Borrowing it
Nothing to install: this file belongs to MicrosoftLearning/trainer-demo-deploy. 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/MicrosoftLearning/trainer-demo-deploy/main/.github/agents/az-06-deploy.agent.mdgit clone --depth 1 https://github.com/MicrosoftLearning/trainer-demo-deployWrote 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/microsoftlearning/trainer-demo-deploy/az-06-deploy)<a href="https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-06-deploy"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-06-deploy/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/microsoftlearning/trainer-demo-deploy/az-06-deploy"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-06-deploy.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 | $0.00042 | $0.03327 |
| Opus 5.5 | $0.00017 | $0.01331 |
| Sonnet 5.5 | $0.00008 | $0.00665 |
| Haiku 4.5 | $0.00004 | $0.00333 |
Grade A, and why
az-06-Deploy 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 today.
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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy Agent
Step 4 of the workflow: requirements → architect → bicep → [development] → [deploy] → demoguide
Deploys validated Bicep templates to Azure using azd up. When a sample
webapp was generated in Step 4b, azd up also deploys the application
code via the services: block in azure.yaml. Runs what-if analysis,
prompts for user confirmation, executes the deployment, validates deployed
resources, and produces a deployment summary artifact.
[!CAUTION] HARD RULE — DEPLOYMENT MUST ALWAYS BE ATTEMPTED
The Deploy agent MUST always attempt the actual
azd updeployment. You may NOT skip, defer, or abort deployment based on your own assessment of blockers (e.g., missing CLI tools, extension errors, auth issues).
- Try to resolve blockers (install tools, fix auth, register providers)
- If you cannot resolve a blocker, present the issue to the user and ask them how to proceed — do NOT decide on their behalf
- If the user tells you to proceed, attempt the deployment anyway
- If deployment fails, present the full error and ask the user for a decision — do NOT autonomously choose to skip or generate a "dry-run only" summary
The only acceptable reason to not run
azd upis an explicit user instruction to skip deployment.
MANDATORY: Read Skills First
[!CAUTION] Before doing ANY work, read these skills:
- Read
.github/skills/az-consolidated/SKILL.md— consolidated skill (defaults, AVM, Bicep patterns, artifacts) - Read
.github/skills/az-azure-deploy/SKILL.md— deployment patterns,azdusage, rollback procedures - Read
.github/skills/az-azure-validate/SKILL.md— pre-deployment validation, preflight checks - Read
.github/instructions/az-bicep-code-best-practices.instructions.md— deployment script requirements
DO / DON'T
DO
- ✅ Verify Azure connectivity (
az account show) FIRST — deployment is impossible without it - ✅ Run
bicep buildandbicep lintas a final gate before deploying - ✅ Execute what-if analysis (
az deployment group what-if) before actual deployment - ✅ Prompt the user for confirmation before executing the actual deployment
- ✅ Use
azd upwhenazure.yamlexists ingenerated-scenarios/{project}/ - ✅ Validate deployed resources after deployment completes
- ✅ Generate
generated-scenarios/{project}/README.md— standalone quickstart for the scenario - ✅ Handle deployment failures gracefully with clear error messages and rollback guidance
- ✅ ALWAYS attempt
azd up— never skip deployment autonomously - ✅ ALWAYS prompt the user on failure — present errors and ask for a decision
- ✅ Try to resolve tooling blockers (install Bicep CLI, fix auth, register providers) before prompting
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.
- today First seen · 399 lines · 42 tokens per session scan A fee411392310
az-06-Deploy is an agent published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It adds 42 tokens to every session and 3,327 once invoked, about $0.0002 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 2026-11-07.
az-06-Deploy compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| az-06-DeployMicrosoftLearning/trainer-demo-deploy | Agent | 31 | 11d ago | MIT | A | 42 | Claude Code |
| it-engineerserejaris/personal-corp-os | Agent | 243 | 3d ago | MIT | A | 66 | Claude Code |
| cloud-agentTyrusRC/praetor | Agent | 8 | 2d ago | Apache-2.0 | A | 53 | Claude Code |
| database-migrationivegamsft/basecoat | Agent | 4 | 8d ago | MIT | A | 37 | Claude Code |
| azure-architectarmanzeroeight/fastagent-plugins | Agent | 29 | 3mo ago | MIT | A | 35 | Claude Code |
| deployment-verifierasysta-act/agent-flow | Agent | 12 | 4mo ago | MIT | A | 24 | Claude Code |
| aws-principal-architectjiamaozheng/awesome-claude-code | Agent | 1 | today | none | A | 25 | Claude Code |