Coding Tools
GitHub Copilot CLI adds agentic usage metrics
GitHub Changeloghigh confidence
Why it matters
- →Enables data-driven decisions on which CLI customizations to prioritize or retire.
- →Provides granular visibility into MCP server and plugin usage within the CLI environment.
- →Helps justify AI infrastructure investment by measuring actual developer engagement with agentic tools.
GitHub has expanded its Copilot usage metrics API to include agentic activity data for CLI customizations. The update adds fields tracking interaction counts and distinct usage for skills, custom agents, Model Context Protocol (MCP) servers, slash commands, and plugins. These metrics are available in per-user and aggregate reports for enterprise and organization administrators. The change allows teams to identify high-value automations and measure adoption rates of internal AI tools.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1GitHub Copilot Enhances Usage Metrics Accuracy
GitHub Changelog · July 2, 2026 · Same story
What happened next
- 2GitHub Copilot metrics now name custom agents and MCPs
GitHub Changelog · October 22, 2026 · Same story
Follow this story
Open the full story →GitHub Copilot CLI adds agentic usage metrics
3 developments
- Sep 17 · GitHub Changelog
GitHub Copilot CLI adds agentic usage metrics (This article) - Sep 17 · GitHub Changelog
GitHub Copilot adds feature-level engagement metrics↳ GitHub Copilot introduces feature-level engagement metrics to distinguish passive code reviews from active agent edits and CLI usage for ent - Sep 18 · GitHub Changelog
GitHub Copilot adds model tiers and Sentry integration↳ GitHub Copilot introduces efficiency, balance, and intelligence tiers for cost-performance control alongside Sentry integration to turn cras
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
llama.cpp Releases