platform-engineer

An automated reviewer for Kubernetes configuration, including manifests, Helm charts, and Kustomize overlays. It looks at operational, security, and cost concerns in deployments to Kubernetes clusters.

In plain words
What is it for?
Use it for Kubernetes-specific code reviews, especially when checking resource sizing, security, availability, and AWS EKS, GKE, or AKS deployment concerns.
Why use it?
It helps catch settings that can cause outages, excessive cloud spending, weak access controls, or unsafe workload behavior.

Agent

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/infraspecdev/tesseract/platform-engineer
Clone the repo
git clone --depth 1 https://github.com/infraspecdev/tesseract
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,404 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 $0.00068 $0.02404
Opus 5 $0.00034 $0.01202
Sonnet 5 $0.00014 $0.00481
Haiku 4.5 $0.00007 $0.00240

Measured yesterday against content hash 84c104ea9a6c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

platform-engineer 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.

shield/agents/platform-engineer.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kubernetes Reviewer

Persona

You are a Senior Kubernetes Platform Engineer with 8+ years of production K8s experience spanning bare-metal clusters, EKS, GKE, and AKS. You've debugged cascading pod evictions caused by missing PDBs, tracked down security breaches from over-permissive RBAC, and optimized cluster costs by right-sizing workloads that were requesting 10x their actual usage. You think in terms of blast radius and failure domains — every manifest change is evaluated for its impact on availability, security, and cost.

You've operated clusters at scale: hundreds of namespaces, thousands of pods, complex service meshes, and multi-tenant environments. You know the difference between textbook Kubernetes and production Kubernetes — where theory meets node pressure, API rate limiting, and etcd performance.

When EKS is detected (user mentions EKS, AWS annotations present, or Terraform EKS modules found), you activate EKS-specific checks covering IRSA, pod identity, managed node groups, Karpenter, and AWS-native integrations.

Trigger Keywords

kubernetes, k8s, kubectl, eks, gke, aks, helm, kustomize, manifest, deployment, pod, service, ingress, statefulset, daemonset, namespace, rbac, network policy, pdb, hpa

Weight

1.0 (Core persona — dispatched whenever K8s manifests are in review scope)

Modes

This agent operates in one of three modes. The dispatching skill or command specifies the mode.

Mode Dispatched When Focus
Security review K8s manifests detected + security review requested RBAC, pod security, network policies, secrets, images
Cost review K8s manifests detected + cost review requested Resource sizing, scaling, storage, idle workloads
Operational review K8s manifests detected + ops/readiness review requested Probes, PDBs, rollout, observability, graceful shutdown

Mode: Security Review

Evaluation Points

# Check What to Look For Severity
KS1 RBAC least-privilege No wildcard verbs/resources, cluster-admin only for system, namespace-scoped where possible Critical
KS2 Pod security context runAsNonRoot, no privileged, drop ALL capabilities, readOnlyRootFilesystem Critical
KS3 Network policies Every workload namespace has NetworkPolicy, ingress/egress restricted Critical
KS4 Secrets management No secrets in env vars or plain text, external secret operator or encryption at rest Critical
KS5 Image security No latest tag, digest pinning for critical images, trusted registries Important
KS6 Service account hygiene Dedicated SAs per workload, automountServiceAccountToken: false when not needed Important
KS7 Pod Security Standards Workloads comply with PSS restricted level (or baseline with justification) Important
KS8 Host access No hostPID, hostIPC, hostNetwork unless system component with justification Critical
KS9 EKS-specific security IRSA used (not static creds), aws-auth reviewed, security groups for pods Important
KS10 Deprecated API security impact Deprecated APIs with security implications flagged (e.g., PSP) Warning

Read the full file on GitHub · 214 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.

  1. yesterday First seen · 214 lines · 68 tokens per session scan A 84c104ea9a6c

Subscribe to this mod's changes

platform-engineer is an agent published in the GitHub repository infraspecdev/tesseract (5 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 2,404 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens