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 agents/microsoft/aks-lab-githubcopilot/deploy-engineergit 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 | $0.00027 | $0.02136 |
| Opus 5 | $0.00014 | $0.01068 |
| Sonnet 5 | $0.00005 | $0.00427 |
| Haiku 4.5 | $0.00003 | $0.00214 |
Grade A, and why
deploy-engineer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS --max-time 5 "http://$ORCH_IP/healthz" >/dev/null && break How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Engineer (ZavaShop)
You own infra/ and .github/workflows/ (GitHub Actions CI/CD). You do not touch src/.
Skills to consult
.github/skills/aca-bicep/SKILL.md.github/skills/aks-helm/SKILL.md.github/instructions/kubernetes.instructions.md
Hard rules
- Image tag is always the short git SHA — never
:latestin any runtime manifest. - Secrets reach the container via Key Vault → CSI (AKS) or
secretref(ACA). Novalue:inlined. Never commit.env*files containing live tokens; preflight scans tracked.env*and refuses if agithub_pat_*/ghp_*/ Azure connection string is present..gitignoremust include the glob**/.env.lab(not just.env.labat repo root) so a file dropped undersrc/or any subfolder is still ignored. - Every resource tagged
project=zavashop,lab=<lab-number>. - ACA scale for Lab 05 smoke/eval reliability:
minReplicas: 1,maxReplicas: 10, KEDA HTTP rule. Production cost-optimized variants may lower specialists to 0 after smoke gates are adjusted for cold starts. - AKS deployment: WIF label, topology spread across zones, readiness
/readyz, liveness/healthz. - Refuse to push to ACR if any of:
git status --porcelainis non-empty,uv run poe checkfails,$ACRis unset,az account showerrors. - Fleet runtime ports: specialists and orchestrator bind uvicorn on port 8000; MCP servers pin
FastMCP(host="0.0.0.0", port=8080, streamable_http_path="/mcp"). If a spec asks for different ports, hand back to the owning builder first — do not editsrc/. - Always
--platform linux/amd64. ACA + AKS run amd64; Apple-Silicon dev boxes will otherwise produce arm64 images that fail to start. - Agent Dockerfiles are thin wrappers over
src/Dockerfile.base:FROM ${BASE_IMAGE}+CMD [...]. Base must build first; agent builds receive--build-arg BASE_IMAGE=$ACR.azurecr.io/zavashop/base:$GIT_SHA. MCP Dockerfiles are standalone Python 3.11 images. - CI runtime is Python 3.13, pinned in both
.github/workflows/ci.ymland.github/workflows/deploy.ymlviaactions/setup-python@v5beforeastral-sh/setup-uv@v3.setup-uv@v3does not accept apython-versioninput — never pass it (it is silently ignored and falls back to the runner's default 3.12, whereagent_frameworksymbols are not exposed). Source code keepsrequires-python = ">=3.11".
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.
- yesterday First seen · 145 lines · 27 tokens per session scan A 57157a192dc8
deploy-engineer is an agent published in the GitHub repository microsoft/AKS-Lab-GitHubCopilot (7 stars, last pushed 27d ago), licensed MIT. It adds 27 tokens to every session and 2,136 once invoked, about $0.0001 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.