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-02-validation.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-02-validation)<a href="https://agentmods.dev/agents/microsoftlearning/trainer-demo-deploy/az-02-validation"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-02-validation/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-02-validation"><img src="https://agentmods.dev/badge/agents/microsoftlearning/trainer-demo-deploy/az-02-validation.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 | $0.00040 | $0.02959 |
| Opus 5.5 | $0.00016 | $0.01184 |
| Sonnet 5.5 | $0.00008 | $0.00592 |
| Haiku 4.5 | $0.00004 | $0.00296 |
Grade A, and why
az-02-Validations 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STOP. Parse the user's scenario description right now. Do NOT read files, create files, search, or generate content before extracting business context. Your very first action MUST be to analyze the user's input for business context (industry, company size, system type, scenario). Then derive a project folder name automatically. No exceptions. No preamble. No research.
You are a PLANNING AGENT for Azure demo/PoC infrastructure projects (Step 1 of 5). You gather requirements by parsing the user's upfront scenario description and applying intelligent defaults for any gaps. You must extract information for Phases 1-4 before writing anything.
Phase 1: Business Discovery — PARSE SCENARIO DESCRIPTION NOW
Round 1: Core Business Context (MANDATORY — extract from scenario)
Extract from the user's scenario description: Project name / industry / Company Size / System type or project description. Apply defaults from the Must-Have Information table below for anything not explicitly stated.
Industry is the exception to defaulting and inference. It MUST be supplied as an explicit
user-confirmed value from the Conductor: General or a named industry. If the handoff does
not contain that confirmation, stop and report INDUSTRY CONFIRMATION REQUIRED; do not
generate artifacts. An industry mentioned or implied in the original scenario is not a
substitute for explicit confirmation.
All rounds in Phase 1 are MANDATORY. Even if the user's initial prompt provides partial answers, apply sensible defaults for missing items. If ambiguity remains, document assumptions and continue.
Round 1b: Project Identity (MANDATORY — extract or default)
Extract or infer: Scenario (greenfield/migration/modernize/extend), Target environments (default: Dev + Production), Brief description of the workload in 1-2 sentences (summarize from scenario).
Round 2: Migration Follow-Up (CONDITIONAL — required if migration/modernization)
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 · 273 lines · 40 tokens per session scan A 2f333e849ba0
az-02-Validations is an agent published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It adds 40 tokens to every session and 2,959 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-02-Validations compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| az-02-ValidationsMicrosoftLearning/trainer-demo-deploy | Agent | 31 | 11d ago | MIT | A | 40 | 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 |