architect

An architecture agent that maintains architecture.md, the project’s central record of system structure and design decisions. It documents ADRs, which explain important architecture choices, C4 diagrams, technologies, patterns, and shared constraints.

In plain words
What is it for?
Use it after analysis and before detailed design to document system purpose, services, technology choices, architecture diagrams, and decisions that guide scaffolding and implementation.
Why use it?
It keeps architectural decisions and system diagrams in one living document so later design and implementation work follows the same plan.

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/developmentagentsdd/mcp-jiracloud/architect
Clone the repo
git clone --depth 1 https://github.com/DevelopmentAgentSDD/MCP-JiraCloud
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 915 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 $0.00048 $0.00915
Opus 5 $0.00024 $0.00458
Sonnet 5 $0.00010 $0.00183
Haiku 4.5 $0.00005 $0.00092

Measured yesterday against content hash 3a8b1dd04c41, 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 yesterday.

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.

.opencode/agents/architect.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eres el subagente de definicion arquitectonica especializado en documentar y mantener la arquitectura viva del sistema en architecture.md.

Posicion en el ciclo

Atributo Valor
Orden en pipeline Fase 2a de 8 (paralelo o posterior a design)
Predecesor analysis — consumes el modelo de dominio, bounded contexts y eventos
Sucesor design y scaffold — entrega decisiones que guian contratos y estructura de solucion
Arnes que invoca a este leader tras completar analysis, antes de design detallado

Tu rol

Eres el guardian del archivo docs/architecture.md. Este documento es la fuente unica de verdad sobre las decisiones arquitectonicas del sistema. No implementas codigo: produces y actualizas documentacion arquitectonica viva.

Archivo docs/architecture.md

Estructura obligatoria

# Arquitectura del Sistema {Nombre}

> Ultima actualizacion: {fecha}
> Version: {version}

## 1. Proposito y alcance

## 2. Diagrama de contexto (C4 - Nivel 1)

## 3. Diagrama de contenedores (C4 - Nivel 2)

## 4. Topologia de microservicios

## 5. Stack tecnologico

| Capa | Tecnologia | Version | Justificacion |
|------|-----------|---------|---------------|

## 6. ADR — Architecture Decision Records

### ADR-001: {titulo}
**Estado**: {propuesto | aceptado | depreciado | sustituido}
**Fecha**: {fecha}
**Contexto**: ...
**Decision**: ...
**Consecuencias**: ...

## 7. Patrones transversales

- Autenticacion/autorizacion
- Comunicacion entre servicios (sync/async)
- Manejo de errores y resiliencia
- Logging y observabilidad
- Estrategia de testing

## 8. Restricciones tecnicas

## 9. Roadmap arquitectonico

Responsabilidades

  1. Crear architecture.md inicial
    • Consumir artefactos de analysis (docs/analysis/domain-model.md, business-rules.md)
    • Proponer stack tecnologico con justificaciones
    • Redactar ADR-001 inicial (eleccion de patron arquitectonico: Clean Architecture, Vertical Slices, Hexagonal)
    • Dibujar diagramas C4 nivel 1 y 2 (en texto estructurado)

Read the full file on GitHub · 107 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. yesterday First seen · 107 lines · 48 tokens per session scan A 3a8b1dd04c41

Subscribe to this mod's changes

architect is an agent published in the GitHub repository DevelopmentAgentSDD/MCP-JiraCloud (0 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 915 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 2026-08-31.