Agent Configuration Architect

Agent Configuration Architect is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 24 tokens per session (1,569 once invoked), scanned A, original, MIT.

A guide for configuring AI agents through reusable templates, business-specific overrides, tools, models, prompts, and initial data.

In plain words
What is it for?
Use it to define role-based agent templates, set model choices, customize business behavior, and specify how tools should be used.
Why use it?
It organizes the different layers of an agent's configuration so general behavior, customer rules, and tool instructions can be combined.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define role-based agent templates, set model choices, customize business behavior, and specify how tools should be used.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-configuration-architect
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.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-configuration-architect
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

Made for: Claude Code, Codex.

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 Agent Configuration Architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-configuration-architect/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-configuration-architect)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-configuration-architect"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-configuration-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 Agent Configuration Architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-configuration-architect"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-configuration-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,569 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00024 $0.01569
Opus 5 $0.00012 $0.00785
Sonnet 5 $0.00005 $0.00314
Haiku 4.5 $0.00002 $0.00157

Measured 9d ago against content hash ca968b7fd24d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Agent Configuration 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 9d 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.

skills/agent/agent-configuration-architect/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Configuration Architect - Platform AI Solutions (v7.1.2)

1. Concepto: La Arquitectura de Agentes Nexus

Filosofía Multi-Capa

Nexus no usa un único system prompt estático. Utiliza una arquitectura de 3 capas para construir la inteligencia del agente en runtime:

  1. Capa 1: Template Base (Polimorfismo): Definida en agent_service/app/core/agent_templates.py. Provee la estructura de identidad y reglas core según el rol (Sales, Support, Leads, Logistics).
  2. Capa 2: Wizard Overrides (Identidad de Negocio): Datos específicos del cliente (Tono, Reglas de Negocio, Diccionario de Sinónimos) que sobreescriben los valores del template.
  3. Capa 3: Instrucciones de Tools (Táctica de Ejecución): Instrucciones detalladas sobre CÓMO usar cada herramienta y CÓMO formatear la respuesta, inyectadas dinámicamente.

2. Configuración de Templates (Wizard Defaults)

Los valores predeterminados para el Wizard se definen en orchestrator_service/app/api/agents.pyAGENT_TEMPLATES.

Ejemplo: Sales Agent (Pointe Coach inspired)

AGENT_TEMPLATES = {
    "sales": {
        "agent_name": "Agente de Ventas (IA)",
        "model_provider": "openai",
        "model_version": "gpt-4o",
        "temperature": 0.7,
        "defaultValue": {
            "agent_tone": "Sos una asesora experta en danza clásica... usamos voseo argentino...",
            "synonym_dictionary": "mallas: Leotardos\ncancanes: Medias...",
            "business_rules": "1. Prioridad: Venta asistida...\n2. Fitting: Ofrecer siempre para puntas...",
            "catalog_knowledge": "Categorías: Zapatillas, Medias, Leotardos, Accesorios.",
            "store_website": "https://pointecoach.com"
        }
    }
}

3. Dynamic Global Templates (v7.2+)

Nexus ahora soporta Templates Dinámicos almacenados en la base de datos. Esto permite crear plantillas que aparecen automáticamente en el Wizard de todos los inquilinos.

Lógica de Visibilidad

El endpoint /admin/agent-templates mezcla los templates hardcoded con los de la base de datos siguiendo esta lógica:

  • is_template = TRUE: El registro es tratado como una plantilla, no como un agente vivo.
  • tenant_id IS NULL: Template Global. Visible para todas las cuentas del sistema.
  • tenant_id = X: Template Privado. Visible solo para el inquilino X.

Read the full file on GitHub · 120 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 120 lines · 24 tokens per session scan A ca968b7fd24d

Subscribe to this mod's changes

Agent Configuration Architect is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,569 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 2026-09-03.