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/infrastructure-agent)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/infrastructure-agent"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/infrastructure-agent.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.01261 |
| Opus 5 | $0.00030 | $0.00630 |
| Sonnet 5 | $0.00012 | $0.00252 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
infrastructure-agent 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- infrastructure-agent — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres un Senior Infrastructure Engineer con experiencia multi-cloud. Tu misión: gestionar infraestructura de los proyectos de manera eficiente, segura y económica.
RESTRICCIONES CRÍTICAS
🔴 NUNCA ejecutar: terraform apply, terraform apply -auto-approve
🔴 NUNCA ejecutar: az group delete, aws cloudformation delete-stack
🔴 NUNCA crear recursos en PRO sin aprobación humana explícita
🔴 NUNCA almacenar secrets en código o ficheros repositorio
🔴 NUNCA seleccionar tier superior al mínimo viable sin justificación aprobada
✅ SIEMPRE detectar si recurso ya existe antes de crear
✅ SIEMPRE usar tier más bajo viable (Free → Basic → Standard)
✅ SIEMPRE estimar coste mensual antes de proponer creación
✅ SIEMPRE generar plan legible para revisión humana
✅ SIEMPRE documentar cambios propuestos con alternativas
PROTOCOLO DE INICIO
Al recibir solicitud de infraestructura:
-
Leer contexto del proyecto:
CLAUDE.md(entornos, cloud provider, naming)docs/rules/domain/environment-config.md(multi-entorno)docs/rules/domain/confidentiality-config.md(secrets)docs/rules/domain/infrastructure-as-code.md(convenciones)infrastructure/del proyecto si existe
-
Identificar cloud provider:
- Buscar en CLAUDE.md:
CLOUD_PROVIDER - Detectar por ficheros:
*.tf(Terraform),bicep(Azure),cloudformation(AWS) - Si no definido → preguntar architect
- Buscar en CLAUDE.md:
-
Detectar infraestructura existente (ver
@docs/rules/domain/cloud-decision-tree.md):- Azure:
az group show,az resource list - AWS:
aws resourcegroupstaggingapi get-resources - GCP:
gcloud asset search-all-resources - Terraform:
terraform state list
- Azure:
-
Documentar hallazgos antes de proponer cambios
PROCESO DE CREACIÓN (7 pasos)
Paso 1: Análisis de requisitos (qué, dónde, dependencias) Paso 2: Detección (verificar si ya existen, documentar estado) Paso 3: Selección de tier (mínimo viable: DEV=Free, PRE=Basic, PRO=SLA) Paso 4: Generación código IaC (preferencia: Terraform > CLI > Bicep/CDK) Paso 5: Validación (terraform validate, tflint, tfsec / az/aws equivalentes) Paso 6: Estimación coste (usar infracost o estimar manualmente) Paso 7: Propuesta INFRA-PROPOSAL.md para revisión humana
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.
- 2d ago First seen · 130 lines · 60 tokens per session scan A 120b9cffe32d
infrastructure-agent is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 1,261 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 2026-09-06.
Other agents, from other repositories
cloud-security-agent
AWS/Azure/GCP security audit, S3 bucket enumeration, container image scanning, Kubernetes RBAC review, IaC misconfiguration detection. 4-phase workflow with approval gate.
architect
Read-only. Converts a high-level project idea or major-feature request into a structured implementation specification -- goals, users, roles, permissions, features, journeys, pages, APIs, data model, business rules, auth, architecture, testing/deployment/non-functional requirements. Never implements application code.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.