Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

A refined collection of Hypervelocity Engineering components (instructions, prompts, agents, and skills) to start your project off right, or upgrade your existing projects to get the most out of GitHub Copilot

01Result

microsoft/hve-core ↗

microsoft/hve-core AI coding statistics: 11.3%

of 681 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
11.3% agent · top contributor 13%29 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

77
agent commits
604
other considered commits
29
agent contributors
13%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

73assisted
4autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0214.6%158
2026-032.8%109
2026-048.7%69
2026-0526.9%26
2026-064.8%126
2026-073.3%60
2026-0824.4%78
2026-0920%55

Peak month: 26.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub7310.7%
Claude CodeAnthropic40.6%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 9bf1a300 on GitHubfeat(skills): add HVE Slides workflow and deck tooling (#2903)GitHub Copilot
  • 3e29a0b2 on GitHubfeat(skills): add demo-setup skill to design-thinking collection (#2886)GitHub Copilot
  • 1c9e73dd on GitHubfeat(build): replace alex with direct retext dependencies (#2818)GitHub Copilot
  • f1a70432 on GitHubfeat(workflows): add beval behavioral evaluation workflow for dt-coach ageClaude Code
  • 878843cb on GitHubfeat(graphify): Add graphify skill with thin prompt + applyTo instructionsClaude Code
  • 84077a82 on GitHubfeat(agents): add enablement dimension to Experiment Designer for code-witClaude Code

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window791
Merge commits removed−0
CI / dependency bots removed−110
Considered681

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli microsoft/hve-core

Scan another repository

Try