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.

A simple Markdown viewer for reading .md files

01Result

pluk-inc/markdown-preview ↗

pluk-inc/markdown-preview AI coding statistics: 27.5%

of 291 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
27.5% agent · top contributor 86.3%10 contributors
individual

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

80
agent commits
211
other considered commits
10
agent contributors
86.3%
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

80assisted
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
2026-0463.6%11
2026-0527.7%94
2026-060%6
2026-0722.4%85
2026-0845.1%51
2026-0911.4%44

Peak month: 63.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic7927.1%
Cursor AgentAnysphere10.3%

03Evidence

Inspect the matches

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

Matched commit samples

  • efd65c04 on GitHubEscape the article template terminator case-insensitively (#398)Claude Code
  • 6014e9a7 on GitHubKeep Mermaid figures from collapsing in the flex article (#388)Claude Code
  • 6bcbb2f2 on GitHubAdopt the system type scale, semantic colors, render-time highlighting, anClaude Code
  • fb8dfa83 on GitHubSupport .mdx files as Markdown documents (#384)Cursor 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 window297
Merge commits removed−6
CI / dependency bots removed−0
Considered291

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 →Cursor Agent commitsBrowse repositories with detected Cursor Agent signatures →Swift AI coding statisticsCompare evidence across Swift 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 pluk-inc/markdown-preview

Scan another repository

Try