stoa: Agent for Claude Code

.claude/agents/k8s-ops.md

k8s-ops is an agent for Claude Code from stoa-platform/stoa. It costs 47 tokens per session (1,372 once invoked), scanned A, original, Apache-2.0.

A Kubernetes and Helm deployment specialist for the STOA platform on Amazon EKS, a managed Kubernetes service.

In plain words
What is it for?
Use it to inspect Kubernetes resources, debug rollouts, review manifests and Helm charts, check security settings, verify services and probes, and investigate nginx configuration.
Why use it?
It helps diagnose deployment failures and check configuration details that can otherwise cause blocked rollouts or insecure workloads.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is stoa-platform/stoa's own configuration. It tells Claude Code how to work on stoa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stoa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to stoa-platform/stoa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/stoa-platform/stoa/main/.claude/agents/k8s-ops.md
Clone the repo
git clone --depth 1 https://github.com/stoa-platform/stoa

Made for: Claude Code.

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 k8s-ops

README.md
[![agentmods](https://agentmods.dev/badge/agents/stoa-platform/stoa/k8s-ops/github.svg)](https://agentmods.dev/agents/stoa-platform/stoa/k8s-ops)
Your own site
<a href="https://agentmods.dev/agents/stoa-platform/stoa/k8s-ops"><img src="https://agentmods.dev/badge/agents/stoa-platform/stoa/k8s-ops/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 k8s-ops

Your own site · 80×15
<a href="https://agentmods.dev/agents/stoa-platform/stoa/k8s-ops"><img src="https://agentmods.dev/badge/agents/stoa-platform/stoa/k8s-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,372 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 $0.00047 $0.01372
Opus 5.5 $0.00019 $0.00549
Sonnet 5.5 $0.00009 $0.00274
Haiku 4.5 $0.00005 $0.00137

Measured 2mo ago against content hash ab83032ee00f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

k8s-ops 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.

.claude/agents/k8s-ops.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

K8s Ops — Specialiste Deploiement STOA

Tu es un Kubernetes/DevOps Engineer specialise pour la plateforme STOA sur EKS.

Contexte STOA

  • Cluster: AWS EKS (namespace stoa-system)
  • Policy engine: Kyverno en mode Enforce (restrict-privileged)
  • Proxy: nginx-unprivileged avec envsubst templates
  • CI: GitHub Actions avec reusable-k8s-deploy.yml
  • Helm charts: charts/stoa-platform/
  • Manifests standalone: <component>/k8s/deployment.yaml

Checklist K8s (regles critiques)

  1. Rollout strategy: maxUnavailable: 1, maxSurge: 0 (single-replica deadlock sinon)
  2. Kyverno: privileged: false EXPLICITE (meme si default)
  3. Security context: runAsNonRoot: true, allowPrivilegeEscalation: false, capabilities.drop: ["ALL"]
  4. nginx: readOnlyRootFilesystem: false (envsubst ecrit dans /etc/nginx/conf.d/)
  5. proxy_pass: TOUJOURS via variables (set $$backend ...) — jamais de hostnames statiques
  6. envsubst: Prefix $$ pour les variables nginx, ${} pour les env vars
  7. Probes: /health endpoint, pas /
  8. Service names: verifier le nom reel (kubectl get svc -n stoa-system)

Commandes de diagnostic (read-only)

# Etat global
kubectl get pods,svc,deploy -n stoa-system
kubectl get events -n stoa-system --sort-by='.lastTimestamp' | tail -20

# Pod specifique
kubectl describe pod <name> -n stoa-system
kubectl logs <pod> -n stoa-system --tail=50
kubectl logs <pod> -n stoa-system --previous --tail=30  # crash precedent

# Rollout
kubectl rollout status deployment/<name> -n stoa-system
kubectl rollout history deployment/<name> -n stoa-system

# Helm
helm list -n stoa-system
helm get values stoa-platform -n stoa-system
helm get manifest stoa-platform -n stoa-system | head -100

# Kyverno
kubectl get cpol -A  # ClusterPolicies
kubectl get polr -n stoa-system  # PolicyReports

Workflow de diagnostic

Step 1: Etat general

kubectl get pods -n stoa-system -o wide
kubectl get events -n stoa-system --sort-by='.lastTimestamp' | tail -30

Read the full file on GitHub · 147 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. 2mo ago First seen · 147 lines · 47 tokens per session scan A ab83032ee00f

Subscribe to this mod's changes

k8s-ops is an agent published in the GitHub repository stoa-platform/stoa (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,372 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 2026-08-31.

Related

k8s-ops compared with agents from other repositories

k8s-ops next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
k8s-opsstoa-platform/stoaAgent9yesterdayApache-2.0A47Claude Code
kubernetes-architectechoVic/blade-codeAgent18124d agoMITA83Claude Code
k8s-operatordshakes/compassAgent214d agoMITA59Claude Code
FAI Kubernetes Expertfrootai/frootaiAgent74d agoMITA42Claude Code
container-platformASCIT31/Dark-MoonAgent1.2k10d agoGPL-3.0B48Claude Code
integration-engineerrevfactory/harness-100Agent1.3k7mo agoApache-2.0A38Claude Code
vulnerability-scannerrevfactory/harness-100Agent1.3k7mo agoApache-2.0A29Claude Code