arch-crusade

arch-crusade is a command for Claude Code from btachinardi/church. It costs 30 tokens per session (4,449 once invoked), scanned A, original, MIT.

A command that reviews a codebase's architecture, including its layers, imports, and dependencies between parts of the system.

In plain words
What is it for?
Use it for a full architecture audit, a specific domain such as orders or users, or selected backend and frontend directories. It can also document the current and planned structure.
Why use it?
It helps reveal circular dependencies, broken boundaries, and unwanted connections between domains before they make the code harder to change.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Part of the church plugin — 1 skill, 14 commands, 14 agents shipped together

Good fit Use it for a full architecture audit, a specific domain such as orders or users, or selected backend and frontend directories. It can also document the current and planned structure.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/btachinardi/church/arch-crusade
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/btachinardi/church

Made for: Claude Code.

Or install church, the plugin that ships this one along with the rest of its 1 skill, 14 commands, 14 agents.

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-crusade

README.md
[![agentmods](https://agentmods.dev/badge/commands/btachinardi/church/arch-crusade/github.svg)](https://agentmods.dev/commands/btachinardi/church/arch-crusade)
Your own site
<a href="https://agentmods.dev/commands/btachinardi/church/arch-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/arch-crusade/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-crusade

Your own site · 80×15
<a href="https://agentmods.dev/commands/btachinardi/church/arch-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/arch-crusade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,449 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 $0.04449
Opus 5 $0.00015 $0.02225
Sonnet 5 $0.00006 $0.00890
Haiku 4.5 $0.00003 $0.00445

Measured 11d ago against content hash d45709f445d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

arch-crusade 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 11d 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.

commands/arch-crusade.md · 589 lines

How it starts

The opening of the file, as written. The whole thing — 589 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Crusade

WAR CRY: "The Architecture Purists inspect every import, every boundary, every layer. Multiple squads deployed across all domain modules. The fortress will hold — or we will REBUILD it."

Command Overview

This slash command orchestrates a comprehensive architectural audit of the entire codebase using parallel Architecture Purist agents. It detects layer violations, circular dependencies, cross-domain coupling, and structural rot across all domains.

NEW CAPABILITY: The crusade can also generate comprehensive architecture documentation including domain catalogs, context maps, target state visions, and migration plans.

Usage

/arch-crusade [path] [--domain <name>] [--fix]

Arguments:

  • [path] — Optional. Root path to audit (defaults to current working directory)
  • --domain <name> — Optional. Audit specific domain only (e.g., "orders", "users")
  • --fix — Optional. Automatically apply fixes for auto-fixable violations

Examples:

/arch-crusade                                    # Full audit
/arch-crusade apps/api/src/domains               # Backend only
/arch-crusade --domain orders                    # Specific domain
/arch-crusade apps/api/src/domains/orders --fix  # Auto-fix violations
/arch-crusade --docs                             # Generate architecture docs
/arch-crusade --target-state                     # Design target architecture

Extended Modes:

  • --docs — Generate comprehensive architecture documentation (domains.md, context-map.md, etc.)
  • --target-state — Design target state architecture with ADRs and migration plans
  • --reconcile — Ensure all features are accounted for in architecture redesign
  • --scenarios — Validate architecture against real-world development scenarios

Mission Phases

Phase 1: Reconnaissance

Objective: Map the battlefield. Identify all domain modules, build the dependency graph, classify layers.

Actions:

  1. Use Glob to find all domain modules:
    • Backend: apps/api/src/domains/*/
    • Frontend: apps/web/src/domains/*/
  2. Use Glob to find all TypeScript files: **/*.ts, **/*.tsx
  3. Use Grep to extract all import statements across the codebase
  4. Classify each file by layer based on directory structure:
    • Files in */domain/ → Domain layer
    • Files in */application/ → Application layer
    • Files in */infrastructure/ → Infrastructure layer
    • Files in */presentation/ → Presentation layer
  5. Build import dependency graph (adjacency list)

Read the full file on GitHub · 589 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. 11d ago First seen · 589 lines · 0 tokens per session scan A d45709f445d6

Subscribe to this mod's changes

arch-crusade is a command published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 4,449 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.