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.

Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案

01Result

deusyu/harness-engineering ↗

deusyu/harness-engineering AI coding statistics: 15.8%

of 57 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
Too little recent activity to publish. Only 57 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.
15.8% 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.

9
agent commits
48
other considered commits
1
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

9assisted
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
2026-030%7
2026-040%22
2026-050%4
2026-060%11
2026-0777.8%9
2026-0850%4

Peak month: 77.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere915.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • 68e92eef on GitHubworks: 用 open-kimi-ppt skill 生成项目介绍 PPT 与海报 (#20)Cursor Agent
  • 677c98aa on GitHubdocs: 收录 2026-08-03 调研批次（观察项 +7 行 + ReviewBench 升格 #70 + 翻译） (#19)Cursor Agent
  • 90208d60 on GitHubdocs: 收录 2026-07-27 调研批次（12 篇新条目 + 19 行观察项 + 2 篇翻译）+ 新增 C13 守卫 (#18)Cursor Agent

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 window57
Merge commits removed−0
CI / dependency bots removed−0
Considered57

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

Continue exploring

Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 deusyu/harness-engineering

Scan another repository

Try