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 in two books: constraints, query loops, context governance and multi-agent verification in Claude Code and Codex. harness-books.agentway.dev

01Result

wquguru/harness-books ↗

wquguru/harness-books AI coding statistics: 29.4%

of 34 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 34 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

29.4% agent · top contributor 40%3 contributors

individual

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

agent commits

other considered commits

agent contributors

40%

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

8assisted

2autonomous

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.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	8	23.5%
Devin	Cognition	2	5.9%

03Evidence

Inspect the matches

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

Matched commit samples

cd9f3a48 on GitHubDocument PUML diagram best practicesClaude Code
ee82cb2c on GitHubRedesign PUML diagrams to expose behavior over structureClaude Code
c8746cc2 on GitHubAdd builder scaffolding to book2 chapters (zh + en)Claude Code
bd34f444 on GitHubFix broken images: cover double-prefix and missing diagrams in distDevin
6c22bf8a on GitHubFix pandoc option: --syntax-highlighting -> --highlight-styleDevin

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	39
Merge commits removed	−5
CI / dependency bots removed	−0
Considered	34

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 →Devin commitsBrowse repositories with detected Devin signatures →Python AI coding statisticsCompare evidence across Python 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 wquguru/harness-books

Scan another repository

Try