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.

Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows.

01Result

daymade/claude-code-skills ↗

daymade/claude-code-skills AI coding statistics: 73.7%

of 833 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
73.7% agent · top contributor 99.7%3 contributors
individual

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

614
agent commits
219
other considered commits
3
agent contributors
99.7%
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

614assisted
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
2026-0281.8%11
2026-0380%20
2026-0470.1%107
2026-05100%33
2026-0688.3%60
2026-0780.3%198
2026-0864.3%272
2026-0971.2%132

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic59271.1%
OpenAI CodexOpenAI232.8%

03Evidence

Inspect the matches

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

Matched commit samples

  • ce74fcd5 on GitHubfeat(history-skills): surface fingerprints, zero-hit census, CC-behavior cClaude Code
  • c9bf1922 on GitHubfix(claude-switch-models-setup): identify pin links by listing them, not bClaude Code
  • 70106e42 on GitHubfeat(history-skills): thinking turns, plan bindings, carrier terms + freshClaude Code
  • 49ae501b on GitHubdocs: route hook reminder semantics through rule 7 (#416)OpenAI Codex
  • a9990878 on GitHubchore(claude-code-hooks): refresh security attestation (#415)OpenAI Codex
  • 91f02e6d on GitHubfix(claude-code-hooks): separate advisory cadence from loop budgets (#414)OpenAI Codex

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 window898
Merge commits removed−65
CI / dependency bots removed−0
Considered833

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python 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 daymade/claude-code-skills

Scan another repository

Try