Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser

01Result

mvanhorn/last30days-skill ↗

mvanhorn/last30days-skill AI coding statistics: 29.6%

of 909 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
29.6% agent · top contributor 48%44 contributors
org-wide

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

269
agent commits
640
other considered commits
44
agent contributors
48%
largest contributor

02Drivers

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

268assisted
1autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached. Across the whole index, 96% of agent commits are assisted.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-0292.1%101
2026-0361.1%95
2026-0417.4%115
2026-053.3%153
2026-0616.3%208
2026-0721.4%168
2026-0855%20
2026-0924.5%49

Peak month: 92.1%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic25628.2%
Cursor AgentAnysphere141.5%

03Evidence

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 78218a88 on GitHubchore: normalize line endings to LF via .gitattributes (#1032)Claude Code
  • 8475c855 on GitHubLinkedIn source: honor the date window, follow the cursor, and signal partClaude Code
  • fec2d824 on GitHubfix: accept an API root in *_BASE_URL overrides (#918)Claude Code
  • ac0ed3b7 on GitHubdocs(credit): attribute #953 fix to Terry Li (@terry-li-hm) via #1041/#113Cursor Agent
  • 6db8e94a on GitHubfix(github): qualifier-only or empty topics are clean no-results, not ERROCursor Agent
  • 1dbdbcfc on GitHubfix(planner): honor operator --plan subquery sources at default/deep (#109Cursor Agent

04Method

What entered the denominator

The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.

Exclusion ledger

Commits in window1,191
Merge commits removed−231
CI / dependency bots removed−51
Considered909

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

05Provenance

Pinned to a source state

This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.

Dataset release
2026-09-18-v3.0
Scan date
2026-09-16
Ruleset
sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
Canonical repository
mvanhorn/last30days-skill
Default branch
main
Resolved HEAD
4909c2efb2d90b81004a70c6890f7e7402db3fd9 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

06Peer context

Position among comparable repositories

The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position84th percentile

Midrank percentile; equal shares split the tied positions.

Repository
29.6%
Cohort median
6.3%
Share rank
39 / 247
0th50th100th

Percentile = (repositories below + half of 2 tied repositories) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →GitHub AI commit analyzerInspect another repository with the same evidence model →
Reproduce this observation

Run the same detector locally.

Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.

npx qmmit-cli mvanhorn/last30days-skill

Scan another repository

Try