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 modern Android app for installing and managing APK packages with split APK support, silent install via Shizuku, and VirusTotal malware scanning.

pass-with-high-score/universal-installer ↗

pass-with-high-score/universal-installer AI coding statistics: 17%

of 669 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
17% agent · top contributor 94.7%3 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

114
agent commits
555
other considered commits
3
agent contributors
94.7%
largest contributor

What shapes this result

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

Assisted or autonomous

114assisted
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
2026-030%3
2026-042.7%113
2026-051.2%86
2026-0628.7%143
2026-0737.9%29
2026-0854.2%107
2026-090%188

Peak month: 54.2%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic11417%

Inspect the matches

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

Matched commit samples

  • 9befad1f on GitHubi18n: translate the onboarding analytics page into the 17 core localesClaude Code
  • 94e393a2 on GitHubbuild: keep Crashlytics out of the open-source APK whatever the checkout hClaude Code
  • b3b24bd3 on GitHubdocs(store): bring the description back under Play's 4000-character limitClaude Code

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 window678
Merge commits removed−9
CI / dependency bots removed−0
Considered669

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

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 pass-with-high-score/universal-installer

Scan another repository