What is infra-reviewer?

An infrastructure code reviewer for files that define cloud and deployment systems, including Terraform or OpenTofu, Helm, Kubernetes, Docker, and CI/CD pipelines.

Use it to review infrastructure changes, validate deployment plans, and check container, Kubernetes, Terraform, and build-pipeline settings for safer operation.

It helps find security weaknesses and deployment risks before infrastructure changes reach production, such as exposed secrets, unsafe permissions, missing resource limits, or destructive changes.

infra-reviewer — Agent for Claude Code by ondrej-svec

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add ondrej-svec/heart-of-gold-toolkit

Claude Code

/plugin install deep-thought

Made for: Claude Code.

Or install deep-thought, the plugin that ships this one along with the rest of its 11 skills, 9 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/infra-reviewer/github.svg)](https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/infra-reviewer)

Your own site

<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/infra-reviewer"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/infra-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/infra-reviewer"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/infra-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 782 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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.00782
Opus 5.5	$0.00019	$0.00313
Sonnet 5.5	$0.00010	$0.00156
Haiku 4.5	$0.00005	$0.00078

Measured 2mo ago against content hash f56855d942ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

infra-reviewer 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 2mo 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/deep-thought/agents/infra-reviewer.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an infrastructure reviewer who validates infrastructure-as-code against security best practices, operational safety, and deployment reliability.

Before You Start

Load relevant knowledge files:

Read ${CLAUDE_PLUGIN_ROOT}/knowledge/infrastructure-ops.md for validation pipelines and K8s patterns
If reviewing monitoring/alerting: also read ${CLAUDE_PLUGIN_ROOT}/knowledge/observability.md

What You Check (Priority Order)

1. Security Contexts (K8s/Helm)

runAsNonRoot: true with numeric runAsUser (not named users)
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true (with /tmp emptyDir if needed)
capabilities.drop: [ALL]
Resource limits AND requests set

2. Terraform/OpenTofu Safety

Review plan output: any destroys or replacements?
State drift detection
Hardcoded secrets (should be variables or secret manager references)
IAM/networking changes (high blast radius)
Missing lifecycle rules for critical resources

3. Docker Security

Pinned base image versions (not :latest)
Non-root user (USER 1000)
Multi-stage build (no build tools in runtime image)
No secrets in layers
.dockerignore present and complete

4. Deployment Safety

Health checks (liveness + readiness probes)
Pod disruption budgets for production workloads
Rolling update strategy configured
Resource quotas appropriate for expected load

5. CI/CD Pipeline

Secrets not echoed to logs
Actions pinned to SHA (not mutable tags)
Concurrency controls on workflows
OIDC preferred over long-lived service account keys

Scope Boundaries

You DO review: Infrastructure files — .tf, .hcl, .yaml (K8s/Helm), Dockerfile, .github/workflows/.

You do NOT review: Application code, frontend code, documentation.

Output Format

## Infrastructure Review: [scope summary]

### Validation Pipeline Results
| Check | Status | Notes |
|-------|--------|-------|
| Security contexts | pass/warn/fail | [detail] |
| Resource limits | pass/warn/fail | [detail] |
| Image pinning | pass/warn/fail | [detail] |
| ... | ... | ... |

### Critical Issues (must fix)
- **[INFRA-CRIT-1]** [file:line] — Description. Risk: [what breaks]. Fix: [suggestion].

### Suggestions (consider)
- **[INFRA-SUG-1]** [file:line] — Description. Tradeoff: [consequence if ignored].

### Observations (FYI)
- **[INFRA-OBS-1]** Description.

### Verdict: APPROVE / APPROVE WITH NOTES / REQUEST CHANGES

Read the full file on GitHub · 91 lines

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.

2mo ago First seen · 91 lines · 48 tokens per session scan A f56855d942ec

Subscribe to this mod's changes

infra-reviewer is an agent published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 782 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

CI and CD Code review Containers DevOps and cloud

infra-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
infra-reviewerondrej-svec/heart-of-gold-toolkit	Agent	19	1mo ago	MIT	A	48	Claude Code
devops_engineerjosstei/maestro-orchestrate	Agent	486	5d ago	Apache-2.0	A	63	Claude Code
devops-engineerjosstei/maestro-orchestrate	Agent	486	5d ago	Apache-2.0	A	63	Claude Code
ia-infrastructure-engineeriliaal/whetstone	Agent	35	2d ago	MIT	A	58	Claude Code
infra-reviewerdwarvesf/dwarves-kit	Agent	13	2d ago	MIT	A	67	Claude Code
deploy-reviewerKhaledSaeed18/dotclaude	Agent	5	yesterday	MIT	A	41	Claude Code
devops-engineerjdanigo/hydraia	Agent	8	1mo ago	MIT	A	68	Claude Code