Use it when editing the project’s Jekyll site, Markdown guides, Mermaid diagrams, navigation, or custom styles.

It gives contributors shared rules for writing and maintaining the project. This helps keep documentation structure, diagrams, navigation, and technical examples consistent.

How microsoft/Microsoft-AI-Decision-Framework configures GitHub Copilo

Q: What is Microsoft-AI-Decision-Framework copilot-instructions.md?

A project-wide instruction guide for a Microsoft AI technology decision framework. It describes a Jekyll documentation site, Markdown content, Mermaid diagrams, navigation, styling, and related project conventions.

About the project

Microsoft AI Decision Framework is a guide for choosing among Microsoft AI products such as Microsoft 365 Copilot, Copilot Studio, Azure AI Foundry, and Agent Service. Organizations use it to match an AI technology to their data, permissions, channels, responsibilities, and operational needs. The catalogue entries provide agents and instructions for applying the framework.

microsoft/Microsoft-AI-Decision-Framework · 103 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to microsoft/Microsoft-AI-Decision-Framework. 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/microsoft/Microsoft-AI-Decision-Framework/main/.github/copilot-instructions.md

Clone the repo

git clone --depth 1 https://github.com/microsoft/Microsoft-AI-Decision-Framework

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/microsoft/microsoft-ai-decision-framework/copilot-instructions/github.svg)](https://agentmods.dev/instructions/microsoft/microsoft-ai-decision-framework/copilot-instructions)

Your own site

<a href="https://agentmods.dev/instructions/microsoft/microsoft-ai-decision-framework/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/microsoft-ai-decision-framework/copilot-instructions/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/microsoft/microsoft-ai-decision-framework/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/microsoft/microsoft-ai-decision-framework/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,340 This file is loaded in full into every session.

When invoked 5,340 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	$0.05340	$0.05340
Opus 5.5	$0.02136	$0.02136
Sonnet 5.5	$0.01068	$0.01068
Haiku 4.5	$0.00534	$0.00534

Measured 10d ago against content hash aee050034501, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Microsoft-AI-Decision-Framework copilot-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 10d ago.

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/copilot-instructions.md · 326 lines

How it starts

The opening of the file, as written. The whole thing — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microsoft AI Decision Tree - Copilot Instructions

Project Overview

This is a comprehensive decision framework and reference guide for navigating Microsoft's AI technology portfolio. The project helps users systematically evaluate and select the right Microsoft AI technology (M365 Copilot, Copilot Studio, Microsoft Foundry, Agent Service, SDKs, etc.) for their specific business requirements.

Primary Goal: Enable evidence-based technology selection through a structured learning journey that progresses from foundational concepts to technical mastery.

Target Audience: Technical decision-makers, architects, developers, and business stakeholders evaluating Microsoft AI technologies for enterprise use cases.

Technology Stack

Static Site Generator: Jekyll 4.4+ (GitHub Pages)
Documentation Format: Markdown (.md files)
Diagrams: Mermaid 11.12.1 flowcharts (embedded in Markdown, authored with the dark theme and inline node colors; the site re-renders them to match the reader's light or dark theme and keeps the inline colors)
Navigation: Jekyll front matter with nav_order property (1-16)
Theme: Just the Docs (remote_theme pinned to a release in _config.yml), color scheme aidf: light and dark themes via CSS custom properties, with a Light / Dark / System switch in the header (default: follow the OS)
Custom Styling: SCSS in _sass/custom/custom.scss (tokens and components; no Mermaid overrides; palette is owned inline in diagrams). The visual system is documented in .agents/context/DESIGN.md
Ruby Gems: jekyll-remote-theme, jekyll-seo-tag, jekyll-github-metadata, jekyll-include-cache, webrick
Deployment: GitHub Pages at https://microsoft.github.io/Microsoft-AI-Decision-Framework/

Project Structure & Architecture

Documentation Organization (Core Files)

The documentation follows a progressive learning flow designed to build knowledge systematically:

README.md (nav_order: 1) - Landing page with learning paths
docs/capability-model.md (nav_order: 2) - Foundation - Buckets, the agent checkpoint, and how to describe behavior before naming a product
docs/ai-stack.md (nav_order: 3) - Landscape - The buy-before-build ladder, five capability groupings, shared vocabulary, and the five planes
docs/decision-framework.md (nav_order: 4) - Methodology - Storybook flow & 9 questions
docs/scenarios.md (nav_order: 5) - Context - Real-world use cases
docs/evaluation-criteria.md (nav_order: 6) - Assessment - Complexity, skills, budget, governance
docs/implementation-patterns.md (nav_order: 7) - Execution - Architecture patterns
docs/technologies.md (nav_order: 8) - Deep Dive - Technical specifications
docs/feature-comparison.md (nav_order: 9) - Mastery - Side-by-side matrices
docs/visual-framework.md (nav_order: 10) - Application - Mermaid decision tree diagrams
docs/quick-reference.md (nav_order: 11) - Reference - Fast lookup tables
docs/ai-instinct.md (nav_order: 12) - Companion - The human framework
docs/agentic-engineering.md (nav_order: 13) - Companion - Vibe coding, vibe engineering, and agentic engineering
docs/resources.md (nav_order: 14) - Reference - External links
docs/glossary.md (nav_order: 15) - Reference - Terminology
docs/visual-explorer.md (nav_order: 16) - Reference - Interactive decision explorer

Read the full file on GitHub · 326 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.

10d ago Changed · +1 lines · +68 tokens per session aee050034501
1mo ago Changed · +84 tokens per session c7fb753a28ec
2mo ago First seen · 325 lines · 5,188 tokens per session scan A 2659398511ed

Subscribe to this mod's changes

Microsoft-AI-Decision-Framework copilot-instructions.md is an instructions file published in the GitHub repository microsoft/Microsoft-AI-Decision-Framework (103 stars, last pushed 2d ago), licensed MIT. It adds 5,340 tokens to every session, about $0.0214 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 2026-08-30.

Microsoft-AI-Decision-Framework copilot-instructions.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Microsoft-AI-Decision-Framework copilot-instructions.mdmicrosoft/Microsoft-AI-Decision-Framework	Instructions file	103	2d ago	MIT	A	5,340	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
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

Microsoft-AI-Decision-Framework: Instructions file for GitHub Copilot