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.

Hayabusa (隼) is a sigma-based threat hunting and fast forensics timeline generator for Windows event logs.

01Result

Yamato-Security/hayabusa ↗

Yamato-Security/hayabusa AI coding statistics: 67.1%

of 243 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

67.1% agent · top contributor 71.8%6 contributors

team

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

163

agent commits

other considered commits

agent contributors

71.8%

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

161assisted

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: 97.4%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	161	66.3%
GitHub Copilot	GitHub	2	0.8%

03Evidence

Inspect the matches

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

Matched commit samples

64f7caa4 on GitHubtest: make the -T histogram wiring test timezone-independentClaude Code
4e67e03e on GitHubci: fetch the aarch64 musl toolchain from GitHub instead of musl.ccClaude Code
81cc0c72 on GitHubfix: skip zero-count logon rows before sorting, cover the pivot formatterClaude Code
a2236917 on GitHubfix(ci): open a PR instead of direct-pushing to protected main in sync worGitHub Copilot
ff0b8290 on GitHubInitial planGitHub 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	372
Merge commits removed	−123
CI / dependency bots removed	−6
Considered	243

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 →Rust AI coding statisticsCompare evidence across Rust 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 Yamato-Security/hayabusa

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	2
2026-04	0%	8
2026-05	0%	6
2026-06	97.4%	39
2026-07	70.9%	175
2026-08	14.3%	7
2026-09	0%	6