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 Simple, Speedy, Secure, and Serverless Link Shortener with Analytics, Running Entirely on Cloudflare.

01Result

miantiao-me/Sink ↗

miantiao-me/Sink AI coding statistics: 5.4%

of 185 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

5.4% agent · top contributor 80%2 contributors

individual

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

agent commits

175

other considered commits

agent contributors

80%

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

8assisted

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: 66.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	8	4.3%
GitHub Copilot	GitHub	2	1.1%

03Evidence

Inspect the matches

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

Matched commit samples

5892ed69 on GitHubfix: reject reserved slugs when creating a linkClaude Code
3cd3344c on GitHubfix(mcp): serve the endpoint from /api/mcp so it cannot shadow a linkClaude Code
16b23489 on GitHubrefactor(mcp): table-ize transport tests and trim remaining duplicationClaude Code
592d2b84 on GitHubfix: allow removing link password on editGitHub Copilot
5235a063 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	233
Merge commits removed	−48
CI / dependency bots removed	−0
Considered	185

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 miantiao-me/Sink

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	3%	66
2026-03	0%	7
2026-04	0%	7
2026-05	0%	31
2026-06	0%	4
2026-07	0%	55
2026-08	0%	3
2026-09	66.7%	12