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.

Paste any GitHub URL → interactive architecture map. See how files connect, find what breaks if you change something. No install, no accounts — runs entirely in your browser.

01Result

braedonsaunders/codeflow ↗

braedonsaunders/codeflow AI coding statistics: 73.4%

of 124 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

73.4% agent · top contributor 64.8%7 contributors

team

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

agent commits

other considered commits

agent contributors

64.8%

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

91assisted

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	66	53.2%
Claude Code	Anthropic	25	20.2%

03Evidence

Inspect the matches

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

Matched commit samples

770f0080 on GitHubGive large-repo analysis a 4s CI budgetCursor Agent
9bbdd88e on GitHubSkip Code leftover tooltips so node drags do not re-render cardsCursor Agent
f74d3d3a on GitHubDrop the ineffective Code SVG warmup before leftover dragsCursor Agent
2e127f48 on GitHubchore: ignore card/dev scratch output and superpowers artifactsClaude Code
e19bf674 on GitHubchore: remove docs/superpowers planning artifactsClaude Code
ba2e50d7 on GitHubFix Ruby analysis false positives and partial-fetch blindness (#76-#79)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	141
Merge commits removed	−17
CI / dependency bots removed	−0
Considered	124

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 →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 braedonsaunders/codeflow

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	100%	7
2026-03	0%	1
2026-04	32.1%	28
2026-05	16.7%	6
2026-06	33.3%	3
2026-07	66.7%	6
2026-08	93.3%	45
2026-09	96.4%	28