import-architecture

import-architecture is a command for Claude Code from AhmedHabiba/architor. It costs 0 tokens per session (1,642 once invoked), scanned A, original, MIT.

A command for reviewing an existing architecture document, which describes how a software system is organised. It imports the document into a staged review process covering requirements, patterns, and components.

In plain words
What is it for?
Use it to import an architecture document, review its sections, identify gaps and anti-patterns, and accept or refine each stage.
Why use it?
It helps expose missing requirements, outdated decisions, non-functional needs such as performance or security, and design problems before the architecture is accepted.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to import an architecture document, review its sections, identify gaps and anti-patterns, and accept or refine each stage.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ahmedhabiba/architor/import-architecture
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/AhmedHabiba/architor

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.

agentmods badge for import-architecture

README.md
[![agentmods](https://agentmods.dev/badge/commands/ahmedhabiba/architor/import-architecture/github.svg)](https://agentmods.dev/commands/ahmedhabiba/architor/import-architecture)
Your own site
<a href="https://agentmods.dev/commands/ahmedhabiba/architor/import-architecture"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/import-architecture/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 import-architecture

Your own site · 80×15
<a href="https://agentmods.dev/commands/ahmedhabiba/architor/import-architecture"><img src="https://agentmods.dev/badge/commands/ahmedhabiba/architor/import-architecture.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 1,642 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 $0.00000 $0.01642
Opus 5 $0.00000 $0.00821
Sonnet 5 $0.00000 $0.00328
Haiku 4.5 $0.00000 $0.00164

Measured 10d ago against content hash f4a26be07298, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

import-architecture 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 10d 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.

templates/claude/commands/import-architecture.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read .arch/state.json first.

GATE CHECK:

  • If current_phase is not not_started, STOP: "Cannot import architecture. Current phase is [phase]. Import is only available at the start of a new project. Use /status to check progress."
  • If .arch/existing-architecture.md does not exist, STOP: "No import document found. Run arch-agent import <source-file> from CLI first, then use this command."

Read .arch/existing-architecture.md — this is the existing architecture document to import. Read .arch/org-context.md to check if organizational context is available.

Import Mode — Fast-Track Review

You are importing an existing architecture document. Your job is to:

  1. Parse the document into architecture sections
  2. Present each section for review, applying your adversarial reviewer standards
  3. Progress through all phases using the normal state machine
  4. Challenge — flag gaps, outdated decisions, missing NFRs, and anti-patterns

The user can /accept phases they're happy with quickly, or /refine phases that need updates.


Step 1: Parse the Document

Analyze the imported document and identify these sections (some may be missing):

  • Requirements / PRD content — functional requirements, NFRs, constraints, assumptions
  • Architecture pattern — monolith, microservices, event-driven, etc.
  • Component map — system components and their boundaries
  • Cross-cutting decisions — auth, observability, deployment, error handling, data management
  • Component designs — detailed designs for individual components

If sections are missing, note them — you'll flag these as gaps in the appropriate phase.

Step 2: Phase 1 — Evaluate as PRD Analysis

Present the extracted requirements as a Phase 1 evaluation:

  • Extract functional requirements (FR-001, FR-002...) from the document
  • Extract or infer non-functional requirements
  • Identify gaps — what's missing from the existing design?
  • Rate risks and overall design completeness
  • Be adversarial: "Your existing document says [X], but doesn't address [Y]. What happens when [Z]?"

Read the full file on GitHub · 140 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. 10d ago First seen · 140 lines · 0 tokens per session scan A f4a26be07298

Subscribe to this mod's changes

import-architecture is a command published in the GitHub repository AhmedHabiba/architor (6 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,642 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.