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.
npx agentmods add skills/microsoft/aks-lab-githubcopilot/aca-bicepnpx skills add microsoft/AKS-Lab-GitHubCopilot --skill aca-bicepgit clone --depth 1 https://github.com/microsoft/AKS-Lab-GitHubCopilotWhat 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 | $0.00000 | $0.00650 |
| Opus 5 | $0.00000 | $0.00325 |
| Sonnet 5 | $0.00000 | $0.00130 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
aca-bicep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: ACA Bicep Module
infra/aca/agent.bicep parameters
param name string
param envId string // ACA environment resource id
param image string // full ACR path incl. :<git-sha>
param uamiId string // user-assigned managed identity id
param uamiClientId string
param copilotModel string = 'gpt-5.5'
param mcpEndpoints object = {} // map: ZAVA_<KEY>_MCP_URL -> value
param exposeIngress bool = false
param keyVaultName string
param targetPort int = 8000
param minReplicas int = 1
Container env (mandatory)
env: [
{ name: 'AZURE_CLIENT_ID', value: uamiClientId }
{ name: 'ZAVA_COPILOT_MODEL', value: copilotModel }
{ name: 'ZAVA_COPILOT_TIMEOUT_SECONDS', value: '120' }
{ name: 'GITHUB_TOKEN', secretRef: 'github-token' }
// Spread the mcpEndpoints map into ZAVA_*_MCP_URL entries
]
secrets: [
{
name: 'github-token'
keyVaultUrl: 'https://${keyVaultName}${environment().suffixes.keyvaultDns}/secrets/GITHUB-TOKEN'
identity: uamiId
}
]
Identity
identity: {
type: 'UserAssigned'
userAssignedIdentities: { '${uamiId}': {} }
}
Scale rule (always)
scale: {
minReplicas: minReplicas
maxReplicas: 10
rules: [
{
name: 'http-concurrency'
http: { metadata: { concurrentRequests: '30' } }
}
]
}
Probes
Agents use runtime port 8000; MCP servers use 8080. Probe targetPort so one module works for both.
probes: [
{ type: 'Liveness', httpGet: { path: '/healthz', port: targetPort }, periodSeconds: 10 }
{ type: 'Readiness', httpGet: { path: '/readyz', port: targetPort }, periodSeconds: 5 }
]
Tags (mandatory)
tags: {
project: 'zavashop'
lab: '05'
agent: name
}
Rules
- Image tag is the git SHA.
:latestis a build error. - No
value:for secrets — onlysecretRef. - Lab 05 sets
exposeIngress: trueandminReplicas: 1for specialists and MCPs so AKS smoke/eval calls can reach ACA FQDNs reliably. Production should revisit private ingress and scale-to-zero once DNS/networking and cold-start budgets are designed.
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.
- 2d ago First seen · 88 lines · 0 tokens per session scan A c6e604dce19b
aca-bicep is a skill published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 650 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…