Use them to inspect related projects and templates, consult Azure documentation through available tools, validate prior artifacts, and build confidence before implementation.

They reduce implementation mistakes caused by ignoring existing patterns, missing required inputs, or using the wrong output structure.

How MicrosoftLearning/trainer-demo-deploy configures GitHub Copilot

Q: What is trainer-demo-deploy az-agent-research-first.instructions.md?

Instructions requiring research before an agent creates files or changes a project, including workspace searches, templates, documentation, and input checks.

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/instructions/az-agent-research-first.instructions.md

Clone the repo

git clone --depth 1 https://github.com/MicrosoftLearning/trainer-demo-deploy

Made for: GitHub Copilot.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/microsoftlearning/trainer-demo-deploy/az-agent-research-first/github.svg)](https://agentmods.dev/instructions/microsoftlearning/trainer-demo-deploy/az-agent-research-first)

Your own site

<a href="https://agentmods.dev/instructions/microsoftlearning/trainer-demo-deploy/az-agent-research-first"><img src="https://agentmods.dev/badge/instructions/microsoftlearning/trainer-demo-deploy/az-agent-research-first/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/microsoftlearning/trainer-demo-deploy/az-agent-research-first"><img src="https://agentmods.dev/badge/instructions/microsoftlearning/trainer-demo-deploy/az-agent-research-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,059 This file is loaded in full into every session.

When invoked 1,059 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01059	$0.01059
Opus 5.5	$0.00424	$0.00424
Sonnet 5.5	$0.00212	$0.00212
Haiku 4.5	$0.00106	$0.00106

Measured today against content hash b518cb13d30b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trainer-demo-deploy az-agent-research-first.instructions.md 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/instructions/az-agent-research-first.instructions.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Research Requirements

MANDATORY: All agents MUST perform thorough research before implementation.

This instruction enforces a "research-first" pattern to ensure complete, one-shot execution without missing context or requiring multiple iterations.

Pre-Implementation Research Checklist

Before creating ANY output files or making changes, agents MUST:

Search workspace for existing patterns (generated-scenarios/, similar projects, templates)
Read relevant templates in .github/skills/az-azure-artifacts/templates/ for output structure
Query documentation via MCP tools (Azure docs, best practices)
Validate inputs - confirm all required artifacts from previous steps exist
Check consolidated skill in .github/skills/az-consolidated/SKILL.md
Achieve 80% confidence before proceeding to implementation

Research Workflow Pattern

<research_mandate> MANDATORY: Before producing output artifacts, run comprehensive research.

Step 1: Context Gathering (REQUIRED)

Use read-only tools to gather context without making changes:

# Workspace context
- semantic_search: Find related code, patterns, and documentation
- grep_search: Search for specific terms, resource names, patterns
- read_file: Read templates, existing artifacts, configuration files
- list_dir: Explore project structure

# Azure context (where applicable)
- Azure MCP tools: Query documentation, best practices, SKU info
- mcp_bicep_list_avm_metadata: Check Azure Verified Module availability

Step 2: Validation Gate (REQUIRED)

Before implementation, confirm:

Required inputs exist - Previous step artifacts are present and complete
Templates loaded - Output structure template has been read
Standards understood - Shared defaults and naming conventions reviewed
Azure guidance obtained - Relevant documentation queried

Step 3: Confidence Assessment

Only proceed when you have 80% confidence in your understanding of:

Read the full file on GitHub · 123 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.

today First seen · 123 lines · 1,059 tokens per session scan A b518cb13d30b

Subscribe to this mod's changes

trainer-demo-deploy az-agent-research-first.instructions.md is an instructions file published in the GitHub repository MicrosoftLearning/trainer-demo-deploy (31 stars, last pushed 11d ago), licensed MIT. It adds 1,059 tokens to every session, about $0.0042 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.

Building agents Research

trainer-demo-deploy az-agent-research-first.instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
trainer-demo-deploy az-agent-research-first.instructions.mdMicrosoftLearning/trainer-demo-deploy	Instructions file	31	11d ago	MIT	A	1,059	GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

trainer-demo-deploy: Instructions file for GitHub Copilot