11.5%

of 312 commits were committed by an AI agent — a floor, not an estimate

11.5% agent · top contributor 27.8%19 contributors

org-wide

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

agent commits

276

human commits

agent contributors

27.8%

largest contributor

Assisted or autonomous

34assisted

2autonomous

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: 21.9%. Bars are scaled to that peak, not to 100%.

Which agents

Claude Code	Anthropic	27	8.7%
GitHub Copilot	GitHub	5	1.6%
Cursor Agent	Anysphere	4	1.3%

Verify it yourself

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

1483fc12fix(skills): add database-migration and dependency-audit vocabulary to twoClaude Code
b61213f5Add pull-request vocabulary to git-workflow-and-versioning descriptionClaude Code
b293c024ci: add a gate for references/ links in skillsClaude Code
75dfcb33Potential fix for pull request findingGitHub Copilot
77ffedb2fix: update marketplace.json to use explicit GitHub source formatGitHub Copilot
4d277aa7docs(skills): tighten frontmatter for idea-refine and browser-testingGitHub Copilot
bb68af56fix(hooks): quote opt-in hook paths in setup docsCursor Agent
b68f553adocs: add skill-gap issue form for reporting guidance mismatchesCursor Agent
f25f467efix(validator): reject fenced-block headings and negated triggers (#387)Cursor Agent

What was excluded

Commits in window	466
Merge commits removed	−154
CI / dependency bots removed	−0
Considered	312

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 addyosmani/agent-skills

Scan another repository

Try