infra-auditor

infra-auditor is an agent for Claude Code from pwdev-solucoes/pwdev-claude-marketplace. It costs 61 tokens per session (411 once invoked), scanned A, original, Apache-2.0.

A read-only infrastructure auditor that checks AWS, Kubernetes, security, costs, and operational readiness, then reports findings with evidence.

In plain words
What is it for?
It is for auditing cloud and cluster resources, checking security and spending issues, and producing findings with verification commands, impact, and proposed corrections.
Why use it?
It gives teams a structured view of risks and gaps without changing the systems being reviewed. It also records what could not be checked because of missing access or tools.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the pwdev-devops plugin — 19 skills, 5 commands, 4 agents shipped together

Good fit It is for auditing cloud and cluster resources, checking security and spending issues, and producing findings with verification commands, impact, and proposed corrections.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pwdev-solucoes/pwdev-claude-marketplace/infra-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/pwdev-solucoes/pwdev-claude-marketplace

Made for: Claude Code.

Or install pwdev-devops, the plugin that ships this one along with the rest of its 19 skills, 5 commands, 4 agents.

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 infra-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/infra-auditor/github.svg)](https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/infra-auditor)
Your own site
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/infra-auditor"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/infra-auditor/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 infra-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/pwdev-solucoes/pwdev-claude-marketplace/infra-auditor"><img src="https://agentmods.dev/badge/agents/pwdev-solucoes/pwdev-claude-marketplace/infra-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 411 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 $0.00061 $0.00411
Opus 5 $0.00030 $0.00205
Sonnet 5 $0.00012 $0.00082
Haiku 4.5 $0.00006 $0.00041

Measured 6d ago against content hash 70cdcb9e3520, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

infra-auditor 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 6d 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.

plugins/pwdev-devops/agents/infra-auditor.md · 36 lines

What it actually says

Subagente: Infra Auditor

Papel

Auditor. Percorre aws-architect, kubernetes-platform, devsecops, finops e reliability-engineer em modo leitura.

Contrato de entrada

  • LANGUAGE, ESCOPO (aws | k8s | seguranca | custo | tudo)
  • CONTEXT_FILE, AMBIENTE

Regras inegociáveis

  1. Somente leitura. describe, list, get, plan, status. Nenhuma mutação, em nenhuma hipótese, nem com pedido do usuário — outro agente faz isso.
  2. Confirme conta e contexto antes: aws sts get-caller-identity, kubectl config current-context.
  3. Todo achado traz o comando que o comprova.
  4. Severidade pelo que a brecha permite, não pelo CVSS isolado. Não infle.
  5. Nunca imprima valor de segredo. get secret -o yaml expõe base64 — use describe.
  6. Recurso aparentemente órfão pode ter dono: verifique tag antes de sugerir remoção.
  7. Declare o que não pôde ser verificado por falta de permissão ou ferramenta.

Contrato de saída

Achados por severidade, cada um com evidência, comando de verificação, impacto e correção proposta. Seção final obrigatória: "não verificado".

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. 6d ago First seen · 36 lines · 61 tokens per session scan A 70cdcb9e3520

Subscribe to this mod's changes

infra-auditor is an agent published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 61 tokens to every session and 411 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 2026-09-03.