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.

Pixiv第三方Android客户端

CeuiLiSA/Pixiv-Shaft ↗

CeuiLiSA/Pixiv-Shaft AI coding statistics: 82.1%

of 1,856 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
82.1% agent · top contributor 99%5 contributors
individual

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

1,523
agent commits
333
other considered commits
5
agent contributors
99%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

1523assisted
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
2026-0390.8%98
2026-0496.8%375
2026-0582%328
2026-0698.9%91
2026-0791.4%304
2026-0872.9%535
2026-0935.2%125

Peak month: 98.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic152282%
OpenAI CodexOpenAI10.1%

Inspect the matches

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

Matched commit samples

  • 10b12fe6 on GitHubchore(cleanup): 删掉 15 个零引用的类和 3 个孤儿布局Claude Code
  • ef31f935 on GitHubfix(build): models 的 desugar_jdk_libs 1.1.5→2.1.3 对齐 app,过新版 lint 的 CoreLiClaude Code
  • c19cf0a7 on GitHubchore(build): AGP 8.7.3→8.13.2、Gradle 8.9→8.14.5,daemon 钉 JDK 17Claude Code
  • e6b3ff01 on GitHubchore(release): 4.9.3OpenAI Codex

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 window1,943
Merge commits removed−87
CI / dependency bots removed−0
Considered1,856

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

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 CeuiLiSA/Pixiv-Shaft

Scan another repository