New to Claude Skills? Learn how to install them →

microsoft on GitHub

Policy and Managed Settings

OfficialFree

Streamline enterprise policy management for AI tools.

by microsoft188.6k stars on microsoft/vscode
3 views
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Policy and Managed Settings does

The Policy and Managed Settings skill is designed for developers and administrators who need to manage enterprise policies related to AI tools, including Copilot and other agents. This skill helps you determine the appropriate policy destination based on where the governed behavior is implemented, ensuring that your configurations align with best practices for runtime management and VS Code settings. It provides a structured approach to adding, modifying, or reviewing policies, making it easier to maintain compliance and governance in your organization.

When using this skill, you will follow a flowchart that guides you through the decision-making process for policy placement. This includes considerations for whether the behavior is executed in the SDK/runtime, the VS Code editor, or as part of an extension. By adhering to the guidelines provided, you can avoid common pitfalls, such as duplicating runtime parsers or mismatching policy types. The skill also emphasizes the importance of running specific commands after making changes to ensure that your policies are properly exported and integrated.

This skill is particularly useful for organizations that utilize AI tools extensively and require clear policies for their usage. It serves as a foundational resource for teams looking to implement or update their Copilot enterprise controls and maintain a structured policy framework. By following the provided documentation and guides, users can ensure that their policy management processes are efficient and compliant with organizational standards.

Overall, the Policy and Managed Settings skill is an essential tool for any developer or administrator tasked with overseeing AI tool governance, providing clarity and structure to the often complex landscape of policy management.

When to use it

Use this skill when adding or modifying policies for AI tools in an enterprise environment, especially when dealing with Copilot and other agents.

When not to use it

This skill may not be suitable for individual developers or small teams without complex policy management needs.

What you can build with it

Implementing New Copilot Controls

When introducing new enterprise controls for Copilot, use this skill to ensure they are properly governed.

Updating Existing Policies

Use this skill to review and modify existing policies for AI tools in your organization.

Compliance Audits

Leverage this skill during audits to verify that your policy management aligns with organizational standards.

How to install Policy and Managed Settings

View source

1. Install with the skills CLI

npx skills add microsoft/vscode/policy-and-managed-settings --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by microsoft

Adding an Enterprise Policy

Choose the policy destination by where the governed behavior is implemented, not by which team requested it. Most controls for Copilot agent behavior belong in the SDK/runtime rather than VS Code.

flowchart TD
	A[Enterprise control] --> P{Existing permission policy<br/>introduced before VS Code 1.133.0?}
	P -->|Yes| L[Pre-1.133 compatibility migration]
	P -->|No| B{Where is the governed behavior implemented?}

	B -->|Copilot runtime, tools, MCP,<br/>sandbox, or agent loop| R[SDK/runtime managed setting]
	B -->|VS Code editor or workbench| V[VS Code configuration policy]
	B -->|Extension-provided setting| E[Extension policy]
	B -->|Independent runtime and editor behavior| M[Split runtime/editor control]

Follow the matching guide:

General rules:

  • Runtime enforcement is authoritative for behavior executed inside the runtime.
  • Do not duplicate a runtime parser, matcher, or security decision in VS Code.
  • A VS Code policy is appropriate only for editor/workbench-owned behavior.
  • New Copilot enterprise controls should target the shared managed-settings/SDK model.
  • Run npm run export-policy-data for every VS Code or extension policy change. Never edit build/lib/policies/policyData.jsonc manually.

Deprecated and Historical Channels

Some policy channels remain supported for existing controls but are closed to new properties:

  • GitHub token/account policy data (IPolicyData fields consumed by AccountPolicyService) is deprecated for new controls. Do not add new entitlement or policy properties from the GitHub token. Existing fields remain for compatibility.
  • New Copilot enterprise controls use managed settings and runtime/SDK enforcement.
  • Pre-1.133 permission-policy translation is a bounded migration, not a reusable channel.

When another channel is deprecated, record the boundary here and keep implementation details in the relevant destination guide.

Supporting references:

Keep these guides contract-focused. Document contributor decisions and behavioral invariants; point to source rather than copying implementation that will drift.

Trust executable source and tests over planning documents.

Frequently asked questions about Policy and Managed Settings

Similar skills