โฎ CHAPTER 1 โฎ
Playbook
โ THE AI DEV PLAYBOOK โ
A structured map of GitHub Copilot tools and ideas across the SDLC: planning, development, review, testing, security, and operations.
Introduction
ใฏใใใซ 3 items
๐ค Theo Monfort
A platform-level overview of GitHub and GitHub Copilot.
-
NO.01GitHub
The AI-native developer platform used by more than 180 million developers. From Pull Requests to GitHub Copilot, GitHub continues to shape the history of software development.
Read details -
NO.02GitHub Copilot
The world's most widely used AI development tool. An orchestrator offering the broadest choice of AI models and surfaces among its competitors.
Read details - ๐ฎNO.03
Hands-on
A workshop where you get hands-on with the concepts in this playbook by rebuilding a simplified version of this very playbook site from scratch โ together with Copilot. Touches MCP / Instructions / Agent Skills / Plan mode / Cloud Agent / Code Review / Agentic Workflow end-to-end.
Read details
Plan
ไผ็ป 7 items
๐ค Team Manager
Plan with Issues and Projects, then prepare the AI harness with MCP servers, instruction files, agent skills, and custom agents.
-
NO.04MCP Server
MCP Server (Model Context Protocol)
MCP is a method for providing additional context to AI models.
Read details - ๐NO.05
Instructions
Persistent rule files that give AI standing development guidelines at the repository or file level, so every teammate's Copilot follows the same conventions.
Read details - ๐ดNO.06
Agent Skills
Reusable instruction packs that teach Copilot agents how to handle specialized tasks โ loaded automatically when the request matches, no re-explaining required.
Read details - ๐ฅทNO.07
Custom Agent
A specialist profile that bundles role, tools, and behavior together for Copilot. Switch between Planner, Reviewer, and Tester personas with their own permissions.
Read details - ๐ชNO.7.5
Hooks
A mechanism for injecting custom scripts into the agent execution lifecycle (session start, prompt submission, pre/post tool execution, error, session end). Configured via `.github/hooks/hooks.json`. The most powerful hook is PreToolUse, which can deny specific commands (rm -rf, sudo, pushes to production, etc.) to block the agent. Works with both Copilot CLI and Cloud Agent.
Read details - ๐ก๏ธNO.08
Harness Engineering
The discipline of designing the scaffold that lets agents operate safely and effectively โ tools, constraints, permissions, and external connections.
Read details - ๐งNO.8.5
Context Engineering
The art of designing the context you pass to AI โ not too little, not too much, just the information needed to complete the task.
Read details
Develop
้็บ 6 items
๐ค Junior Developer
Code in shared Codespaces environments with Plan / Agent mode, Copilot Chat, and the CLI. Delegate work to Cloud Agent for parallel development.
- ๐ฌNO.3.5
Copilot Chat
The synchronous conversation surface for Copilot. Available across IDE, GitHub.com, and Mobile, with the deepest harness on the IDE side.
Read details - ๐ปNO.14
Copilot CLI
Copilot living in the terminal. An IDE-agnostic "colleague in the terminal" that lets you move between planning โ implementation โ review with just Shift+Tab.
Read details - โ๏ธNO.15
Cloud Agent
A "doppelganger" that works through the night even when you leave the IDE. Assign an Issue and it implements, verifies, and returns with a PR from a GitHub Actions runner.
Read details - ๐งฌNO.15.5
Third-party agents
A mechanism to launch coding agents other than Copilot โ such as Claude or Codex โ from VS Code and GitHub with the same feel as Copilot.
Read details -
NO.17GitHub Codespaces
Customizable remote development environments hosted in the cloud. The ideal AI-driven development playground for safely sandboxing AI experiments and work.
Read details - ๐ชNO.17.5
GitHub Copilot Spaces
A shared place to organize the context you want Copilot to use: code, issues, pull requests, docs, notes, images, uploads, and instructions that ground Copilot's answers.
Read details
Review
ใฌใใฅใผ 1 items
๐ค Senior Developer
Let Copilot perform automated code review so humans can focus on final judgment.
Test & Secure
ใในใ & ๅ่ณชไฟ่จผ 5 items
๐ค DevSecOps Engineer
Automate tests with GitHub Actions, and protect quality with Code Scanning, Secret Scanning, and Dependabot.
- โ๏ธNO.19.2
GitHub Actions
GitHub's native CI/CD and automation platform. Steps written in .github/workflows/*.yml run automatically on push / PR / schedule. Public repos are free; private repos get a free tier plus pay-as-you-go. Cloud Agent and Copilot Code Review also run on top of this.
Read details - ๐คNO.19.3
Dependabot
GitHub's official bot that monitors repository dependencies for vulnerabilities and opens automated fix PRs. Built on the dependency graph, it runs in three layers โ Security alerts, Security updates, and Version updates. Free for public and private repos.
Read details - ๐NO.19.4
Code Scanning
CodeQL statically analyzes source code for vulnerabilities, and Copilot Autofix generates fix PRs automatically. Default setup requires no config file โ just one click. Free for public repos; private repos need GHAS / Code Security.
Read details - ๐NO.19.6
Secret Scanning
GitHub's secret detection feature that automatically finds API keys and tokens mixed into commits, issues, PRs, and history. Push protection can block commits before they land. Free for public repos; push protection is also free for private repos on a per-user opt-in basis.
Read details - NO.19.8
GHAS
GitHub Advanced Security
GitHub's paid security product suite. Split into GitHub Secret Protection ($19) and GitHub Code Security ($30) in April 2025, billed per active committer. Public repos remain free.
Read details
Operate
้็จ 3 items
๐ค Whole Team
Automate operations with agentic workflows, visualize AI usage with Copilot Metrics, and accumulate knowledge through Memory.
- ๐NO.16
Agentic Workflow
A new kind of automation that runs AI agents on top of GitHub Actions. Write what you want done in natural language Markdown and get workflows that can reason and act.
Read details - ๐NO.18
Copilot Metrics
Metrics API and dashboard for visualizing GitHub Copilot usage and impact. Details coming soon.
Read details - ๐งNO.19
Copilot Memory
A mechanism for Copilot to remember and reuse knowledge learned while working in a repository, passing it on to future selves and the whole team. Gets smarter the more you use it.
Read details