (create_view)

Use when the diagram is for the conversation only - the user wants to see it in the chat and does not need a file.

  • Use create_view with label on shapes (works fine here)
  • Use cameraUpdate to animate and guide attention
  • No file output needed

File output only (Python script)

Use when the user needs a .excalidraw file to open, share, edit, or keep. Skip create_view entirely.

  • Generate the file with scripts/generate_excalidraw.py (see below)
  • Provide the file path to the user
  • Files can be opened by dragging into excalidraw.com, the Excalidraw desktop app, or VS Code with the Excalidraw extension

Both (inline preview + file)

Use when the user wants to see the diagram in the chat AND keep a file. Note: these are built independently with different element formats. There is no data bridge between them - you define the diagram structure once conceptually but render it twice.

Read the full file on GitHub · 117 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. 4d ago Changed · +2 lines ccd2663996d9
  2. 8d ago First seen · 115 lines · 30 tokens per session scan A 352d83ec33f9

Subscribe to this mod's changes

excalidraw-diagrams is a skill published in the GitHub repository sammcj/agentic-coding (160 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 1,739 once invoked, about $0.0002 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 2026-08-30.