🧭
Agentic AI & Agent Mode
Copilot Agent Mode
Copilot CLI & Terminal Agents
- Copilot CLI — terminal-native agentic development
- Enhanced agents, context management (Jan 2026)
- Four sub-agents: Explore, Task, Plan, Code-review with parallel execution
- Autopilot mode,
/compactcontext management,--resumesessions - Multi-model: Claude Sonnet 4.5 (default), GPT-5, GPT-4.1, Claude Opus 4.6
Copilot Spaces & Context
Custom Agents & agents.md
- Creating custom agents — file-based
.agent.mdprofiles - How to write a great agents.md — lessons from 2,500+ repos
- Scopes: repo (
.github/agents), org (.github-private), CLI (~/.copilot/agents) - Shareable across teams with custom prompts, tools, and MCP configs
Mission Control & Agent HQ
- Introducing Agent HQ — any agent, any way you work
- Mission Control: unified command center across GitHub, VS Code, mobile, CLI
- Fleet orchestration: assign agents work in parallel, steer mid-task
- Agent identity & access management (treat agents like team members)
- Integrations: Slack, Linear, Jira, Teams, Azure Boards, Raycast
- Third-party agents: Anthropic, OpenAI, Google, Cognition, xAI
🛡️
MCP (Model Context Protocol)
Registry & Guides
- GitHub MCP Registry launch
- MCP Tips best practices
- MCP Apps: interactive visualizations in VS Code chat (Jan 2026)
Security & Governance
- MCP Config Scan (Go) — audit configs for risky scopes
- Agent governance template — approvals, permissions, incident playbooks
- Agent guardrails: approvals, least privilege, blast-radius checks
Enterprise MCP Controls
- Internal MCP registry & allowlist controls
- Centrally curated trust boundaries for enterprise MCP servers
- Admin policies for which agents and MCP servers developers can use
📈
Developer Experience & Workflows
Assessment Tools
- AI-First Decision Tree — quick task assessment for AI approach
- Team Maturity Assessment — 5-minute scorecard
Workflow Foundations
Health Checks
- DX Health Check survey + AI analysis (this repo)
- Teaching Moments capture for continuous fluency
Agentic Code Review
- Copilot code review with agentic tool-calling (gathers full project context)
- Autonomous PR review capabilities for agent-authored code
- Risk-based review tiers: human-authored vs. agent-authored PRs
VS Code Agent Features (Jan 2026)
- VS Code v1.109 — multi-agent development hub
- Claude agent support (public preview) via Claude Agent SDK
- Copilot Memory: retains relevant context across interactions
- Terminal command sandboxing for agent-executed commands
🌐
The Ecosystem
Tools & Repos
- teamxray — VS Code expertise analysis (GitHub Models + MCP)
- open-source-best-practices — 8-phase OSS skill framework
- git-history-cleaner — safe history cleanup
Agent Context System
- Agent Context System — persistent context, multi-tool orchestration, 24/7 agent execution
- Highlights: context engineering, scoped permissions, autonomous task runners
📰
Main Branch Newsletter
🎤
Talks & Appearances
- GitHub Universe 2025 — panel with Justin Cormack (Docker) + Quincy Larson (freeCodeCamp)
- Commit Your Code Conference 2025 — hybrid human/AI workflows
- JFrog SwampUP 2025 — AI agent security risks and autonomy
- GitHub Universe LATAM Series — Universe announcements (Spanish)
- freeCodeCamp Podcast #199 — Tips from a Serial Career Changer
- RedMonk Conversation (Feb 2025) — onboarding beginners to Git with Kedasha Kerr
📊
Research & Data
- Deloitte: 25% of companies running agentic pilots in 2025; 50% by 2027.
- McKinsey: governance-first teams see +37% adoption success, -41% security issues.
- Microsoft: productivity gains arrive after ~11 weeks of steady use.
- GitHub Enterprise Research: structured sharing drives ~40% better outcomes.
- Octoverse 2025: 1.13M repos importing LLM SDKs (+178% YoY); Universe 2025 launched Agent HQ, Mission Control, Custom Copilot Agents.
- Agent HQ multi-model fleet: Anthropic, OpenAI, Google, Cognition, xAI agents on one platform via Copilot subscription.
- Free users get core Mission Control dashboard + basic agent features by Q1 2026.
- 2,500+ repos with agents.md analyzed — custom agents becoming standard practice.