What is arch-suggest?

An architecture analysis command that turns detected design-rule violations into prioritized improvement suggestions. Software architecture is the high-level structure of a project and how its parts fit together.

Use it to review architecture violations and find refactoring opportunities in a repository or local project path.

It removes the need to turn a raw architecture scan into an ordered list of concrete fixes by identifying affected files, severity, and possible solutions.

arch-suggest — Command for Claude Code by gonzalezpazmonica

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/gonzalezpazmonica/savia

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/arch-suggest/github.svg)](https://agentmods.dev/commands/gonzalezpazmonica/savia/arch-suggest)

Your own site

<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/arch-suggest"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/arch-suggest/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/arch-suggest"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/arch-suggest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 867 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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.00867
Opus 5	$0.00008	$0.00434
Sonnet 5	$0.00003	$0.00173
Haiku 4.5	$0.00002	$0.00087

Measured 6d ago against content hash edbac89b83d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

arch-suggest 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

arch-suggest — 100% identical, 0 lines differ

.claude/commands/arch-suggest.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/arch-suggest {repo|path}

Analiza un proyecto y genera sugerencias priorizadas de mejora arquitectónica.

Prerequisitos

Ejecutar /arch-detect primero (o se ejecutará automáticamente)
Acceso al repositorio

2. Cargar perfil de usuario

Leer .claude/profiles/active-user.md → obtener active_slug
Si hay perfil activo, cargar (grupo Architecture & Debt del context-map):
- profiles/users/{slug}/identity.md
- profiles/users/{slug}/projects.md
- profiles/users/{slug}/preferences.md
Adaptar profundidad del análisis según preferences.detail_level
Si no hay perfil → continuar con comportamiento por defecto

3. Parámetros

{repo|path} — Ruta local o nombre del repositorio

4. Flujo de Ejecución

1. Cargar detección previa

Si existe output/architecture/{proyecto}-detection.md, leerlo. Si no existe, ejecutar /arch-detect primero.

2. Analizar violaciones

Para cada violación del reporte de detección:

Clasificar severidad: CRITICAL (rompe el patrón) vs WARNING (desvío menor)
Identificar ficheros afectados
Proponer solución concreta con ejemplo

3. Identificar oportunidades de refactoring

Buscar:

God classes/modules: ficheros >300 líneas con múltiples responsabilidades
Dependencias inversas: módulos de bajo nivel usados por alto nivel
Código duplicado: patrones repetidos que deberían ser abstracciones
Missing abstractions: implementaciones directas sin interfaces/traits
Tight coupling: clases que instancian dependencias (new) en lugar de recibirlas

4. Priorizar por impacto × esfuerzo

Matriz de priorización:

	Esfuerzo Bajo	Esfuerzo Alto
Impacto Alto	🟢 Quick Win	🟡 Proyecto
Impacto Bajo	🔵 Nice to have	⚪ Postpone

5. Generar Reporte

# 🔍 Architecture Suggestions — {proyecto}

**Patrón Detectado**: {nombre} ({score}%)
**Fecha**: {fecha}

## 🟢 Quick Wins (alto impacto, bajo esfuerzo)
1. **{título}** — {descripción}
   - Ficheros: {lista}
   - Acción: {qué hacer}
   - Ejemplo: {antes → después}

## 🟡 Proyectos (alto impacto, alto esfuerzo)
1. **{título}** — {descripción}
   - Estimación: {horas}
   - Beneficio: {qué mejora}

## 🔵 Nice to Have
1. **{título}** — {descripción}

## ⚠️ Violaciones Críticas a Resolver
1. **{violación}**
   - Severidad: CRITICAL
   - Impacto: {qué rompe}
   - Solución: {cómo arreglarlo}

## 📊 Métricas de Salud Arquitectónica
| Métrica | Valor | Target |
|---------|-------|--------|
| Adherencia al patrón | {n}% | >80% |
| Dependencias inversas | {n} | 0 |
| Ficheros >300 líneas | {n} | 0 |
| Coupling index | {n} | <0.3 |

Read the full file on GitHub · 111 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.

6d ago First seen · 111 lines · 16 tokens per session scan A edbac89b83d5

Subscribe to this mod's changes

arch-suggest is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 867 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 2026-09-06.

Claude Code Code review Planning codex harness opencode

arch-suggest