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.

🔐 Securely share sensitive information with automatic expiration & deletion after a set number of views or duration. Track who, what and when with full audit logs.

01Result

pglombardo/PasswordPusher ↗

pglombardo/PasswordPusher AI coding statistics: 6.6%

of 243 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
6.6% agent · top contributor 87.5%3 contributors
individual

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

16
agent commits
227
other considered commits
3
agent contributors
87.5%
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

16assisted
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
2026-020%16
2026-031.8%55
2026-043.4%59
2026-0510.5%19
2026-063.8%26
2026-0733.3%24
2026-080%38
2026-0933.3%6

Peak month: 33.3%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere104.1%
GitHub CopilotGitHub72.9%
Claude CodeAnthropic10.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • e74b6a50 on GitHubDefault Docker Solid Queue to async to cut idle worker memory. (#4816)Cursor Agent
  • 4ca35185 on GitHubWarn against mounting volumes over /opt/PasswordPusher/db (#4795)Cursor Agent
  • 451f40a2 on GitHubEnable Permissions-Policy headers for browser feature restrictions. (#4621Cursor Agent
  • 46d78126 on GitHubFilter payload and passphrase from logs and error tracking (#4614)GitHub Copilot
  • 881a82de on GitHubSecurity: Trash unnecessary workflows; Harden Others (#4556)GitHub Copilot
  • c5aa47fb on GitHubAdd copyable share message to push preview page (#4474)GitHub Copilot
  • 4d8b069c on GitHub:lock: Add require_mfa setting to enforce two-factor authentication (#4336Claude 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 window708
Merge commits removed−4
CI / dependency bots removed−461
Considered243

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 pglombardo/PasswordPusher

Scan another repository

Try