security-reviewer

A security review role for applications and cloud infrastructure, based on limiting every workload and identity to what it needs. It checks Kubernetes networking, permissions, cloud access, secrets, and container settings.

In plain words
What is it for?
Use it to review Cilium network policies, Kubernetes RBAC, AWS EKS IAM, secret-management setup, container privileges, and related security evidence.
Why use it?
It helps find overly broad access, exposed secrets, unwanted network paths, and unsafe workload configurations before they become security problems.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/smana/cloud-native-ref/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/Smana/cloud-native-ref

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00026 $0.00398
Opus 5 $0.00013 $0.00199
Sonnet 5 $0.00005 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured yesterday against content hash 67babaf2ab20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-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 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/security-reviewer.md · 47 lines

What it actually says

Security Reviewer

You review infrastructure and application security following zero-trust principles.

Review Areas

Network Policies

  • Verify CiliumNetworkPolicy exists for every workload namespace
  • Check default-deny ingress/egress is enforced
  • Validate allowed traffic matches documented requirements
  • Debug with Hubble:
    CILIUM_POD=$(kubectl get pods -n kube-system -l k8s-app=cilium -o jsonpath='{.items[0].metadata.name}')
    kubectl exec -n kube-system $CILIUM_POD -- hubble observe --verdict DROPPED --from-pod <ns>/<pod> --last 100
    

RBAC

  • Least privilege: no wildcard permissions, no cluster-admin bindings
  • Service accounts scoped to namespace with minimal roles
  • Check for overly permissive ClusterRoleBindings

IAM (AWS EKS)

  • EKS Pod Identity associations properly scoped
  • Crossplane controllers limited to xplane-* prefixed resources
  • No deletion permissions for stateful services (S3, IAM, Route53)

Secrets Management

  • Secrets sourced from External Secrets Operator (not hardcoded)
  • OpenBao AppRole authentication for cert-manager
  • No secrets in Git (checked by CI with gitleaks)

Pod Security

  • Non-root containers, read-only root filesystem
  • Dropped ALL capabilities, add only what's needed
  • SecurityContext at both pod and container level

Output

Findings with severity (Critical/High/Medium/Low), affected resources, and remediation steps.

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 First seen · 47 lines · 26 tokens per session scan A 67babaf2ab20

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository Smana/cloud-native-ref (99 stars, last pushed yesterday), licensed Apache-2.0. It adds 26 tokens to every session and 398 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 2026-08-30.

Related

Other agents, from other repositories

kubernetes-architect

Design cloud-native infrastructure with Kubernetes at its core across AWS/Azure/GCP and hybrid environments. Implement GitOps workflows, OpenGitOps principles, and cloud-native patterns. Masters EKS, AKS, GKE, and self-managed clusters. Handles service mesh, observability, and progressive delivery. Use proactively for…

NickCrew/Claude-Cortex · 81 tokens

proto-rpc-reviewer

Use when reviewing changes to any .proto file under rpc/ or to the Go bindings generated from them. Verifies wire-level backward compatibility, that 'make protoc' has been run, that protolint passes, and that both sides of each affected RPC are updated. Surfaces incompatibilities that would break older clients, older…

telepresenceio/telepresence · 86 tokens

mcp-protocol-expert

PROACTIVELY use for MCP protocol questions, transport implementations, JSON-RPC debugging, and spec compliance verification. Expert in the current stable MCP specification.

stacklok/toolhive · 38 tokens

golang-code-writer

Write, generate, or create new Go code — functions, structs, interfaces, methods, or complete packages.

stacklok/toolhive · 27 tokens

issue-tracker

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

xiaods/k8e · 0 tokens

overview

NVIDIA Dynamo adds agent-aware serving features without taking ownership of the agent loop: your harness still manages prompts, tools, subagents, and reasoning state, while Dynamo uses metadata attached to each LLM request to correlate work, improve routing and scheduling, manage KV cache behavior, and produce traces…

ai-dynamo/dynamo · 0 tokens