← AI PulseSep 17, 2026

Policy · news · Single-source brief

GitHub Copilot CLI Usage Metrics API Adds Agentic Activity Data

GitHub Copilot has expanded its Command Line Interface (CLI) report coverage to include agentic activity metrics for skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins.

By Illumora Editorial

Source · Sep 17, 2026, 9:08 PM · On Illumora · Sep 17, 2026, 9:58 PM

Media from the primary source — shown here so you can stay on Illumora.

Rewritten from one allowlisted primary — not independent enterprise reporting. Lanes →

Brief drafted by Illumora’s editorial model from the linked primary source. Ops desk reviews flagged pieces. How we write →

Read the source →GitHub Changelog (Copilot) — Agentic CLI customizations now in the usage metrics API - GitHub Changelog
Save

GitHub Copilot has updated its usage metrics API to provide new data points for agentic activity within the CLI. This expansion covers interactions with skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins.

The new fields are integrated into enterprise and organization per-user and aggregate 1-day reports, per-user 28-day reports, and the day_totals entries in aggregate 28-day reports.

Key Points

  • The API now includes totals_by_skill, totals_by_custom_agent, totals_by_mcp, totals_by_slash_cmd, and totals_by_plugin arrays.
  • These arrays list up to five items with the most recorded activity for each category, including an interaction_count.
  • New fields like distinct_skill_use_count and distinct_custom_agent_use_count track the number of different items used.
  • For MCP servers, interaction_count increases on connection attempts, regardless of success.
  • Plugin metrics count skill invocations associated with a plugin, which are also reflected in skill totals.
  • Customer-defined names for skills, custom agents, MCP servers, and plugins are grouped under "other" for privacy.
  • Reports are accessible to enterprise owners, billing managers, organization owners, and roles with "View Copilot Metrics" permission, provided the Copilot usage metrics policy is enabled.

Context

According to GitHub, these new metrics enable enterprise and organization administrators to identify which Copilot CLI customizations are gaining traction. Administrators can also find enablement gaps and focus investment on automations that developers find valuable.

Why It Matters

This update provides administrators with granular data to understand how developers are interacting with GitHub Copilot's agentic features, allowing for informed decisions on resource allocation and training.

What To Do

  • Review the Copilot usage metrics API documentation to understand the new fields and their definitions.
  • Examine your enterprise and organization reports to identify top-used agentic CLI customizations.
  • Compare distinct_use_count fields over time to observe trends in the variety of agentic items being utilized.
  • Note that plugin metrics are a subset of skill metrics and should not be added together.