← the index
K-Dense-AI/scientific-agent-skills
17%
of 411 commits were committed by an AI agent — a floor, not an estimate
17% agent · top contributor 67.1%17 contributors
team

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

70
agent commits
341
human commits
17
agent contributors
67.1%
largest contributor

Assisted or autonomous

67assisted
3autonomous

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: 38.5%. Bars are scaled to that peak, not to 100%.

Which agents

Cursor AgentAnysphere4410.7%
Claude CodeAnthropic266.3%

Verify it yourself

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

  • c1ed16d9Add companion identifier APIs to ontology-term-resolution (#262)Cursor Agent
  • eef7c207Add RegulomeDB and live VEP/CADD traps to database-lookup (#264)Cursor Agent
  • ea2c9f0fAdd companion literature APIs to paper-lookup (#263)Cursor Agent
  • 515742b7Revert "chore: post-merge follow-ups for #252"Claude Code
  • ca2620dbgenomic-intelligence: annotation sync limit and the splice orientation cheClaude Code
  • 45af7aefgenomic-intelligence: reconcile the skill against the live /v1 contract (1Claude Code

What was excluded

Commits in window496
Merge commits removed56
CI / dependency bots removed29
Considered411

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 K-Dense-AI/scientific-agent-skills

Scan another repository