GitHub Copilot Usage Metrics API Now Shows Custom Skills Names

Disclosure: this post contains affiliate links. If you buy through them we may earn a commission at no extra cost to you. Learn more.

TL;DR: GitHub has updated its Copilot usage metrics API to display the actual configured names of custom skills, agents, Model Context Protocol servers, slash commands, and plugins created by organizations. The update also increases the number of entries shown per category from five to 25, giving administrators better visibility into which internal customizations developers are actually using.

What's New

GitHub has released a significant enhancement to its Copilot usage metrics API that gives enterprise and organization administrators much clearer visibility into how developers use custom tools. Previously, custom skills, agents, Model Context Protocol (MCP) servers, slash commands, and plugins created by organizations were grouped under generic labels like "other" or "custom" in usage reports.

Now, these metrics display the actual configured names of customer-defined items. This change applies across all enterprise and organization reports, including per-user 1-day and 28-day reports, aggregated 1-day reports, and day_totals in aggregated 28-day reports. The new named entries appear in the totals_by_skill, totals_by_custom_agent, totals_by_mcp, totals_by_slash_cmd, and totals_by_plugin arrays.

GitHub has also expanded the number of entries visible in each category. Previously limited to five entries per record, each totals_by_* list now includes up to 25 entries, providing much deeper insight into the long tail of customizations that developers use. Any remaining activity beyond the top 25 is combined into a trailing "other" entry.

The update builds on agentic CLI customization metrics that GitHub released in September. While the presentation has changed, the underlying calculation methods remain the same—interaction_count and distinct_*_use_count fields continue to be calculated as before.

Names are reported from multiple sources including Copilot CLI (both interactive sessions and prompt mode), the GitHub Copilot app, Agent Client Protocol (ACP) integrations such as JetBrains, and the Copilot SDK. However, specific version requirements apply: prompt mode, the app, and ACP integrations require Copilot CLI 1.0.97 or later, while the Copilot SDK requires v1.0.21 or later. IDEs report names when their agent experiences run on Copilot SDK v1.0.21 or later, though names aren't reported from an IDE's built-in chat telemetry.

Pricing and Availability

This enhancement is available now to GitHub Copilot enterprise and organization customers. Reports are accessible to enterprise owners and billing managers, organization owners, and anyone with a custom organization or enterprise role that grants the "View Copilot Metrics" permission. The Copilot usage metrics policy must be enabled for access.

The feature was released on October 22, 2026, and names appear starting with report days processed after this release. Earlier days still show "other" or "custom" in the historical data.

How to Try It

Administrators can access the updated metrics through the Copilot usage metrics API. To get started, visit the Copilot usage metrics API documentation on GitHub. Ensure that your organization has the Copilot usage metrics policy enabled and that you have the appropriate permissions to view Copilot metrics.

For names to appear in reports, client versions must meet minimum requirements: Copilot CLI 1.0.97 or later, or Copilot SDK v1.0.21 or later. Names are reported as configured, trimmed and limited to 128 characters. GitHub notes that names looking like file paths will stay grouped under "other" or "custom," and recommends reviewing names before sharing reports outside your organization.

Who It's For

This update is designed for enterprise and organization administrators who need to track adoption and usage of internal development tools. According to GitHub, "The customizations that matter most to an organization are often the ones its own teams build." With named metrics, administrators can see which internal skills, custom agents, and MCP servers developers actually use, track adoption after rolling out a new tool, and focus enablement efforts where they're most needed.

The feature is particularly valuable for organizations investing in custom Copilot extensions and wanting to measure their impact and adoption rates across development teams.

Alternatives

For organizations seeking analytics and automation capabilities, Make offers workflow automation that can complement development metrics tracking. Apify provides web scraping and automation tools for data collection needs.

GitHub notes that these metrics come from client telemetry and can undercount activity when clients are outdated or telemetry is blocked. The company recommends using these metrics to understand trends and adoption rather than for exact accounting purposes.