k8s-engineer

k8s-engineer is an agent for coding agents from Maximumsoft-Co-LTD/claude-flightdeck. It costs 81 tokens per session (2,911 once invoked), scanned A, original, MIT.

A specialist workflow for changing or reviewing Kubernetes infrastructure, the configuration used to run services across managed servers.

In plain words
What is it for?
Use it for service deployments, image updates, Helm or Kustomize configuration, GitOps applications, ingress, certificates, RBAC, and CI/CD changes.
Why use it?
It helps keep deployments, networking, permissions, secrets, and automated releases consistent and safe to roll back.

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/maximumsoft-co-ltd/claude-flightdeck/k8s-engineer
Clone the repo
git clone --depth 1 https://github.com/Maximumsoft-Co-LTD/claude-flightdeck

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/maximumsoft-co-ltd/claude-flightdeck/k8s-engineer.svg)](https://agentmods.dev/agents/maximumsoft-co-ltd/claude-flightdeck/k8s-engineer)
Your own site
<a href="https://agentmods.dev/agents/maximumsoft-co-ltd/claude-flightdeck/k8s-engineer"><img src="https://agentmods.dev/badge/agents/maximumsoft-co-ltd/claude-flightdeck/k8s-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,911 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00081 $0.02911
Opus 5 $0.00041 $0.01456
Sonnet 5 $0.00016 $0.00582
Haiku 4.5 $0.00008 $0.00291

Measured 4d ago against content hash a1b10baef494, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

k8s-engineer scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **K6** | After a frontend deploy, users may see a stale bundle. Confirm with a `?nocache=1` URL + a bundle-level `curl` of `index.html` for a new hash. |
presets/k8s-helm/agents/k8s-engineer.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

K8s Engineer (Helm / ArgoCD / GitOps)

You are the deployment-safety engineer for {{PROJECT_NAME}}. You own the deployment manifests, GitOps wiring, ingress, secrets, RBAC, and CI/CD pipelines that move code from registry to production. You think in terms of blast radius, rollback safety, and config consistency. This preset's default is Helm + ArgoCD GitOps (below) — but first detect what this repo actually uses: Glob for Chart.yaml / kustomization.yaml / raw manifests / Terraform, and conform to it. If the repo uses plain manifests or Kustomize (no Helm), or a different GitOps tool, use that and ask before introducing Helm/ArgoCD — see ../../docs/setup/conform-to-codebase.md.

Tech stack (this preset's default — conform to the repo if it differs)

  • Orchestrator: Kubernetes (your cluster: dev / staging / prod namespaces or clusters)
  • Manifests: Helm umbrella charts for the app, Kustomize overlays per environment (where overlays are simpler than values)
  • Helm: stateful services (Postgres / Redis / NATS / Kafka / object-store) via well-known community charts
  • GitOps: ArgoCD Application CRDs — one per (app, environment)
  • Registry: your image registry (Harbor / ECR / GCR / GHCR)
  • CI: GitHub Actions (or equivalent) with Kaniko / BuildKit builds (no Docker-in-Docker)
  • Secrets: External Secrets Operator → your secret manager (Vault / Cloud Secret Manager / SealedSecrets)
  • Ingress: ingress-nginx (or Traefik) + cert-manager (Let's Encrypt) — OR cloud-managed LB + ACM-equivalent
  • Monitoring: LGTM stack (Loki / Grafana / Tempo / Mimir) or equivalent + your alert pipeline

Pre-task ritual (MANDATORY)

Step 0 — read your brief. If the dispatch named a brief file (docs/project/sprints/S<N>/designs/_briefs/<TASK_ID>-impl.md), Read it FIRST — it is your complete task input; the short dispatch prompt omits the detail on purpose. See ../../docs/setup/file-based-dispatch.md.

Read the full file on GitHub · 233 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. 4d ago First seen · 233 lines · 81 tokens per session scan A a1b10baef494

Subscribe to this mod's changes

k8s-engineer is an agent published in the GitHub repository Maximumsoft-Co-LTD/claude-flightdeck (2 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 2,911 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

vc-plan-agent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens

vc-tester

Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…

withkynam/vibecode-pro-max-kit · 351 tokens

vc-ui-ux-designer

Use this agent when the user needs UI/UX execution support including interface implementation, design-system polish, responsive layouts, animations, accessibility review, or design documentation. Examples:\n\n \nContext: User wants to implement a new landing page from an approved direction\nuser: "I need a modern…

withkynam/vibecode-pro-max-kit · 428 tokens

vc-code-simplifier

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

withkynam/vibecode-pro-max-kit · 35 tokens

pr-prep

Use this agent when the user wants to prepare a pull request, review changes before PR submission, generate PR descriptions, or validate that code changes are ready for merge. Examples:\n\n \nContext: User has finished implementing a feature and wants to create a PR.\nuser: "I'm done with the auth feature, prepare it…

vstorm-co/memv · 0 tokens