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/prompts/run-conductor.prompt.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/commands/microsoftlearning/trainer-demo-deploy/run-conductor)<a href="https://agentmods.dev/commands/microsoftlearning/trainer-demo-deploy/run-conductor"><img src="https://agentmods.dev/badge/commands/microsoftlearning/trainer-demo-deploy/run-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.
<a href="https://agentmods.dev/commands/microsoftlearning/trainer-demo-deploy/run-conductor"><img src="https://agentmods.dev/badge/commands/microsoftlearning/trainer-demo-deploy/run-conductor.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 | $0.00009 | $0.01081 |
| Opus 5.5 | $0.00004 | $0.00432 |
| Sonnet 5.5 | $0.00002 | $0.00216 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
run-conductor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Conductor — End-to-End Workflow
Orchestrate the complete Azure infrastructure development workflow for a new project, delegating to specialized agents with automatic handoffs between each step.
Mission
Guide a project from business description through validated Bicep templates using the full agent pipeline: Requirements → Architect → Design → Bicep → Development (conditional) → Deploy → Demo Guide. All steps are required to have a successful project and do the handover to the user. After the final handoff, prompt the user to confirm the project run is complete.
Scope & Preconditions
- User describes their project in business terms or technical terms
- All artifacts are saved to
generated-scenarios/${input:projectName}/ - Bicep templates are saved to
generated-scenarios/${input:projectName}/infra/and should supportazd provision - Each step produces artifacts that feed the next step
- Proceed through workflow steps automatically unless the user explicitly pauses
Inputs
| Variable | Description | Default |
|---|---|---|
${input:projectName} |
Project name (kebab-case) | Required |
${input:projectDescription} |
Business or technical description of the workload | Required |
Workflow
Step 1: Requirements
Delegate to Requirements agent with the project description.
Wait for 01-requirements.md to be generated.
Automatically continue to Step 2 after requirements generation.
Step 2: Architecture Assessment
Delegate to Architect agent to review requirements and produce WAF assessment with cost estimates.
Automatically continue to the next step after architecture generation.
Step 3: Design Artifacts
Delegate to Design agent to generate architecture diagrams. Automatically continue to Step 4 after design generation.
Step 4: Bicep Templates
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 · 141 lines · 9 tokens per session scan A efad8414f9d6
run-conductor is a command published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It adds 9 tokens to every session and 1,081 once invoked, about $0.0000 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.
run-conductor compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| run-conductorMicrosoftLearning/trainer-demo-deploy | Command | 31 | 11d ago | MIT | A | 9 | Claude Code, GitHub Copilot |
| cost-optimizewshobson/agents | Command | 42k | 2d ago | MIT | A | 26 | Claude Code |
| deploybutterbase-ai/butterbase-skills | Command | 535 | 7d ago | MIT | A | 20 | Claude Code |
| envvercel/vercel-plugin | Command | 328 | yesterday | none | A | 35 | Claude Code |
| firebase-publishPierry/harness-kit | Command | 4 | 1mo ago | MIT | A | 20 | Claude Code |
| scanprajapatimehul/claude-aws-cost-saver | Command | 24 | 4mo ago | MIT | A | 6 | Claude Code |
| migrationdatabayt/hogwarts | Command | 18 | 4d ago | none | A | 4 | Claude Code |