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.

Skip is a framework for building reactive services

01Result

SkipLabs/skip ↗

SkipLabs/skip AI coding statistics: 87.9%

of 753 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
87.9% agent · top contributor 95.3%7 contributors
individual

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

662
agent commits
91
other considered commits
7
agent contributors
95.3%
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

662assisted
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
2026-0293.3%90
2026-0396.2%237
2026-0475.4%65
2026-0598.8%85
2026-0616.1%31
2026-0786.9%244
2026-080%1

Peak month: 98.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic65887.4%
GitHub CopilotGitHub40.5%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8fb4f621 on GitHubskc: emit llvm.memcpy/memset intrinsics directlyClaude Code
  • 0fb29117 on GitHubci: base native-addon test image on node:bookworm-slim, not ubuntu+nodesouClaude Code
  • b09b6d88 on GitHublower: type the SKIP_llvm_memcpy call site as ptr, not void (#1472)Claude Code
  • 0990bf1b on GitHubPotential fix for code scanning alert no. 16: Information exposure throughGitHub Copilot
  • 35f79e86 on GitHubPotential fix for code scanning alert no. 18: Information exposure throughGitHub Copilot
  • 7d4e8892 on GitHubPotential fix for code scanning alert no. 5: Uncontrolled data used in patGitHub 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 window1,148
Merge commits removed−319
CI / dependency bots removed−76
Considered753

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 Copilot commitsBrowse repositories with detected GitHub Copilot signatures →TypeScript AI coding statisticsCompare evidence across TypeScript repositories →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 SkipLabs/skip

Scan another repository

Try