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.

Monorepo for tools developed by the Rush Stack community

01Result

microsoft/rushstack ↗

microsoft/rushstack AI coding statistics: 27.1%

of 388 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
27.1% agent · top contributor 29.5%14 contributors
org-wide

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

105
agent commits
283
other considered commits
14
agent contributors
29.5%
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

105assisted
0autonomous

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
2026-0211%91
2026-0318.4%49
2026-0430.1%83
2026-0520%10
2026-068.3%36
2026-0720%30
2026-0857.4%61
2026-0953.6%28

Peak month: 57.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub7920.4%
Claude CodeAnthropic287.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 25542506 on GitHub[eslint-config] Separate type-aware rules, add without-type-information heGitHub Copilot
  • 071bc2b3 on GitHubHarden reporter telemetry privacy projection (#5990)GitHub Copilot
  • cb044736 on GitHubIntegrate negotiated Heft child reporting (#6000)GitHub Copilot
  • 02a5f0a6 on GitHub[playwright-browser-tunnel] Widen playwright-core peer dependency range (#Claude Code
  • f29d18d9 on GitHubAdd file-based transfer APIs to build cache provider interface and all cacClaude Code
  • 0e46b84a on GitHub[package-deps-hash] Fix build cache failures in git linked worktrees causeClaude 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 window420
Merge commits removed−3
CI / dependency bots removed−29
Considered388

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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/rushstack

Scan another repository

Try