agentmods.dev

arch-diagram

arch-diagram is a skill for Claude Code, Codex from JansenAnalytics/claudex. It costs 21 tokens per session (452 once invoked), scanned A, original, MIT.

A tool that turns a codebase's components and dependencies into architecture diagrams. It can produce Mermaid, PlantUML, or plain-text diagrams.

In plain words
What is it for?
Extract dependencies from package files or imports, create diagrams for documentation or pull requests, and map components or sequences.
Why use it?
It makes relationships between parts of a software project easier to understand and document.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/dep-graph.sh --path /path/to/project --type node.

not rated 5repo 4mo ago A scan 21 tokens original MIT

Good fit Extract dependencies from package files or imports, create diagrams for documentation or pull requests, and map components or sequences.

Compare 6 skills from other repositories ↓
View source ↗ JansenAnalytics/claudex
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/JansenAnalytics/claudex
agentmods
npx agentmods add skills/jansenanalytics/claudex/arch-diagram

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 arch-diagram

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jansenanalytics/claudex/arch-diagram"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/arch-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 452 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 $0.00021 $0.00452
Opus 5.5 $0.00008 $0.00181
Sonnet 5.5 $0.00004 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured 2mo ago against content hash 747c9f63d4bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arch-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 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/arch-diagram/SKILL.md · 60 lines

What it actually says

arch-diagram

Generate architecture diagrams from codebase analysis: Mermaid, PlantUML, or ASCII.

When to Use

  • Visualizing system architecture
  • Documenting component relationships
  • Creating sequence diagrams
  • Mapping dependencies from package.json or imports
  • Generating diagrams for documentation or PRs

How It Works

  1. Point dep-graph.sh at a project to extract dependencies
  2. Use mermaid-gen.sh to produce Mermaid diagram syntax
  3. Use ascii-diagram.sh for quick terminal-friendly box diagrams
  4. Consult references for syntax help and diagram type selection

Scripts

Script Purpose
dep-graph.sh Extract dependency graph from package.json or import statements
mermaid-gen.sh Generate Mermaid diagram markup from components/relationships
ascii-diagram.sh Generate ASCII box-and-arrow diagrams

References

File Content
mermaid-syntax.md Mermaid diagram syntax quick reference
plantuml-syntax.md PlantUML syntax quick reference
diagram-selection.md Guide for choosing the right diagram type

Example Usage

# Extract deps from a Node.js project
bash scripts/dep-graph.sh --path /path/to/project --type node

# Generate a Mermaid flowchart
bash scripts/mermaid-gen.sh --type flowchart \
  --components "API,Database,Cache,Queue" \
  --relations "API->Database,API->Cache,API->Queue"

# Quick ASCII diagram
bash scripts/ascii-diagram.sh \
  --components "Client,API Gateway,Auth Service,DB" \
  --relations "Client->API Gateway,API Gateway->Auth Service,Auth Service->DB"
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. 2mo ago First seen · 60 lines · 21 tokens per session scan A 747c9f63d4bb

Subscribe to this mod's changes

arch-diagram is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 452 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 2026-08-31.

Design and UXarchitectureascii-diagramdependency-graphdevelopmentmermaidplantuml
Related

arch-diagram compared with skills from other repositories

arch-diagram next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
arch-diagramJansenAnalytics/claudexSkill54mo agoMITA21Claude Code, Codex
diagram-creatorclaude-office-skills/skillsSkill5689mo agoMITA34Claude Code, Codex
code-quality-principlesathola/claude-night-marketSkill348todayMITA38Claude Code
mk:previewngocsangyem/MeowKitSkill157d agoMITA92Claude Code
tech-diagramdesirecore/marketSkill2todayMITA210Claude Code
code-to-diagramserejaris/kimi-skillsSkill113mo agoMITA74Claude Code, Codex
mermaid-diagramswpank/aiSkill129mo agononeA77Claude Code, Codex