Pulse
2026-09-18-v3.0
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.

基于 Karpathy llm-wiki 方法论的个人知识库构建 Skill，支持多平台！

01Result

sdyckjq-lab/llm-wiki-skill ↗

sdyckjq-lab/llm-wiki-skill AI coding statistics: 20.1%

of 1,020 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
20.1% agent · top contributor 48.8%5 contributors
team

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

205
agent commits
815
other considered commits
5
agent contributors
48.8%
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

205assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0463.4%131
2026-0511.3%62
2026-0610.9%403
2026-0716.7%424

Peak month: 63.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic20520.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • efa2294d on GitHubtest(workbench): stop racing the transient warning banner (#312) (#313)Claude Code
  • b85300ed on GitHubtest(graph): keep workbench fixture from being rebuilt (#291) (#309)Claude Code
  • 860ed06f on GitHubdocs(graph): revise ID collision governance spec after adversarial reviewClaude 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 window1,135
Merge commits removed−115
CI / dependency bots removed−0
Considered1,020

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 →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 sdyckjq-lab/llm-wiki-skill

Scan another repository

Try