trainer-demo-deploy: Agent for Claude Code

.github/agents/az-01-conductor.agent.md

az-01-conductor is an agent for Claude Code from MicrosoftLearning/trainer-demo-deploy. It costs 50 tokens per session (3,187 once invoked), scanned A, original, MIT.

An orchestration agent for an Azure demo-building workflow. It coordinates specialized steps for validation, architecture, design, Bicep infrastructure, development, deployment, and a demo guide.

In plain words
What is it for?
Use it to turn a scenario into a structured Azure demo project, run the development stages, and attempt deployment with azd.
Why use it?
It removes the need to manually coordinate these workflow stages and their handoffs while building an Azure demonstration project.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions subagents; Copilot chat-mode frontmatter (tools: vscode/*).

This is MicrosoftLearning/trainer-demo-deploy's own configuration. It tells Claude Code how to work on trainer-demo-deploy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything trainer-demo-deploy configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/MicrosoftLearning/trainer-demo-deploy/main/.github/agents/az-01-conductor.agent.md
Clone the repo
git clone --depth 1 https://github.com/MicrosoftLearning/trainer-demo-deploy

Made for: Claude Code.

Wrote 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.

agentmods badge for az-01-conductor

README.md
[![agentmods](https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-01-conductor/github.svg)](https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-01-conductor)
Your own site
<a href="https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-01-conductor"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-01-conductor/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.

agentmods 80×15 button for az-01-conductor

Your own site · 80×15
<a href="https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-01-conductor"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-01-conductor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,187 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.03187
Opus 5.5 $0.00020 $0.01275
Sonnet 5.5 $0.00010 $0.00637
Haiku 4.5 $0.00005 $0.00319

Measured today against content hash 35f98d1ec283, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

az-01-conductor 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.

.github/agents/az-01-conductor.agent.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conductor Agent

Conductor for the Azure demo builder workflow.

[!CAUTION] HARD RULE — EXTRACT CONTEXT BEFORE YOU READ

Your very first action MUST be to parse the user's scenario description. Derive a kebab-case project folder name from the description and proceed without interactive confirmation.

  1. Parse scenario → derive project folder name automatically
  2. Create generated-scenarios/{project}/
  3. THEN read skills and delegate

MANDATORY: Read Skills (After Project Name, Before Delegating)

After deriving the project name, read:

  1. Read .github/skills/az-consolidated/SKILL.md — consolidated skill (defaults, artifacts, Bicep patterns, diagrams, demo guide)

Core Principles

  1. Autonomous Execution: Proceed through workflow steps automatically unless the user explicitly requests a pause
  2. Context Efficiency: Delegate heavy lifting to subagents to preserve context window
  3. Structured Workflow: Follow the 5-step process, tracking progress in artifacts
  4. Mandatory Deployment: The Deploy step (Step 5) MUST always attempt actual azd up — never skip it autonomously
  5. User Decides on Failure: If deployment fails, present the error to the user and ask for their decision — never autonomously skip or generate a dry-run summary
  6. Explicit Industry Choice: Always ask whether the user wants a specific industry; never infer or default one

DO / DON'T

DO

  • ✅ Continue automatically from one delegated step to the next
  • ✅ Delegate to subagents via #runSubagent for each workflow step
  • ✅ Track progress by checking artifact files in generated-scenarios/{project}/
  • ✅ Summarize subagent results concisely (don't dump raw output)
  • ✅ Create generated-scenarios/{project}/ directory at project start

DON'T

  • ❌ Read skills or templates before deriving the project folder name
  • ❌ Pause the workflow unless the user explicitly asks for a checkpoint
  • ❌ Modify files directly — delegate to the appropriate agent
  • ❌ Include raw subagent dumps — summarize and present key findings
  • ❌ Skip step sequencing or handoff order
  • ❌ NEVER skip the Deploy step (Step 5) — always delegate to the Deploy agent and let it attempt azd up
  • ❌ NEVER auto-advance past Deploy on failure — if the Deploy agent reports a failure, present the error to the user and wait for their decision before proceeding to DemoGuide

Read the full file on GitHub · 316 lines

Changes

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.

  1. today First seen · 316 lines · 50 tokens per session scan A 35f98d1ec283

Subscribe to this mod's changes

az-01-conductor is an agent published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It adds 50 tokens to every session and 3,187 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.

Related

az-01-conductor compared with agents from other repositories

az-01-conductor next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
az-01-conductorMicrosoftLearning/trainer-demo-deployAgent3111d agoMITA50Claude Code
it-engineerserejaris/personal-corp-osAgent2433d agoMITA66Claude Code
cloud-agentTyrusRC/praetorAgent82d agoApache-2.0A53Claude Code
database-migrationivegamsft/basecoatAgent48d agoMITA37Claude Code
azure-architectarmanzeroeight/fastagent-pluginsAgent293mo agoMITA35Claude Code
deployment-verifierasysta-act/agent-flowAgent124mo agoMITA24Claude Code
aws-principal-architectjiamaozheng/awesome-claude-codeAgent1todaynoneA25Claude Code