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.

CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness

01Result

microsoft/waza ↗

microsoft/waza AI coding statistics: 60.3%

of 696 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
60.3% agent · top contributor 44%15 contributors
org-wide

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

420
agent commits
276
other considered commits
15
agent contributors
44%
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

392assisted
28autonomous

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
2026-0249.7%471
2026-0354.8%62
2026-0495.1%41
2026-0594.7%38
2026-0697.3%37
2026-0784.6%26
2026-0892.9%14
2026-0985.7%7

Peak month: 97.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub42060.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • af29e002 on GitHubfix(graders): treat .agent.md tools as an allow-list (#587)GitHub Copilot
  • 6a94c96e on GitHubfix: drop duplicate skill inventory and handle YAML block scalars (#583)GitHub Copilot
  • 2dec7661 on GitHubfix: align check summary table for wide-character skill names (#394)GitHub Copilot

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 window890
Merge commits removed−62
CI / dependency bots removed−132
Considered696

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

Continue exploring

GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Go AI coding statisticsCompare evidence across Go repositories →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/waza

Scan another repository

Try