← the index
shanraisshan/claude-code-best-practice ↗
88.7%
of 1,881 commits were committed by an AI agent — a floor, not an estimate
88.7% agent · top contributor 53.6%4 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

1,669
agent commits
212
human commits
4
agent contributors
53.6%
largest contributor

Assisted or autonomous

1665assisted
4autonomous

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

Which agents

Claude CodeAnthropic166988.7%

Verify it yourself

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

  • b5461b8achore(badge): update Last Updated badge to Sep 03, 2026 v2.1.259Claude Code
  • 678bfc9echore(changelog): append 2026-09-03 subagents drift entry (v2.1.259)Claude Code
  • bc80a94cchangelog(claude-commands): append 2026-09-03 drift entry for v2.1.259 — nClaude Code

What was excluded

Commits in window1,944
Merge commits removed−63
CI / dependency bots removed−0
Considered1,881

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 shanraisshan/claude-code-best-practice

Scan another repository

Try