← the index
mihomo-party-org/clash-party
5.8%
of 276 commits were committed by an AI agent — a floor, not an estimate
5.8% agent · top contributor 75%5 contributors
team

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

16
agent commits
260
human commits
5
agent contributors
75%
largest contributor

Assisted or autonomous

16assisted
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: 19%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic165.8%

Verify it yourself

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

  • 7d4caf83fix: a batch of small UI, tray, floating window and file handling bugs (#2Claude Code
  • 9ddc3ac4fix: let users recover from a crash without restarting the app (#2111)Claude Code
  • a092eb50feat(plugin): CPX v2 availability hardening (squash of cpx-v2-availabilityClaude Code

What was excluded

Commits in window278
Merge commits removed2
CI / dependency bots removed0
Considered276

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 mihomo-party-org/clash-party

Scan another repository