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

github/spec-kit ↗

github/spec-kit AI coding statistics: 52.6%

of 1,391 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
52.6% agent · top contributor 21.6%106 contributors
org-wide

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

731
agent commits
660
other considered commits
106
agent contributors
21.6%
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

570assisted
161autonomous

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
2026-0240.6%32
2026-0341.1%129
2026-0430.6%183
2026-0517.9%140
2026-0654.7%247
2026-0772.5%378
2026-0866.1%189
2026-0953.8%93

Peak month: 72.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub46733.6%
Claude CodeAnthropic29221%
Cursor AgentAnysphere50.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 1d5106f5 on GitHubAdd OpenUP Governance preset to community catalog (#4596)GitHub Copilot
  • abe0d1de on GitHubAdd OpenUP Governed Lifecycle extension to community catalog (#4598)GitHub Copilot
  • 10270e16 on GitHubUpdate adrkit extension to v0.1.4 (#4600)GitHub Copilot
  • 4c1db740 on GitHubfix(integrations): dispatch bob commands via `bob run` (#4492)Claude Code
  • 42153451 on GitHubfix(events): cap stdin in the generated dispatcher, not just the CLI commaClaude Code
  • e4842a03 on GitHubdocs(core): SPECIFY_FEATURE sets the feature label, not the feature directClaude Code
  • 39f2ac3c on GitHubclarify: require real interrogatives, ban topic-label questions (#3745)Cursor Agent
  • 82c078bb on GitHubdocs: clarify that release tags keep the leading v prefix (#3463)Cursor Agent
  • 8e5643d4 on GitHubfix(cursor-agent): enable headless CLI dispatch end-to-end (-p --trust --aCursor 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 window1,451
Merge commits removed−3
CI / dependency bots removed−57
Considered1,391

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
github/spec-kit
Default branch
main
Resolved HEAD
1d5106f59e1b148ee23ab136638932dd790ff1b6 ↗
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 position93rd percentile

Midrank percentile; equal shares split the tied positions.

Repository
52.6%
Cohort median
6.3%
Share rank
17 / 247
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot 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 github/spec-kit

Scan another repository

Try