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

obra/superpowers ↗

obra/superpowers AI coding statistics: 15.9%

of 409 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
15.9% agent · top contributor 30.8%8 contributors
team

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

65
agent commits
344
other considered commits
8
agent contributors
30.8%
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

65assisted
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
2026-0251.9%27
2026-0328.3%120
2026-0430%20
2026-0550%2
2026-063.4%177
2026-074.8%62
2026-08100%1

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic6315.4%
Cursor AgentAnysphere30.7%

03Evidence

Inspect the matches

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

Matched commit samples

  • b36e0829 on GitHubRelease v6.3.0: Devin CLI and Hermes Agent support, brainstorming three-paClaude Code
  • 28b96af9 on GitHubchore(codex): remove orphaned session-start-codex hook + refresh hook docsClaude Code
  • 7d8d3d4b on GitHubfix(codex): suppress SessionStart hook auto-discovery with empty hooks objClaude Code
  • b36e0829 on GitHubRelease v6.3.0: Devin CLI and Hermes Agent support, brainstorming three-paCursor Agent
  • 6015d37f on GitHubfix(systematic-debugging): match find -path ./ prefix in find-polluter.sh Cursor Agent
  • 772ec9f8 on GitHubAdd Cursor plugin manifest and hook response compatibilityCursor 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 window427
Merge commits removed−18
CI / dependency bots removed−0
Considered409

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
obra/superpowers
Default branch
main
Resolved HEAD
b36e0829c6d0140e93cfef2ca599b1b07d4a7797 ↗
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 position72nd percentile

Midrank percentile; equal shares split the tied positions.

Repository
15.9%
Cohort median
1.5%
Share rank
7 / 23
0th50th100th

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

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 obra/superpowers

Scan another repository

Try