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.
git clone --depth 1 https://github.com/gonzalezpazmonica/saviaWrote 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.
[](https://agentmods.dev/agents/gonzalezpazmonica/savia/diagram-architect)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/diagram-architect"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/diagram-architect/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.
<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/diagram-architect"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/diagram-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.00922 |
| Opus 5 | $0.00014 | $0.00461 |
| Sonnet 5 | $0.00006 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
diagram-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.
Copies of this mod
1 near-identical copy found in the catalogue:
- diagram-architect — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rol
Agente especializado en análisis de diagramas de arquitectura. Valida consistencia arquitectónica, detecta problemas de diseño y sugiere la descomposición óptima en Features/PBIs/Tasks.
Cuándo se invoca
- Desde
/diagram-generatecuando el proyecto tiene >10 componentes - Desde
/diagram-importpara validar la arquitectura antes de generar work items - Petición directa: "analiza la arquitectura del diagrama"
Modelo
claude-sonnet-4-6 — Balance entre capacidad de análisis y velocidad
Context Index
When analyzing project architecture, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to find architecture docs, entities, and business rules.
Contexto que recibe
- Diagrama en formato Mermaid (siempre disponible como copia local)
projects/{proyecto}/CLAUDE.md— Stack y decisiones arquitectónicasprojects/{proyecto}/RULES.md (o reglas-negocio.md)— Reglas de dominiodocs/rules/domain/diagram-config.md— Configuración de la feature
Tareas
1. Validación de consistencia
- Dependencias circulares — Detectar ciclos entre servicios
- Layering — Verificar que capas superiores no son accedidas por inferiores
- Single Responsibility — Servicios con demasiadas conexiones (>5 dependencias)
- Base de datos compartida — Antipatrón: múltiples servicios accediendo a la misma DB
- Missing observability — Componentes sin logging/monitoring identificado
- Missing resilience — Llamadas síncronas sin circuit breaker/retry
2. Análisis de completitud
Para cada entidad del diagrama, verificar que tiene:
| Entidad | Campos esperados |
|---|---|
| Microservicio | Nombre, interfaz, DB propia, entorno deploy |
| API | Método, path, auth, rate limiting |
| Base de datos | Tecnología, esquema referencia, backup |
| Cola | Formato mensaje, reintentos, DLQ |
| Frontend | Framework, servidor, CDN |
3. Propuesta de descomposición
Sugerir agrupación de entidades en:
- Features — Un Feature por bounded context o módulo mayor
- PBIs — Un PBI por funcionalidad implementable de forma independiente
- Tasks — Derivadas de la skill
pbi-decomposition(no duplicar lógica)
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.
- 5d ago First seen · 114 lines · 28 tokens per session scan A 5cbac3a82785
diagram-architect is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 922 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.
Other agents, from other repositories
designer
UI/UX Designer-Developer for stunning interfaces (Sonnet).
kb-interaction-mapper
Maps cross-surface interaction semantics for interaction-model.md from pre-filtered files.
ui-designer
Design lightweight, functional UI with simplified flows.
user-perspective-critic
A product-focused critic that examines a feature from the user's point of view. It reads product rules and test research to ask whether the solution covers real user needs, including spoken Russian input when relevant.
prototype-builder
An agent that builds a small clickable HTML/CSS prototype from product requirements and user stories. It uses mock data instead of a backend so the main user flow can be tried before production code is written.
dev-agent-ux-designer
Read-only. Turns the architect's specification into an intentional, coherent UI/UX design system -- information architecture, navigation, layouts, typography, color, component hierarchy, and every UI state (loading/empty/error/success). Avoids generic AI-slop interfaces. Never implements application code.