Provides architectural guidelines and technical specifications for developing features within the Agents window environment.

Install

mkdir -p .claude/skills/sessions && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10393" && unzip -o skill.zip -d .claude/skills/sessions && rm skill.zip

Installs to .claude/skills/sessions

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Agents window architecture — covers the agents-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agents window.
232 chars✓ has a “when” trigger
Advanced

Key capabilities

  • Manage Agents window UI layout
  • Implement session provider interfaces
  • Apply layering and dependency injection
  • Develop chat widget and menu contributions

How it works

The skill enforces strict architectural rules, including layer hierarchy and dependency injection patterns, to ensure consistency across the Agents window codebase.

Inputs & outputs

You give it
Feature request or issue in Agents window
You get back
Updated UI component or session service implementation

When to use sessions

  • Develop new features in the Agents window
  • Fix issues within the agents-first app UI
  • Apply consistent layering in session code
  • Update UI layout controllers

About this skill

Agents Window development

Use this skill for implementation, review, or design work under src/vs/sessions/**.

1. Apply the core principles

  • Preserve the layer direction: vs/sessions may import vs/workbench and lower layers; vs/workbench must never import vs/sessions.
  • Keep shared Sessions code provider-neutral. Non-provider contributions must not import provider implementations.
  • Model mutable session and chat state with observables. Use events for notifications, not as a parallel state model or for control flow.
  • Register Sessions menu IDs in browser/menus.ts and consume Menus.*.
  • Import contributions from the appropriate sessions.*.main.ts entry point.
  • Prefer Sessions-owned adaptations over shared workbench changes unless the capability is genuinely shared.
  • Put stable architecture in the owning specification and concrete behavior in tests. Do not preserve implementation chronology as development guidance.

2. Identify the owning area

Start with src/vs/sessions/README.md, then read only the specifications relevant to the change:

AreaSpecification
Layering, folder ownership, cross-module importssrc/vs/sessions/LAYERS.md
Session/chat model, services, provider contract, core data flowsrc/vs/sessions/SESSIONS.md
Workbench parts, grid, title bar, editor presentationsrc/vs/sessions/LAYOUT.md
Session-aware layout state and restorationsrc/vs/sessions/LAYOUT_CONTROLLER.md
Single-pane behavior and expected compositionssrc/vs/sessions/SINGLE_PANE_SCENARIOS.md
Sessions sidebar list, grouping, filtering, and persistencesrc/vs/sessions/SESSIONS_LIST.md
Phone layout and mobile componentssrc/vs/sessions/MOBILE.md
AI customizationssrc/vs/sessions/AI_CUSTOMIZATIONS.md
Copilot customizationssrc/vs/sessions/copilot-customizations-spec.md
Copilot Chat providersrc/vs/sessions/contrib/providers/copilotChatSessions/COPILOT_CHAT_SESSIONS_PROVIDER.md
Agent Host providersrc/vs/sessions/contrib/providers/agentHost/AGENT_HOST_SESSIONS_PROVIDER.md
Remote Agent Host providersrc/vs/sessions/contrib/providers/remoteAgentHost/REMOTE_AGENT_HOST_SESSIONS_PROVIDER.md

Do not load the learning inbox by default. Search its headings and scopes, then read only matching entries after the authoritative specification.

3. Inspect before changing

  • Trace the current implementation and its existing tests.
  • Search for shared helpers, context keys, menu IDs, entry-point imports, and provider abstractions before adding new ones.
  • Confirm which layer owns the behavior. Keep provider-specific decisions in the provider and view/layout decisions in Sessions-owned browser code.
  • For UI work, also invoke the applicable accessibility, design, CSS, layout, or theming skill.
  • For agent, LLM, policy, permissions, telemetry, or managed-setting changes, invoke the applicable specialist skill before implementation.

4. Implement the contract

Apply the core principles and the focused specification. Prefer small changes that preserve these boundaries:

  • ISessionsManagementService owns model orchestration and provider routing.
  • ISessionsService owns visible and active session behavior.
  • Providers expose provider-neutral state through ISession and IChat.
  • Session state is observable; consumers derive UI state reactively.
  • Contributions load through the appropriate sessions.*.main.ts entry point.
  • Sessions menus use the shared Menus registry.
  • Shared workbench changes represent shared capability, not Sessions-specific policy.

Update a specification when its architecture or durable behavior changes. Do not add implementation chronology, rejected approaches, or bug narratives to a specification.

5. Validate proportionally

Run the smallest existing checks that cover the change:

  • focused unit tests for affected behavior;
  • npm run valid-layers-check when imports or module ownership change;
  • targeted type checking or compilation when TypeScript changes warrant it;
  • relevant integration, E2E, or visual validation for cross-process or UI work.

Documentation-only changes require link, path, and consistency checks rather than a full build.

6. Record feedback correctly

When a user explicitly corrects or rejects an approach, invoke the feedback-learning skill unless they use the literal learn! trigger. Literal learn! requests follow .github/instructions/learnings.instructions.md instead. A durable architecture invariant belongs in the owning specification, concrete behavior belongs in a regression test, and unproven reusable guidance belongs temporarily in the scoped learning inbox. Never append every correction to this skill.

7. Maintain this skill

Update this skill only when a principle is stable, cross-cutting, and useful for most Agents Window work, or when the routing/workflow itself changes. Put subsystem contracts in their focused specification and bug behavior in tests.

Keep the core-principles section at no more than ten bullets. Before adding one, merge overlap, remove obsolete guidance, and prefer rewriting an existing principle. Never append incident-specific details or use this skill as a learning log.

When not to use it

  • When modifying code outside of src/vs/sessions/
  • When using standard workbench menu IDs

Prerequisites

Read coding guidelines and source code organization instructions

Limitations

  • contrib/* must not import from contrib/providers/*
  • Session state must flow through IObservable, not Event

How it compares

It mandates adherence to specific internal specifications and ESLint-enforced import restrictions that differ from standard workbench development.

Compared to similar skills

sessions side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
sessions (this skill)026dNo flagsAdvanced
react-native-architecture552moReviewAdvanced
nextjs-best-practices316moNo flagsIntermediate
react-component-patterns329dNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by microsoft

View all by microsoft

Search skills

Search the agent skills registry