← the index
cathrynlavery/diagram-design
11.2%
of 125 commits were committed by an AI agent — a floor, not an estimate
11.2% agent · top contributor 21.4%10 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

14
agent commits
111
human commits
10
agent contributors
21.4%
largest contributor

Assisted or autonomous

14assisted
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

Apr26
May26
Jul26
Aug26
Sep26

Peak month: 40.9%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic118.8%
Cursor AgentAnysphere21.6%
GitHub CopilotGitHub10.8%

Verify it yourself

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

  • b26918f5docs(style-guide): Cyrillic labels — Noto Serif title fallback (#221)Claude Code
  • 3a1a7e09fix(doctor): fall through a python3 that cannot report its version (#201)Claude Code
  • d0a0f464feat(patterns): add traceable block decomposition semantic pattern (#169)Claude Code
  • 899579b4feat: import Excalidraw diagrams for editorial redraw (#192)Cursor Agent
  • 48fecccdfeat: add a waterfall chart visual type (#191)Cursor Agent
  • fc9c0be3docs: add GitHub Copilot marketplace install (#218)GitHub Copilot

What was excluded

Commits in window169
Merge commits removed29
CI / dependency bots removed15
Considered125

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 cathrynlavery/diagram-design

Scan another repository