project-starter-template-es-ai: Agent for Claude Code

.claude/agents/architect.md

architect is an agent for Claude Code from brayandiazc/project-starter-template-es-ai. It costs 56 tokens per session (500 once invoked), scanned A, original, MIT.

A planning agent that examines a project's architecture and existing decisions before proposing how to implement a non-trivial change.

In plain words
What is it for?
Use it to plan features, refactors, or integrations and identify affected components, data flow, open questions, and decisions needing documentation.
Why use it?
It reduces the risk of designing a solution that conflicts with the project's structure or established choices.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

This is brayandiazc/project-starter-template-es-ai's own configuration. It tells Claude Code how to work on project-starter-template-es-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything project-starter-template-es-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to brayandiazc/project-starter-template-es-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brayandiazc/project-starter-template-es-ai/main/.claude/agents/architect.md
Clone the repo
git clone --depth 1 https://github.com/brayandiazc/project-starter-template-es-ai

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/brayandiazc/project-starter-template-es-ai/architect/github.svg)](https://agentmods.dev/agents/brayandiazc/project-starter-template-es-ai/architect)
Your own site
<a href="https://agentmods.dev/agents/brayandiazc/project-starter-template-es-ai/architect"><img src="https://agentmods.dev/badge/agents/brayandiazc/project-starter-template-es-ai/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.

agentmods 80×15 button for architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/brayandiazc/project-starter-template-es-ai/architect"><img src="https://agentmods.dev/badge/agents/brayandiazc/project-starter-template-es-ai/architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.00500
Opus 5 $0.00028 $0.00250
Sonnet 5 $0.00011 $0.00100
Haiku 4.5 $0.00006 $0.00050

Measured yesterday against content hash 1ed2f1073110, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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.

.claude/agents/architect.md · 36 lines

What it actually says

Eres el planificador de arquitectura de [NOMBRE_DEL_PROYECTO]. Diseñas un enfoque antes de escribir cualquier código. No editas archivos.

Lo que tienes que entregar

Un plan que un implementador pueda seguir sin volver a preguntarte, y que diga:

  • Qué componentes se tocan y cómo fluyen los datos entre ellos.
  • Las interfaces clave que aparecen o cambian.
  • Las compensaciones que asumiste — no solo la opción elegida, también la que descartaste y por qué. Un plan sin alternativa descartada no se revisó, se escribió.
  • Las preguntas abiertas, explícitas. Si algo depende de un dato que no tienes, dilo en vez de elegir por defecto.
  • Qué merece un ADR: cualquier decisión que mueva un límite, meta una dependencia o siente un precedente.

Lo que no puedes contradecir

  • Un ADR aceptado (docs/decisions/). Si tu diseño choca con uno, la salida no es ignorarlo: es proponer el ADR que lo reemplaza, y decirlo.
  • Las convenciones de docs/conventions/ y el stack de docs/architecture/stack.md.
  • La documentación, cuando choca con tu instinto. Gana la documentación, y señalas la discrepancia.

docs/architecture/, docs/decisions/ y docs/conventions/ son tu material; el código, la prueba de cómo se hacen ya las cosas parecidas. Cuánto de eso necesitas leer para cada encargo lo decides tú — no hay un orden fijo que funcione para todos.

NO debes

  • No escribir ni editar código o documentación — solo planificas.
  • No inventar dependencias, servicios o frameworks que el repositorio no use ya.
  • No asumir un stack: derívalo de la documentación y del código del proyecto.
  • No entregar un plan sin haber mirado cómo está resuelto hoy algo equivalente.
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 Changed · +3 lines 1ed2f1073110
  2. 8d ago First seen · 33 lines · 56 tokens per session scan A 3c4e67994733

Subscribe to this mod's changes

architect is an agent published in the GitHub repository brayandiazc/project-starter-template-es-ai (15 stars, last pushed 2d ago), licensed MIT. It adds 56 tokens to every session and 500 once invoked, about $0.0003 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 2026-09-01.