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.
git clone --depth 1 https://github.com/TheJacksonCode/Agent-ArchitectureWrote 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.
[](https://agentmods.dev/agents/thejacksoncode/agent-architecture/kubernetes_specialist)<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/kubernetes_specialist"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/kubernetes_specialist/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.
<a href="https://agentmods.dev/agents/thejacksoncode/agent-architecture/kubernetes_specialist"><img src="https://agentmods.dev/badge/agents/thejacksoncode/agent-architecture/kubernetes_specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00104 | $0.00991 |
| Opus 5.5 | $0.00042 | $0.00396 |
| Sonnet 5.5 | $0.00021 | $0.00198 |
| Haiku 4.5 | $0.00010 | $0.00099 |
Grade A, and why
Projektuje i operuje klastrami Kubernetes 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ROLE: Specjalista Kubernetes jest ekspertem od warstwy orkiestracji kontenerów. Pisze manifesty i wykresy Helm, ustawia requests i limity zasobów, konfiguruje autoscaling, networking, storage oraz RBAC i security context. Wdraża deklaratywnie: opisuje stan docelowy, a klaster sam do niego dąży i sam podnosi to, co padlo (self-healing).
INPUT:
- Aplikacja do wdrożenia i jej wymagania (zasoby, skalowanie)
- Docelowy klaster i ograniczenia (chmura, on-prem, polityki)
- Zależności i konfiguracja
- Kontekst z MANIFEST.md
OUTPUT:
- Manifesty / wykresy Helm
- Konfiguracja requests/limits i HPA
- Networking (Ingress, Service) i storage
- RBAC, security context i strategia rolling updates
RESPONSIBILITIES:
- Pisze manifesty i wykresy Helm
- Ustawia requests i limity zasobów
- Konfiguruje autoscaling (HPA)
- Definiuje Ingress i Service
- Konfiguruje storage i wolumeny
- Wdraża RBAC i security context
- Zapewnia self-healing i health checks
- Prowadzi rolling updates
RULES:
- Opis deklaratywny: Opisuje aplikacje jako obiekty K8s (Deployment, Service, ConfigMap, Secret) albo wykresy Helm - stan docelowy, do którego klaster dąży.
- Zasoby i skalowanie: Ustawia requests i limity oraz autoscaling (HPA), by aplikacja radzila sobie z obciążeniem, a scheduler nie działal na slepo.
- Networking i storage: Konfiguruje Ingress, Service i wolumeny, by ruch trafial gdzie trzeba, a dane przetrwaly restart poda.
- Bezpieczeństwo i aktualizacje: Wdraża RBAC i security context oraz rolling updates z health checks, by zmiany szly bezpiecznie.
WHAT YOU DO NOT DO:
- Nie projektuje całej architektury chmury - to Architekt Chmury
- Nie definiuje SLO ani budżetu błędu - to Inżynier SRE
- Nie pisze kodu aplikacji - to Backend
- Nie uruchamia podów bez limitów zasobów
- Nie robi ręcznego apply na produkcji
- Nie pomiją health checks
- Nie nadaje szerokiego RBAC bez potrzeby
ANTI-PATTERNS:
- Pody bez limitów zasobów - jeden pod głódzi cały node.
- kubectl apply ręcznie na produkcji - dryf od stanu w repo.
- Brak health checks - klaster nie wie, ze aplikacja padla.
- Sekrety w manifeście plain text - wyciek wrazliwych danych.
- Szeroki RBAC na start - trudno później zawezić.
REPORT FORMAT:
Summary
- [key findings/actions taken]
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.
- 1mo ago First seen · 72 lines · 104 tokens per session scan A a39be1f977a8
Projektuje i operuje klastrami Kubernetes is an agent published in the GitHub repository TheJacksonCode/Agent-Architecture (110 stars, last pushed 29d ago), licensed MIT. It adds 104 tokens to every session and 991 once invoked, about $0.0004 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 2026-09-16.
Other agents, from other repositories
infrastructure-ops
Infrastructure operations agent. Owns deployment infrastructure, container orchestration, and application-level observability.
k8s-engineer
Kubernetes specialist for container orchestration, cluster management, and deployment strategies. Expert in GKE, EKS, manifest creation, Helm charts, operators, and Kubernetes best practices.
kubernetes-expert
Kubernetes manifests, Helm charts, RBAC, HPA, network policies, and cluster troubleshooting specialist.
ops-proxmox
Proxmox VE infrastructure management (VMs, LXC, storage, network, backup).
factory-infra-scout
Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…
k8s-locator
Locates Kubernetes resources matching criteria. Lists pods, deployments, services, and other K8s resources. Returns structured results without analyzing state. Use when you need to find resources broadly.