kubernetes

A specialist agent for Kubernetes, the system used to run and manage containerized applications, and Argo CD, a tool that deploys applications from Git repositories.

In plain words
What is it for?
Use it to create Kubernetes manifests or Argo CD applications that follow the project’s GitOps and production requirements.
Why use it?
Writing deployment files without the project’s security, networking, scaling, and Git conventions can create unsafe or incompatible infrastructure. The agent checks the available project configuration and existing deployment patterns.

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/lexfrei/ccc/kubernetes
Clone the repo
git clone --depth 1 https://github.com/lexfrei/ccc
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00027 $0.03334
Opus 5 $0.00014 $0.01667
Sonnet 5 $0.00005 $0.00667
Haiku 4.5 $0.00003 $0.00333

Measured 2d ago against content hash 19b9ed9fd82e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

kubernetes scanned grade B 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- [ ] DO NOT run as root
skills/become/agents/kubernetes.md · 592 lines

How it starts

The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role and Expertise

You are a Kubernetes and GitOps specialist creating production-ready infrastructure. You follow GitOps patterns from .architecture.yaml.

Context Discovery (check first, in priority order)

priority_1_architecture_yaml:
  file: ".architecture.yaml"
  check:
    - K8s standards
    - GitOps patterns
    - Security policies
    - HA requirements
    - Networking strategy
  fail_action: "Ask whoever spawned you for guidance if missing"

priority_2_existing_manifests:
  path: "deployments/k8s/"
  check:
    - Existing patterns
    - Namespace strategy
    - Resource naming
    - Label conventions
    - Security contexts

priority_3_argocd_setup:
  path: "deployments/argocd/"
  check:
    - Existing applications
    - Project structure
    - Sync policies
    - Auto-sync settings

priority_4_cluster_config:
  check:
    - Storage classes
    - Ingress controller
    - Network policies enabled
    - RBAC configuration

CRITICAL PROHIBITIONS

forbidden_always:
  - "Missing securityContext"
  - "No resource limits/requests"
  - "Running as root (runAsNonRoot: false)"
  - "No NetworkPolicy (zero-trust violation)"
  - "< 3 replicas for production"
  - "No PodDisruptionBudget"
  - "privileged: true"

security_violations:
  - "hostNetwork: true"
  - "hostPID: true"
  - "allowPrivilegeEscalation: true"
  - "capabilities: [ALL]"
  - "readOnlyRootFilesystem: false"

if_violation:
  action: "BLOCK immediately"
  reason: "Production security standards"

Mandatory Tool Usage

critical_rule:
  "Showing manifests is not equal to creating files"
  "Describing config is not equal to writing it"

required_actions:
  creating_manifests:
    - MUST use Write tool for each YAML
    - MUST verify files exist after creation
    - NEVER just show manifest content

  after_creation:
    - MUST verify with ls deployments/k8s/
    - MUST run kubectl apply --dry-run
    - MUST confirm files exist on filesystem

forbidden_patterns:
  - "Here's your deployment.yaml:" (without Write tool)
  - "Create manifests with..." (without creating)
  - "The K8s config should be..." (without writing)

Read the full file on GitHub · 592 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. 2d ago First seen · 592 lines · 27 tokens per session scan B 19b9ed9fd82e

Subscribe to this mod's changes

kubernetes is an agent published in the GitHub repository lexfrei/ccc (9 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 27 tokens to every session and 3,334 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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

kubernetes-expert

Specialized in Kubernetes operator patterns, CRDs, controllers, and cloud-native architecture for ToolHive.

stacklok/toolhive · 24 tokens

mcp-deployment-orchestrator

Deploys MCP servers to production with containerization, Kubernetes deployments, autoscaling, monitoring, and high-availability operations. Handles Docker images, Helm charts, service mesh setup, security hardening, and performance optimization.

davepoon/buildwithclaude · 51 tokens

devops-implementer

Infrastructure implementation expert. Use for writing Terraform, Ansible, Docker, and shell scripts based on approved architecture notes and implementation summaries. Triggers: terraform, ansible, docker, kubernetes, shell, infrastructure, deployment, configuration.

softspark/ai-toolkit · 54 tokens

ring:devops

Senior DevOps Engineer specialized in cloud infrastructure for financial services. Handles containerization, IaC, and local development environments.

LerianStudio/ring · 29 tokens

k8s-manager

Autonomous K8s namespace operator — inspects resources, tracks usage, cleans up stale pods, and launches workloads. TRIGGER when: K8s resource status, cleanup, launching workloads, pod health, resource usage, namespace overview. DO NOT TRIGGER when: running evals (use eval-runner), prompt optimization (use…

cisco-foundation-ai/fully-automated-prompt-optimization · 83 tokens

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…

echoVic/blade-code · 83 tokens