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 plugin to edit and view Excalidraw drawings in Obsidian

01Result

zsviczian/obsidian-excalidraw-plugin ↗

zsviczian/obsidian-excalidraw-plugin AI coding statistics: 3.3%

of 782 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

3.3% agent · top contributor 96.2%2 contributors

individual

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

agent commits

756

other considered commits

agent contributors

96.2%

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

26assisted

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

Peak month: 21.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	21	2.7%
GitHub Copilot	GitHub	5	0.6%

03Evidence

Inspect the matches

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

Matched commit samples

2580ab84 on GitHubFix blank sections in Hybrid Note PDF export when Markdown side has an imaClaude Code
efb00d1d on GitHubEliminate remaining any-collapse in ExcalidrawAutomate.tsClaude Code
8d06fe1e on GitHubFix @excalidraw/common type resolution, eliminating a huge any-collapseClaude Code
6860b4a1 on GitHubPotential fix for pull request finding 'CodeQL / Replacement of a substrinGitHub Copilot
444ac933 on GitHub2.22.2, 0.18.0-90GitHub Copilot
713f1973 on GitHub2.22.1, 0.18.0-89GitHub 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 window	869
Merge commits removed	−87
CI / dependency bots removed	−0
Considered	782

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 zsviczian/obsidian-excalidraw-plugin

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	46
2026-03	0%	64
2026-04	21.4%	14
2026-05	0.7%	141
2026-06	0%	121
2026-07	0.8%	124
2026-08	10.4%	192
2026-09	1.3%	80