arch

A set of commands for examining and documenting how a software project is organized, including its components, dependencies, and design patterns.

In plain words
What is it for?
Use it to analyze architecture, create diagrams, plan structural changes, or review architecture decisions.
Why use it?
It helps you understand an unfamiliar codebase and identify or plan changes to its overall structure.

Command

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.

agentmods
npx agentmods add commands/data-wise/claude-plugins/arch
Clone the repo
git clone --depth 1 https://github.com/Data-Wise/claude-plugins
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 2,637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02637
Opus 5 $0.00000 $0.01319
Sonnet 5 $0.00000 $0.00527
Haiku 4.5 $0.00000 $0.00264

Measured yesterday against content hash 57956f7fc7a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arch 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • arch — 91% identical, 13 lines differ
craft/docs/commands/arch.md · 354 lines

How it starts

The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Commands

⏱️ 5 minutes • 🟡 Intermediate • ✓ System design and analysis

TL;DR (30 seconds)

  • What: 4 commands for analyzing, planning, reviewing, and diagramming software architecture
  • Why: Understand your codebase structure, identify patterns, and plan improvements with AI assistance
  • How: Use /craft:arch:analyze for analysis, /craft:arch:diagram for visual diagrams
  • Next: Try /craft:arch:analyze debug to see your project's architecture patterns

Craft's architecture commands help you understand, document, and improve your codebase structure with AI-powered analysis and visualization.


Commands Overview

Command Purpose Time (default)
/craft:arch:analyze Analyze architecture patterns < 15s
/craft:arch:diagram Generate architecture diagrams < 30s
/craft:arch:plan Plan architectural changes < 60s
/craft:arch:review Review architecture decisions < 120s

All commands support execution modes for different levels of detail.


/craft:arch:analyze - Architecture Analysis

Analyze codebase architecture, patterns, dependencies, and structure.

Quick Start

/craft:arch:analyze                 # Quick overview
/craft:arch:analyze debug           # Deep pattern analysis
/craft:arch:analyze optimize        # Performance architecture
/craft:arch:analyze release         # Full audit

Modes

Mode Time Focus
default < 15s Quick overview, basic structure
debug < 120s Deep dive, all patterns, anti-patterns
optimize < 180s Performance hotspots, import analysis
release < 300s Full architectural audit with metrics

Analysis Areas

The command examines:

  • Structure: Directory layout, module organization, separation of concerns
  • Dependencies: Import graphs, coupling metrics, circular dependencies
  • Patterns: MVC, microservices, layered architecture, design patterns
  • Data Flow: How data moves through the system
  • Complexity: Cyclomatic complexity, nesting depth, function sizes

Read the full file on GitHub · 354 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. yesterday First seen · 354 lines · 0 tokens per session scan A 57956f7fc7a0

Subscribe to this mod's changes

arch is a command published in the GitHub repository Data-Wise/claude-plugins (7 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,637 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.