Pulse
2026-09-18-v3.0
Dataset
2026-10-27-catalog-ai-v2
Ruleset
b2e8889c66f7
Scanned
2026-10-27
Window
February–September 15, 2026
Catalog tracking observation. This repository is measured with the same fixed window and ruleset, but it is not part of the published benchmark or its aggregate claims.

Bootstraps a fresh Ubuntu VPS into a complete multi-agent AI development environment in 30 minutes: coding agents, session management, safety tools, and coordination infrastructure

01Result

Dicklesworthstone/agentic_coding_flywheel_setup ↗

Dicklesworthstone/agentic_coding_flywheel_setup AI coding statistics: 47.3%

of 1,604 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
47.3% agent · top contributor 78.7%4 contributors
team

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

759
agent commits
845
other considered commits
4
agent contributors
78.7%
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

759assisted
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.

Agent share by month

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-01100%4
2026-0297.7%128
2026-0381.9%248
2026-0444.9%345
2026-0512.4%346
2026-0666.3%80
2026-0775%32
2026-0833.3%378
2026-0960.5%43

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic75947.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • bd480b6d on GitHubfeat(docs): generate the Compatible Agents roster from the manifest (#392)Claude Code
  • 4c3748ca on GitHubfix(docs): make every onboard/learn CLI example match the installed tools,Claude Code
  • adb82004 on GitHubfix(docs): teach `ntm send` for non-interactive palette prompts, not `ntm Claude Code

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 window1,937
Merge commits removed−11
CI / dependency bots removed−322
Considered1,604

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

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code 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 Dicklesworthstone/agentic_coding_flywheel_setup

Scan another repository

Try