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.

Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.

01Result

conorbronsdon/avoid-ai-writing ↗

conorbronsdon/avoid-ai-writing AI coding statistics: 41%

of 317 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

41% agent · top contributor 83.1%12 contributors

individual

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

130

agent commits

187

other considered commits

agent contributors

83.1%

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

130assisted

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
Claude Code	Anthropic	113	35.6%
OpenAI Codex	OpenAI	17	5.4%
GitHub Copilot	GitHub	1	0.3%

03Evidence

Inspect the matches

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

Matched commit samples

ff15a578 on GitHubnightly: fix tracker stripping, export spawn errors, release version gapClaude Code
46bdea40 on GitHubMark generated copies as linguist-generated in .gitattributesClaude Code
ce70c28c on GitHubfix(evals): make the rewrite pilot rewrite-onlyClaude Code
fdee2ca6 on GitHubAdd an explicit audited OpenCode rewrite-evaluation runnerOpenAI Codex
a0ff473c on GitHubReturn one final rewrite within a shared editing-pass budgetOpenAI Codex
c520ac78 on GitHubRetain every absorbed heading mapping in comparison artifactsOpenAI Codex
049463a8 on GitHubDistribute as a Claude Code / Cowork plugin (#17)GitHub 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	397
Merge commits removed	−77
CI / dependency bots removed	−3
Considered	317

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →JavaScript AI coding statisticsCompare evidence across JavaScript 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 conorbronsdon/avoid-ai-writing

Scan another repository

Try

Month	Agent share	Considered commits
2026-03	78.1%	32
2026-04	31.3%	16
2026-05	79.2%	24
2026-06	100%	10
2026-07	60.9%	23
2026-08	62.2%	37
2026-09	19.4%	175