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 curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.

01Result

brycewang-stanford/Auto-Empirical-Research-Skills ↗

brycewang-stanford/Auto-Empirical-Research-Skills AI coding statistics: 78.9%

of 265 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

78.9% agent · top contributor 90%6 contributors

individual

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

209

agent commits

other considered commits

agent contributors

90%

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

206assisted

3autonomous

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: 97.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	197	74.3%
OpenAI Codex	OpenAI	12	4.5%
GitHub Copilot	GitHub	1	0.4%

03Evidence

Inspect the matches

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

Matched commit samples

266adb2c on GitHubfeat(48): add a provenance / de-watermark layer to de-AIGC-skillsClaude Code
129c4591 on GitHubchore(gitignore): drop the rule for a guide that is now shipped, not localClaude Code
b7ee3d32 on GitHubfeat(docx): make "data → full Word manuscript" a first-class, demonstratedClaude Code
f4dcfc26 on GitHubHarden generator determinism checksOpenAI Codex
f7e94cf1 on GitHubfeat: add literature review tools skill (#63)OpenAI Codex
a0be3e54 on GitHubchore: sync Paper-WorkFlow quality gatesOpenAI Codex
2f457ddc on GitHubfeat: add safe and audited Kaggle research integration (#66)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	292
Merge commits removed	−7
CI / dependency bots removed	−20
Considered	265

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 →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 brycewang-stanford/Auto-Empirical-Research-Skills

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	88.4%	43
2026-05	85.3%	34
2026-06	64.9%	74
2026-07	75.4%	69
2026-08	97.3%	37
2026-09	75%	8