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.

Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

01Result

James-Yu/LaTeX-Workshop ↗

James-Yu/LaTeX-Workshop AI coding statistics: 6.5%

of 230 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

6.5% agent · top contributor 60%4 contributors

team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

agent commits

215

other considered commits

agent contributors

60%

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

15assisted

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: 18.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	8	3.5%
Claude Code	Anthropic	7	3%

03Evidence

Inspect the matches

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

Matched commit samples

4f98f02d on GitHubFix cleaner test errors on WindowsGitHub Copilot
e5171bae on GitHubAdd cleaner testsGitHub Copilot
82afebbc on GitHubRemove `fs` usage in `cleaner.ts`GitHub Copilot
1df80592 on GitHubfix: use startsWith instead of includes for CodeQL warningClaude Code
20072024 on GitHubrefactor: add getExternalUrlPrefix with updateValidOrigin paramClaude Code
5c7fe1d5 on GitHubrefactor: let getExternalUrlPrefix manage validOriginUriClaude 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 window	331
Merge commits removed	−68
CI / dependency bots removed	−33
Considered	230

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 James-Yu/LaTeX-Workshop

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	9
2026-03	13.3%	15
2026-04	18.6%	70
2026-05	0%	24
2026-06	0%	11
2026-07	0%	5
2026-08	0%	81
2026-09	0%	15