ZavaShop on AKS and Azure Container Apps is a hands-on lab for delivering a multi-agent retail supply-chain application from requirements through deployment. It demonstrates a team of six GitHub Copilot custom coding agents working across specifications, application code, MCP servers, tests, infrastructure, and CI. The catalogue entries define the agents, skills, and instructions used in that workflow.
Borrowing it
Nothing to install: this file belongs to microsoft/AKS-Lab-GitHubCopilot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/AKS-Lab-GitHubCopilot/main/.github/skills/aks-helm/SKILL.mdgit clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilotWrote 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/skills/microsoft/aks-lab-githubcopilot/aks-helm)<a href="https://agentmods.dev/skills/microsoft/aks-lab-githubcopilot/aks-helm"><img src="https://agentmods.dev/badge/skills/microsoft/aks-lab-githubcopilot/aks-helm/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/skills/microsoft/aks-lab-githubcopilot/aks-helm"><img src="https://agentmods.dev/badge/skills/microsoft/aks-lab-githubcopilot/aks-helm.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 | $0.00000 | $0.00956 |
| Opus 5.5 | $0.00000 | $0.00382 |
| Sonnet 5.5 | $0.00000 | $0.00191 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
aks-helm 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: AKS Helm Chart for the Orchestrator
Chart layout
infra/aks/helm/zavashop/
├── Chart.yaml
├── values.yaml
└── templates/
├── _helpers.tpl
├── serviceaccount.yaml
├── secretproviderclass.yaml
├── deployment.yaml
└── service.yaml
values.yaml shape
image:
repository: "" # acr.azurecr.io/zavashop/orchestrator
tag: "" # git short sha — REQUIRED, no default
pullPolicy: IfNotPresent
workloadIdentity:
clientId: "" # UAMI client id, REQUIRED
keyVault:
name: "" # REQUIRED
tenantId: "" # REQUIRED
a2a:
inventory: ""
supplier: ""
logistics: ""
pricing: ""
resources:
requests: { cpu: "200m", memory: "256Mi" }
limits: { cpu: "1", memory: "1Gi" }
podSecurityContext:
runAsNonRoot: true
runAsUser: 10001
runAsGroup: 10001
fsGroup: 10001
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: ["ALL"]
serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: orchestrator-sa
namespace: {{ .Release.Namespace }}
annotations:
azure.workload.identity/client-id: {{ required "workloadIdentity.clientId" .Values.workloadIdentity.clientId }}
labels:
azure.workload.identity/use: "true"
secretproviderclass.yaml
apiVersion: secrets-store.csi.x-k8s.io/v1
kind: SecretProviderClass
metadata:
name: zavashop-github-token
spec:
provider: azure
parameters:
usePodIdentity: "false"
useVMManagedIdentity: "false"
clientID: {{ .Values.workloadIdentity.clientId }}
keyvaultName: {{ .Values.keyVault.name }}
tenantId: {{ .Values.tenantId }}
objects: |
array:
- |
objectName: GITHUB-TOKEN
objectType: secret
secretObjects:
- secretName: github-token
type: Opaque
data:
- objectName: GITHUB-TOKEN
key: token
deployment.yaml essentials
metadata.labels.azure.workload.identity/use: "true"on the pod template.serviceAccountName: orchestrator-sa.topologySpreadConstraintsovertopology.kubernetes.io/zone,maxSkew: 1.- Non-root pod and container security contexts from
values.yaml. - Mount the CSI volume; project
GITHUB_TOKENenv viasecretKeyReftogithub-token/token. - Env:
AZURE_CLIENT_ID,ZAVA_COPILOT_MODEL=gpt-5.5,ZAVA_COPILOT_TIMEOUT_SECONDS=120, and four specialist A2A URLs from.Values.a2a.*. - Probes:
/healthz,/readyzon the orchestrator service port 8000 (see deploy-engineer rule 7).
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.
- 2mo ago First seen · 122 lines · 0 tokens per session scan A 81ee232d961c
aks-helm is a skill published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (10 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 956 tokens. 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.
aks-helm compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aks-helmmicrosoft/AKS-Lab-GitHubCopilot | Skill | 10 | 8d ago | MIT | A | 0 | Claude Code, Codex |
| deploy-docker-composeomnigent-ai/omnigent | Skill | 11k | yesterday | Apache-2.0 | A | 84 | Claude Code, Codex |
| bdd-container-updateNVIDIA-AI-Blueprints/video-search-and-summarization | Skill | 2.0k | yesterday | Apache-2.0 | A | 117 | Cursor |
| securing-kubernetes-on-cloudxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | A | 80 | Claude Code, Codex |
| detecting-privilege-escalation-in-kubernetes-podsxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | A | 40 | Claude Code, Codex |
| docker-socket-mountPurpleAILAB/Decepticon | Skill | 6.5k | 8d ago | Apache-2.0 | B | 67 | Claude Code |
| k8s-networkingrohitg00/kubectl-mcp-server | Skill | 968 | 15d ago | MIT | A | 34 | Claude Code, Codex |