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

mattpocock/skills ↗

mattpocock/skills AI coding statistics: 59.7%

of 352 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
59.7% agent · top contributor 91%6 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

210
agent commits
142
other considered commits
6
agent contributors
91%
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

210assisted
0autonomous

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
2026-020%10
2026-0320%10
2026-0419.5%41
2026-050%25
2026-0636.7%60
2026-0793.8%129
2026-0874.3%74
2026-0966.7%3

Peak month: 93.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic20758.8%
GitHub CopilotGitHub30.9%

03Evidence

Inspect the matches

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

Matched commit samples

  • 6942bff8 on GitHubAdd changeset for retro deterministic-checks updateClaude Code
  • 0243b6ec on GitHubretro: push mechanical coding-standards findings toward deterministic checClaude Code
  • 84b5ee5a on GitHubAdd implement-spec skill (in-progress) with its bucket docsClaude Code
  • b843cb5e on GitHubAdd structured sections for 'what-to-do' and 'supporting-info' in SKILL.mdGitHub Copilot
  • 179a14e7 on GitHubSwapped 'backlog' for 'issue trackerGitHub Copilot
  • 3e3ca9b9 on GitHubAdd initial implementation of design-an-interface skill and linking scriptGitHub Copilot

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 window462
Merge commits removed−104
CI / dependency bots removed−6
Considered352

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
mattpocock/skills
Default branch
main
Resolved HEAD
959a8e9f1edc3adbe2f7e3054bb6fbefa6696260 ↗
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.

CohortShell · 23 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 21 of 44 ecosystem repositories excluded
Agent-commit share position98th percentile

Midrank percentile; equal shares split the tied positions.

Repository
59.7%
Cohort median
1.5%
Share rank
1 / 23
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 23.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot 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 mattpocock/skills

Scan another repository

Try