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.

Actions for running CodeQL analysis

01Result

github/codeql-action ↗

github/codeql-action AI coding statistics: 5.5%

of 1,067 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

5.5% agent · top contributor 79.7%5 contributors

team

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

agent commits

1,008

other considered commits

agent contributors

79.7%

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

57assisted

2autonomous

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: 52.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
GitHub Copilot	GitHub	59	5.5%

03Evidence

Inspect the matches

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

Matched commit samples

eb76062e on GitHubInclude failed bundle attempts in fallback timingGitHub Copilot
ec5eecb2 on GitHubUse per-language CodeQL bundlesGitHub Copilot
1970c450 on GitHubSeparate CodeQL bundle resolution from installationGitHub 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	1,832
Merge commits removed	−477
CI / dependency bots removed	−288
Considered	1,067

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

Continue exploring

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 github/codeql-action

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	1.9%	214
2026-03	0%	241
2026-04	1.4%	72
2026-05	0.9%	109
2026-06	8.2%	61
2026-07	4.2%	262
2026-08	21.9%	64
2026-09	52.3%	44