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.

Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

01Result

michaelshimeles/rstack ↗

michaelshimeles/rstack AI coding statistics: 92.6%

of 27 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 27 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

92.6% agent · top contributor 100%1 contributor

individual

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

agent commits

other considered commits

agent contributors

100%

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

25assisted

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

Which agents

Agent	Vendor	Commits	Share
Cursor Agent	Anysphere	13	48.1%
Claude Code	Anthropic	12	44.4%

03Evidence

Inspect the matches

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

Matched commit samples

957cf100 on GitHubREADME: apply unslop to the existing proseCursor Agent
a007fcdd on GitHubaddress greptile review feedback (greploop iteration 1)Cursor Agent
c27c4c33 on GitHubunslop: vendor the pstack skill and wire it into AGENTS.mdCursor Agent
bc477939 on GitHubaddress greptile review feedback (greploop iteration 1)Claude Code
353fccd1 on GitHubgreploop: make the iteration cap an input, default 10Claude Code
59e6551b on GitHubaddress greptile review feedback (greploop iteration 4)Claude 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	33
Merge commits removed	−6
CI / dependency bots removed	−0
Considered	27

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Python AI coding statisticsCompare evidence across Python 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 michaelshimeles/rstack

Scan another repository

Try

Month	Agent share	Considered commits
2026-07	33.3%	3
2026-08	100%	10
2026-09	100%	14