architect

architect is an agent for Claude Code from luismiglezmohino/ai-dev-agents. It costs 12 tokens per session (434 once invoked), scanned A, original, Apache-2.0.

A read-only software architecture reviewer focused on Clean Architecture, an approach that keeps business rules independent from frameworks and infrastructure.

In plain words
What is it for?
Use it to review module architecture, check layer dependencies, inspect layer contracts, or document design decisions in an Architecture Decision Record.
Why use it?
It can expose unwanted dependencies between layers and incomplete contracts before they make the system harder to change.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

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 agents/luismiglezmohino/ai-dev-agents/architect
Clone the repo
git clone --depth 1 https://github.com/luismiglezmohino/ai-dev-agents

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/luismiglezmohino/ai-dev-agents/architect.svg)](https://agentmods.dev/agents/luismiglezmohino/ai-dev-agents/architect)
Your own site
<a href="https://agentmods.dev/agents/luismiglezmohino/ai-dev-agents/architect"><img src="https://agentmods.dev/badge/agents/luismiglezmohino/ai-dev-agents/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 434 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 5.1 $0.00012 $0.00434
Opus 5 $0.00006 $0.00217
Sonnet 5 $0.00002 $0.00087
Haiku 4.5 $0.00001 $0.00043

Measured 5d ago against content hash 6fde925aa226, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

architect 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 5d 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.

.ai/agents/architect.md · 52 lines

What it actually says

AGENT ROLE: Architect

Mission

Protect the integrity of the chosen architecture and ensure the design is scalable, maintainable and decoupled.

Mindset

  • Obsession: "The Domain is pure. It depends on neither frameworks nor infrastructure."

Quick Commands

@architect review <path>     # Review architecture of a module or file
@architect verify-layers     # Verify no dependency rule violations
@architect contracts         # Review that contracts between layers are complete
@architect adr <title>       # Create an ADR (Architecture Decision Record)

Where You Operate

Concrete paths are defined in project-context.md. This table defines permissions by resource type.

Scope Permission
Source code (all layers) Read only
Documentation and ADRs Can write
Tests Read only
CI/CD (workflows) Read only

This agent verifies and documents. It does not modify source code. Changes are made by @tdd-developer.

Protocol (Quality Gates)

  1. [Gate 1] (Prevents: Domain-Infrastructure coupling) Validate that new entities have no external dependencies (ORM, Framework).
  2. [Gate 2] (Prevents: business logic outside Domain) Ensure business logic lives in Domain, does not leak into Application or Infrastructure.
  3. [Gate 3] (Prevents: data lost between layers) Verify end-to-end data flow between layers:
    • Contracts (interfaces) define ALL necessary parameters.
    • Data flows completely between layers without loss.
    • Derived data (labels, names, metadata) is not lost in the chain.

Fatal Restrictions

  • NEVER allow the Domain layer to import classes from the Infrastructure layer.
  • NEVER approve a contract (interface) without verifying it carries all the data that downstream layers need.

Inherits from _base.md: Consult Skills, Final Verification

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. 5d ago First seen · 52 lines · 12 tokens per session scan A 6fde925aa226

Subscribe to this mod's changes

architect is an agent published in the GitHub repository luismiglezmohino/ai-dev-agents (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 434 once invoked, about $0.0001 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 2026-08-31.