One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
Assisted or autonomous
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
Peak month: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 5 | 14.7% |
| Cursor Agent | Anysphere | 2 | 5.9% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
6bfa520bFix Swiss style minimum font sizes and add weight ladder rulesClaude Code5e210a52Rename skill to guizang-ppt-skill, add npx installClaude Codeb5c6025cdocs: add English READMEClaude Code929c2ecbUpdate sponsors: add Kimi work & Cola Skill gold sponsors, new banner, usaCursor Agentba12c5c9Sync multi-theme optimizations from dev (exclude Bento/Style C)Cursor Agent
What was excluded
| Commits in window | 34 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 34 |
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 op7418/guizang-ppt-skill