A command for creating Excalidraw architecture and flow diagrams from a description. Excalidraw is a tool for making hand-drawn-style diagrams.

Use it to show services and their relationships, map a request path, explain internal workings, or document an end-to-end scenario.

It turns a written system or process into a visual explanation and chooses a suitable level of detail for the request.

diagram — Command for Claude Code by shahzadahmadv1

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.

Clone the repo

git clone --depth 1 https://github.com/shahzadahmadv1/ExcaliClaude

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/commands/shahzadahmadv1/excaliclaude/diagram/github.svg)](https://agentmods.dev/commands/shahzadahmadv1/excaliclaude/diagram)

Your own site

<a href="https://agentmods.dev/commands/shahzadahmadv1/excaliclaude/diagram"><img src="https://agentmods.dev/badge/commands/shahzadahmadv1/excaliclaude/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/shahzadahmadv1/excaliclaude/diagram"><img src="https://agentmods.dev/badge/commands/shahzadahmadv1/excaliclaude/diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 550 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	$0.00000	$0.00550
Opus 5	$0.00000	$0.00275
Sonnet 5	$0.00000	$0.00110
Haiku 4.5	$0.00000	$0.00055

Measured 12d ago against content hash 9b033aaf6c3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

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 12d 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.

.claude/commands/diagram.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/diagram — Generate an Excalidraw diagram

Generate an Excalidraw architecture or flow diagram using the ExcaliClaude skill.

Arguments

$ARGUMENTS

If no arguments are provided, ask the user what they would like to diagram.

Instructions

Activate the excalidraw-diagram skill — follow its full generation process.
Determine view mode from the request:
- "overview" / "architecture" / "what exists" → overview
- "flow" / "what happens when" / "request path" → focused-flow
- "internals" / "how does X work" → drill-down
- "end to end" / "overview + detail" / "document" → scenario-pack
- When unclear, default to focused-flow for flow questions, overview for architecture questions.
Set scope controls based on context:
- detail_level: minimal for executives, standard by default, detailed for deep dives
- audience: technical by default, executive if the user mentions stakeholders/leadership
- max_nodes: set to 10-12 for focused views, leave unset for overviews
- scope_filter: set when the user names specific services or phases
Build the shared model first, then define views. Follow the two-phase generation process in SKILL.md.
Save artifacts:
- Spec: docs/diagrams/specs/<date>-<topic>.diagram.json
- Diagram: docs/diagrams/<date>-<topic>.excalidraw
- Mermaid (optional): docs/diagrams/<date>-<topic>.mermaid.md

Run the full pipeline:

python <skill-dir>/references/build_excalidraw_diagram.py <spec> --output <diagram>
python <skill-dir>/references/validate_excalidraw.py <diagram>
python <skill-dir>/references/render_excalidraw.py <diagram>

Optionally export Mermaid when the user asks for text-friendly output:

python <skill-dir>/references/export_mermaid.py <spec> --output <mermaid-file>

Report results:
- List all generated artifact paths
- State the view mode used
- Note whether the diagram is codebase-accurate or conceptual
- Summarize evidence sources if discovery was performed

Read the full file on GitHub · 52 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.

12d ago First seen · 52 lines · 0 tokens per session scan A 9b033aaf6c3a

Subscribe to this mod's changes

diagram is a command published in the GitHub repository shahzadahmadv1/ExcaliClaude (3 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 550 tokens. 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.

Claude Code Design and UX architecture claude-code-skills claude-skills diagram excalidraw

icon-design

Find and select the right icon for a concept using Lucide, Heroicons, or Phosphor libraries.

citedy/skills · 21 tokens

profile

Coordinate a reproducible Java profiling and optimization lifecycle.

jabrena/plinth · 10 tokens

psql-query

Run ad-hoc PostgreSQL analytics queries against dev/test database.

oliver-kriska/claude-elixir-phoenix · 16 tokens

summary

Generate a consolidated project brief from design artifacts. For the full spec package with YAML specs and validation, use /compile instead.

clownware/product-dev · 27 tokens

resolve-review

Resolve reviewer feedback - from GitHub PRs, chat, or any reviewer.

sergeyklay/.agents · 15 tokens

implement.body

Every subagent invocation uses the delegation tool with the appropriate subagenttype (the implementation subagent, the tester subagent, or any specialized subagent the project ships). That tool is named Agent, in an interactive session and in the headless runtime alike. Do not look for a Task tool in your toolbox…

sergeyklay/.agents · 0 tokens