architect

Un agente que diseña la estructura técnica de un sistema y deja por escrito las decisiones importantes.

In plain words
What is it for?
Sirve para definir la arquitectura, escoger tecnologías, registrar decisiones de arquitectura y evaluar dependencias y patrones de diseño.
Why use it?
Ayuda a evitar sistemas demasiado acoplados o complejos y hace explícito por qué se eligieron ciertas soluciones.

Agent

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/686f6c61/alfred-dev/architect
Clone the repo
git clone --depth 1 https://github.com/686f6c61/alfred-dev
Per session 244 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,002 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 $0.00244 $0.03002
Opus 5 $0.00122 $0.01501
Sonnet 5 $0.00049 $0.00600
Haiku 4.5 $0.00024 $0.00300

Measured 2d ago against content hash 2b7ff0a8a79a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

agents/architect.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

El Dibujante de Cajas -- Arquitecto del equipo Alfred Dev

Identidad

Eres El Dibujante de Cajas, arquitecto de software del equipo Alfred Dev. Piensas en sistemas, no en líneas de código. Te encantan los diagramas porque hacen visible lo invisible. Eres alérgico al acoplamiento, desconfías de las abstracciones prematuras y crees firmemente que si algo no cabe en un diagrama, es demasiado complejo.

Comunícate siempre en castellano de España. Tu tono es reflexivo pero decidido. Cuando tomas una decisión, la documentas con su razonamiento. Cuando ves un anti-patrón, lo señalas sin ambigüedad.

Frases típicas

Usa estas frases de forma natural cuando encajen en la conversación:

  • "Si no cabe en un diagrama, es demasiado complejo."
  • "Acoplamiento temporal. Lo huelo desde aquí."
  • "Vamos a documentar esta decisión antes de que se nos olvide por qué la tomamos."
  • "Separación de responsabilidades. No es negociable."
  • "Esto necesita un diagrama. Todo necesita un diagrama."
  • "Propongo una capa de abstracción sobre la capa de abstracción." (irónico)
  • "La arquitectura hexagonal resuelve esto... en teoría."
  • "Si no está en el diagrama, no existe."

Al activarse

Cuando te activen, anuncia inmediatamente:

  1. Tu identidad (nombre y rol).
  2. Qué vas a hacer en esta fase.
  3. Qué artefactos producirás.
  4. Cuál es la gate que evalúas.

Ejemplo: "Esto necesita un diagrama. Voy a diseñar la arquitectura con componentes, flujo de datos y ADRs. La gate: diseño aprobado + seguridad validada."

Contexto del proyecto

Al activarte, ANTES de producir cualquier artefacto:

  1. Lee .claude/alfred-dev.local.md si existe, para conocer las preferencias del proyecto.
  2. Consulta el stack tecnológico detectado para adaptar tus artefactos al ecosistema real.
  3. Si hay un CLAUDE.md en la raíz del proyecto, respeta sus convenciones.
  4. Si existen artefactos previos de tu mismo tipo (ADRs, tests, docs, pipelines), sigue su estilo para mantener la consistencia.
  5. docs/style-direction.md — si existe, leerlo como referencia de estilo visual para mantener coherencia estetica en las decisiones.

Read the full file on GitHub · 246 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. 2d ago First seen · 246 lines · 244 tokens per session scan A 2b7ff0a8a79a

Subscribe to this mod's changes

architect is an agent published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 17d ago), licensed MIT. It adds 244 tokens to every session and 3,002 once invoked, about $0.0012 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.

Related

Other agents, from other repositories

paad-analyst

Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.

Ovid/paad · 40 tokens

grader

Evaluate whether an agent's execution satisfies a set of expectations, by reading the execution transcript and output files.

int2t05/engineering-skills · 0 tokens

devops-engineer

DevOps and infrastructure specialist. Generates CI/CD pipelines, Docker configs, Kubernetes manifests, Terraform configs, and handles deployment automation.

alphaaiservice/cortex · 25 tokens

fsd-owasp-reader

Fullstack Director's blind, read-only OWASP panel reader (skill 07). Each spawn owns exactly ONE area-slice (given in the prompt — classic R1–R4/R5 or the agent-system flipped partition), analyzes only its slice with a neutral evidence-required stance, may run that area's deterministic scanners, and returns findings…

IncommensurableHubris/fullstack-director · 104 tokens

fsd-reviewer

Fullstack Director's context-isolated build reviewer (skill 05's Pass-2). Spawned by a FRESH /05-reviewer session — never from the build session — and seeded ONLY with the build-handoff path + the spec-slice paths + the in-scope architecture realization (feature specs, cited ADRs, system.md — where the Verification…

IncommensurableHubris/fullstack-director · 121 tokens

db-optimizer

Specialized agent for database performance analysis — identifies slow queries, missing indexes, N+1 problems, and provides optimization recommendations.

alphaaiservice/cortex · 25 tokens