← the index
koodo-reader/koodo-reader
2.6%
of 1,134 commits were committed by an AI agent — a floor, not an estimate
2.6% 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.

30
agent commits
1,104
human commits
1
agent contributors
100%
largest contributor

Assisted or autonomous

30assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 15.8%. Bars are scaled to that peak, not to 100%.

Which agents

Cursor AgentAnysphere211.9%
Claude CodeAnthropic80.7%
GitHub CopilotGitHub10.1%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • cf692087Display featured fonts inline in Font settings instead of a modal overlay.Cursor Agent
  • 41055544Lazy-load font previews in Font settings instead of preloading all fonts iCursor Agent
  • c1334e9cAdd font preview overlay with app and reader font assignment in Font settiCursor Agent
  • 10648518feat(supportDialog): 试用到期退出专业版改为直接退出Claude Code
  • a0b68136docs: 添加 CLAUDE.md 项目架构与开发规范文档Claude Code
  • 8e3f7f30fix(navigation): reset collapsedChapters on new search and cancelClaude Code
  • ad555de9Apply suggestions from code reviewGitHub Copilot

What was excluded

Commits in window1,162
Merge commits removed28
CI / dependency bots removed0
Considered1,134

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli koodo-reader/koodo-reader

Scan another repository