architecture-diagram

architecture-diagram is a skill for Claude Code, Codex from saajunaid/caddis-plugin. It costs 31 tokens per session (1,605 once invoked), scanned A, original, MIT.

A tool for creating dark-themed technical architecture diagrams as standalone HTML and SVG files. It can show software systems, cloud infrastructure, microservices, and deployments in a browser.

In plain words
What is it for?
Use it to document system architecture, cloud setups, microservice connections, and deployment layouts.
Why use it?
It removes the need for external diagram libraries or rendering tools when you need to explain how a system is built and deployed.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: built for hermes-agent.

Good fit Use it to document system architecture, cloud setups, microservice connections, and deployment layouts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saajunaid/caddis-plugin/architecture-diagram
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 architecture-diagram
Clone the repo
git clone --depth 1 https://github.com/saajunaid/caddis-plugin

Made for: Claude Code, Codex.

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 architecture-diagram

README.md
[![agentmods](https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/architecture-diagram/github.svg)](https://agentmods.dev/skills/saajunaid/caddis-plugin/architecture-diagram)
Your own site
<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/architecture-diagram"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/architecture-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.

agentmods 80×15 button for architecture-diagram

Your own site · 80×15
<a href="https://agentmods.dev/skills/saajunaid/caddis-plugin/architecture-diagram"><img src="https://agentmods.dev/badge/skills/saajunaid/caddis-plugin/architecture-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,605 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 $0.00031 $0.01605
Opus 5.5 $0.00012 $0.00642
Sonnet 5.5 $0.00006 $0.00321
Haiku 4.5 $0.00003 $0.00161

Measured 19d ago against content hash 3367a54de23f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

architecture-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 19d 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.

.github/skills/media/architecture-diagram/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Diagram

Generate professional dark-themed architecture diagrams as standalone HTML files with embedded SVG. Browser-only — no Graphviz, no Mermaid renderer, no server required.

Not suitable for: scientific subjects, physical objects, floor plans, hand-drawn aesthetics — use excalidraw or draw-io for those.

When to Use

Load this skill when users ask for:

  • System architecture or component diagrams
  • Cloud infrastructure diagrams (AWS/Azure/GCP)
  • Microservice topology maps
  • API and database relationship diagrams
  • Deployment diagrams

Complements architecture-design (planning/notation) — use that first, then use this skill to produce the rendered output artifact.

Semantic Color System

Map every component to a type, then apply these colors consistently:

Component Type Stroke Fill
Frontend #22d3ee rgba(8, 51, 68, 0.4)
Backend / Service #34d399 rgba(6, 78, 59, 0.4)
Database #a78bfa rgba(76, 29, 149, 0.4)
Cloud / AWS #fbbf24 rgba(120, 53, 15, 0.3)
Security / Auth #fb7185 rgba(136, 19, 55, 0.4)
Message Bus / Queue #fb923c rgba(251, 146, 60, 0.3)
External / Third-party #94a3b8 rgba(30, 41, 59, 0.5)

Canvas & Typography

  • Background: #020617 (slate-950) with a 40px grid pattern using rgba(148, 163, 184, 0.05) lines
  • Font: JetBrains Mono from Google Fonts (wght@400;500;700)
    • Component labels: 12px weight 500
    • Section/group titles: 14px weight 700
    • Annotations: 7–9px weight 400
  • Stroke width: 1.5px on all component boxes

SVG Structure Rules

Render Order (critical)

Render in this exact sequence to avoid transparency bleed-through:

  1. Background + grid
  2. Region/security boundary containers (dashed)
  3. Connection arrows ← must come before components
  4. Component boxes
  5. Component labels
  6. Legend

Double-Rect Masking (required for all component boxes)

Prevents arrow lines from showing through filled shapes:

<!-- 1. opaque background rect (clips arrow lines) -->
<rect x="X" y="Y" width="W" height="H" rx="6"
      fill="#020617" stroke="none"/>
<!-- 2. semi-transparent styled rect on top -->
<rect x="X" y="Y" width="W" height="H" rx="6"
      fill="FILL_COLOR" stroke="STROKE_COLOR" stroke-width="1.5"/>
<!-- 3. label -->
<text x="X+W/2" y="Y+H/2+4" text-anchor="middle"
      font-family="JetBrains Mono" font-size="12" font-weight="500"
      fill="STROKE_COLOR">Component Name</text>

Read the full file on GitHub · 157 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.

  1. 19d ago Changed · -17 tokens per session 3367a54de23f
  2. 1mo ago First seen · 157 lines · 48 tokens per session scan A e35f89796e1a

Subscribe to this mod's changes

architecture-diagram is a skill published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 1,605 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.