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.

Your agent writes bad React. This catches it

01Result

millionco/react-doctor ↗

millionco/react-doctor AI coding statistics: 33%

of 1,371 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
33% agent · top contributor 30.5%9 contributors
org-wide

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

452
agent commits
919
other considered commits
9
agent contributors
30.5%
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

390assisted
62autonomous

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
2026-020.6%166
2026-0325%4
2026-0427%37
2026-0543%419
2026-0667.1%207
2026-0721.8%399
2026-0822.4%116
2026-0934.8%23

Peak month: 67.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere28620.9%
Claude CodeAnthropic1259.1%
DevinCognition574.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 45c0df3f on GitHubtest: stabilize no-boolean-toggle scaling guard on slow runners (#1793)Cursor Agent
  • ff7dd679 on GitHubfix(rule): recognize owned effect cleanup paths (#1762)Cursor Agent
  • 6ac8b719 on GitHubfix(rule): scope GET helper safety to exact calls (#1761)Cursor Agent
  • e69facac on GitHubfeat(lsp): move editor telemetry to Axiom and unify the opt-out (#1610)Claude Code
  • 738b200e on GitHubfeat(cli): send traces, metrics, and the wide event to Axiom (#1609)Claude Code
  • c843b01a on GitHubfeat(core): add Axiom OTLP transport and an anonymizing tracer (#1608)Claude Code
  • 45c0df3f on GitHubtest: stabilize no-boolean-toggle scaling guard on slow runners (#1793)Devin
  • 2979a9bc on GitHubfix(core): exclude untracked TypeScript emit quartets from the product scaDevin
  • e5b06905 on GitHubfeat(skills): add improve-react audit-then-plan advisor skill (#1144)Devin

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 window1,429
Merge commits removed−0
CI / dependency bots removed−58
Considered1,371

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Devin commitsBrowse repositories with detected Devin 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 millionco/react-doctor

Scan another repository

Try