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 beginner tutorial, from 0 to 1

01Result

walkinglabs/learn-harness-engineering ↗

walkinglabs/learn-harness-engineering AI coding statistics: 22.1%

of 208 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
22.1% agent · top contributor 58.7%8 contributors
team

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

46
agent commits
162
other considered commits
8
agent contributors
58.7%
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

46assisted
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
2026-0336.8%19
2026-0434.4%32
2026-0525%88
2026-064.8%42
2026-078.3%12
2026-0820%15

Peak month: 36.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic3717.8%
GitHub CopilotGitHub83.8%
Cursor AgentAnysphere10.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • f8680b3b on GitHubFix inaccurate git analogy in Lecture 03 Atomicity bulletClaude Code
  • 95a50dbd on GitHubdocs(project-01): fix harness docs and align en/zh-TW pagesClaude Code
  • 5f3fce9e on GitHubFix broken HumanLayer link across all 15 localesClaude Code
  • 3d8c3f7c on GitHubi18n(zh-TW): sync project/resource/skill nav titles and cross-linksGitHub Copilot
  • 8cdf8925 on GitHubi18n(zh-TW): sync nav titles and cross-links with actual lecture headingsGitHub Copilot
  • 7f346809 on GitHubi18n(zh-TW): fix Hard Constraints violations in alignment passGitHub Copilot
  • 0df454dc on GitHubfix(zh-CN): point syllabus links to Chinese docs instead of EnglishCursor 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 window252
Merge commits removed−44
CI / dependency bots removed−0
Considered208

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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 walkinglabs/learn-harness-engineering

Scan another repository

Try