GitHub's May release cycle for Copilot in VS Code moves the editor closer to an agent-first workspace. The Agents window is now in Stable as a preview, while remote agents, session sync, BYOK model routing, and terminal safety controls make longer-running coding sessions easier to govern.

This is useful news for teams comparing local IDE agents with cloud agents: VS Code is becoming a command center for multiple sessions, changed-file search, screenshots, and model selection rather than only a chat sidebar.

Field|Current evidence
Primary source|GitHub: GitHub Copilot in Visual Studio Code, May releases
Source date|2026-06-03
Update scope|VS Code agent sessions, BYOK controls, sync, browser, and terminal safety
Verification note|Official source only; no search-result scraping, no ranking guarantee, no uncited claims

This update matters because the editor is moving from one chat pane to a multi-session control surface. The Agents window, changed-file search, screenshots, and session sync make it easier to compare work across agent attempts without leaving VS Code. BYOK support also changes procurement because teams can route work through approved model vendors.

Teams evaluating Copilot should test the full session lifecycle: start an agent task, inspect files changed, check terminal commands, resume the session on another machine, and confirm which model handled the work. That workflow is more important than a single prompt demo.

The decision point is whether VS Code should become the main operator console for agentic development. If developers already live in VS Code, these controls may reduce tool switching; if governance lives elsewhere, the team still needs audit exports and policy alignment.

Limits and open questions: the changelog does not settle enterprise rollout timing, default BYOK cost controls, or how every terminal safeguard behaves in complex repositories. Those claims should be verified against product docs or admin-console evidence before publication. Source handling note: KyenAI records the publisher, publication date, and source URL on the page, then keeps the update date tied to evidence-backed edits rather than automatic refreshes. When source material is thin, the system keeps interpretation narrow and waits for stronger documentation. Editorial review compares the new claim against the article summary, fact table, internal links, and listed source before allowing another optimization pass. Search outcomes are measured after publication rather than assumed at writing time.

GitHub's June 3 changelog highlights the Agents window preview, BYOK controls, session sync, terminal safety, and integrated browser improvements in VS Code.

GitHub Copilot in Visual Studio Code, May releases

GitHub Brings Agent-First Workflows Deeper into VS Code Stable

GitHub Copilot CLI now has a refreshed terminal surface and a rubber duck agent that can critique plans, implementation, or tests before the main agent continues.

Prompt scheduling with /every and /after points toward terminal agents that keep checking builds, usage, or repo state over time. Voice input is local, which matters for teams evaluating privacy and developer ergonomics.

Field|Current evidence
Primary source|GitHub: Copilot CLI: Improved UI, rubber duck, prompt scheduling, and voice input
Source date|2026-06-02
Update scope|terminal agent review, scheduled prompts, local voice input, and CLI ergonomics
Verification note|Official source only; no search-result scraping, no ranking guarantee, no uncited claims

The notable change is the critic agent inside a terminal workflow. Rubber duck review creates a second pass before the main agent continues, which can catch weak plans, missing tests, or risky implementation shortcuts. Scheduled prompts also move CLI agents toward monitoring work, not only answering one command at a time.

For teams, the first evaluation should be operational rather than theatrical: schedule a build check, ask the critic to review a migration plan, and inspect whether the CLI produces auditable output. Voice input is useful only if it fits the team's privacy, accessibility, and workstation norms.

This update is strongest for developers who prefer terminal-first workflows. It is less decisive for organizations that need centralized review logs, because prompt scheduling and critic behavior still need policy and retention boundaries.

Limits and open questions: the source does not prove reliability across shells, operating systems, or private repositories. Claims about productivity gains should wait for measured before-and-after data from real teams. Source handling note: KyenAI records the publisher, publication date, and source URL on the page, then keeps the update date tied to evidence-backed edits rather than automatic refreshes. When source material is thin, the system keeps interpretation narrow and waits for stronger documentation. Editorial review compares the new claim against the article summary, fact table, internal links, and listed source before allowing another optimization pass. Search outcomes are measured after publication rather than assumed at writing time.

GitHub's Copilot CLI refresh adds a redesigned terminal experience, a critic agent, scheduled prompts, and local voice input.

Copilot CLI: Improved UI, rubber duck, prompt scheduling, and voice input

Copilot CLI Adds Rubber Duck Review, Prompt Scheduling, and Voice Input

GitHub's June 2 changelog says the Copilot SDK is now generally available with a stable API and production-ready support. The SDK exposes the agentic runtime behind Copilot for planning, tool invocation, file edits, streaming, and multi-turn sessions.

The strongest signal for developer-platform teams is language and tool coverage: GitHub lists SDK support across Node.js, Python, Go, .NET, Rust, and Java, plus custom tools, MCP connections, OpenTelemetry tracing, cloud sessions, and hook points.

Field|Current evidence
Primary source|GitHub: Copilot SDK is now generally available
Source date|2026-06-02
Update scope|stable Copilot SDK APIs, agent runtime embedding, tools, MCP, tracing, and hooks
Verification note|Official source only; no search-result scraping, no ranking guarantee, no uncited claims

The important shift is that Copilot's agent loop is no longer limited to GitHub-owned surfaces. A stable SDK gives platform teams a supported way to put planning, file edits, tool calls, and streaming sessions inside internal products without rebuilding orchestration from scratch.

Teams should evaluate the SDK as infrastructure, not a demo widget. The checklist is authentication, BYOK policy, tool permissions, trace export, session persistence, and whether custom tools can be audited when the agent acts across repositories or services.

This update is most relevant if a team wants agentic workflows inside its own developer portal, CI assistant, or internal automation. If the team only needs editor help, existing Copilot surfaces may be enough.

Limits and open questions: general availability does not prove fit for every regulated environment, and the source does not publish customer-specific reliability or cost data. Those claims should wait for implementation evidence. Source handling note: KyenAI records the publisher, publication date, and source URL on the page, then keeps the update date tied to evidence-backed edits rather than automatic refreshes. When source material is thin, the system keeps interpretation narrow and waits for stronger documentation. Editorial review compares the new claim against the article summary, fact table, internal links, and listed source before allowing another optimization pass. Search outcomes are measured after publication rather than assumed at writing time.

GitHub made the Copilot SDK generally available, giving teams a supported way to embed Copilot's agent runtime into apps, services, and developer tools.

Copilot SDK is now generally available

GitHub Copilot SDK Reaches General Availability

Evidence-backed guidance for AGENTS.md, CLAUDE.md, Copilot instructions, and Cursor rules.

Agent Instructions

List AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, .github/instructions/*.instructions.md, .cursorrules, and .cursor/rules/*.mdc, then record the exact agent surfaces expected to read each file.

Inventory files and surfaces

Choose the maintained source for setup, architecture, security, edit boundaries, tests, and review rules. Mark generated or manually synchronized adapters so maintainers know which wording is authoritative.

Define the canonical shared policy

Place Codex guidance in AGENTS.md, Claude Code guidance in CLAUDE.md, broad Copilot guidance in .github/copilot-instructions.md, and current Cursor guidance in focused .cursor/rules/*.mdc files.

Create documented adapters

Translate the deprecated .cursorrules file into scoped .mdc rules, preserve it during comparison, and remove it only after observed behavior and repository checks support the change.

Migrate Cursor rules safely

Use the same clean repository state, task, prompt, permissions, and verification criteria for every tool. Record versions and mark unavailable success, elapsed time, cost, or human-intervention data as Not measured.

Run a controlled comparison

Current instruction-file decision table

Use AGENTS.md with Codex

AGENTS.md open format and supported-agent ecosystem

Claude Code memory documentation

GitHub Copilot custom instructions support matrix

Adding custom instructions for GitHub Copilot

Cursor rules documentation

Cursor CLI instruction-file support

Configuration Smells in AGENTS.md Files

Compare CLAUDE.md, .github/copilot-instructions.md, AGENTS.md, and Cursor rules by tool surface, scope, and safe sync policy.

AGENTS.md vs CLAUDE.md vs Copilot Instructions

Saying Copilot reads or ignores CLAUDE.md everywhere

Deleting .cursorrules without a migration check

Copying a shared policy until adapters drift

Publishing zeros or estimates as benchmark data

Use this support matrix to decide whether CLAUDE.md, Copilot instructions, AGENTS.md, or Cursor rules should carry repository guidance for each tool surface.

AGENTS.md vs CLAUDE.md vs Copilot Instructions: Which File Should You Use?

Start with the project purpose, commands, safe boundaries, and review expectations.

Write the root file

Run the listed commands once so the agent does not inherit broken instructions.

Test every command

Use nested AGENTS.md files for monorepo packages, generated folders, or high-risk areas with different rules.

Add folder-specific notes only when needed

Name the person or team that updates instructions when CI, package managers, or release flow changes.

Add a drift owner

AGENTS.md template blocks

OpenAI Codex AGENTS.md documentation

GitHub Copilot custom instructions

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

Copy tested AGENTS.md templates for Codex, Node.js, Python and monorepos. Includes setup commands, test rules, safe edit boundaries and review checks.

AGENTS.md Template for Codex: Node.js, Python & Monorepos

Writing a policy novel

Listing commands nobody runs

Hiding secrets in instructions

Build, audit, copy, and download concise AGENTS.md starters for Codex, Node.js, Python, and monorepos with commands, boundaries, and review checks.

AGENTS.md Template for Codex and Monorepos

Write the repo purpose, shared commands, safe edit scope, generated folders, secret policy, and completion standard.

Choose the root baseline

Swap npm, pnpm, pytest, build, lint, and browser-check examples for commands that actually pass in the repository.

Replace placeholders

Create folder-level AGENTS.md files when a package has different commands, owners, generated files, or approval rules.

Add nested files only where needed

Run one small Codex task that depends on the file and confirm the agent used the expected command and respected the boundary.

Test the instruction

Which AGENTS.md example should you use?

AGENTS.md repository

Copy AGENTS.md examples for Codex projects, including Node.js apps, Python services, monorepos, nested files, commands, and review rules.

AGENTS.md Examples for Codex, Node.js, Python

Copying examples without testing commands

Making nested files too long

Turning AGENTS.md into a secrets file

Copy practical AGENTS.md patterns for Codex projects, including Node.js apps, Python services, and monorepos with nested package instructions.

AGENTS.md Examples for Codex: Node.js, Python and Monorepos

Write down whether the team uses IDE Chat, GitHub web tasks, coding agent flows, code review, CLI, or organization-level instructions.

List active Copilot surfaces

Compare AGENTS.md, CLAUDE.md, .github/copilot-instructions.md, and path-specific instructions against the current support matrix.

Map files to each surface

Put Copilot-wide repository rules in .github/copilot-instructions.md, then keep Claude-specific memory in CLAUDE.md.

Set the broad baseline

Ask each surface to perform a small task that depends on one instruction, then record whether it followed the expected rule.

Run a tiny behavior check

CLAUDE.md support decision table

Custom instructions support in GitHub Copilot

Add repository custom instructions for GitHub Copilot

Claude Code memory

Check when GitHub Copilot reads CLAUDE.md, when to use copilot-instructions.md, and which Copilot surfaces need each file.

Does GitHub Copilot Read CLAUDE.md? Surface Matrix

Using CLAUDE.md as the only Copilot file

Saying Copilot never reads CLAUDE.md

Letting adapters drift

GitHub Copilot support for CLAUDE.md is surface-specific. Use the GitHub support matrix before relying on it, and keep .github/copilot-instructions.md as the broad Copilot baseline.

Does GitHub Copilot Read CLAUDE.md? Support Matrix by Surface

Match your coding tool to its documented instruction path before comparing counts or content.

Choose the exact surface

State whether a percentage uses readable files, sampled files, unique sample repositories, or GitHub file matches.

Preserve the denominator

Check for setup, tests, verification, scope, and security rules with the downloadable categories.

Audit your repository

Run the generator with a GitHub token, record the new date, and compare like-for-like queries.

Reproduce or extend

Instruction-file snapshot by surface

REST API endpoints for search: Search code

Understanding GitHub Code Search syntax

See GitHub match counts and a 400-file sample of AGENTS.md, CLAUDE.md, Copilot instructions, and Cursor rules. Download the raw CSV and JSON.

AI Agent Instruction File Adoption: GitHub Data Report

Calling file matches an adoption rate

Treating best-match results as random

Equating absence with failure

Citing a live number without a date

Explore a reproducible public GitHub snapshot of 400 AGENTS.md, CLAUDE.md, Copilot instruction, and Cursor rule files, including indexed match counts, language mix, test commands, security rules, and common gaps.

Agent Instructions

Core guides

Evidence updates