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.

Claude Code Dedicated Development Harness - Achieving High-Quality Development Through an Autonomous Plan→Work→Review Cycle

01Result

Chachamaru127/claude-code-harness ↗

Chachamaru127/claude-code-harness AI coding statistics: 71%

of 1,492 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
71% agent · top contributor 40.8%7 contributors
team

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

1,060
agent commits
432
other considered commits
7
agent contributors
40.8%
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

1060assisted
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
2026-0284.7%118
2026-0373.1%130
2026-0458.4%341
2026-0547.8%245
2026-0685.3%273
2026-0781.3%252
2026-0885.4%130
2026-090%3

Peak month: 85.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic98866.2%
Cursor AgentAnysphere785.2%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8448ddee on GitHubchore: release v5.14.0Claude Code
  • 9bf9871d on GitHubchore: rebuild binaries after comment-only source change (drift gate)Claude Code
  • d785c5f6 on GitHubdocs(guardrail): broaden queue-file residual comment (plain rm erases traiClaude Code
  • 77a36a69 on GitHubfix: rewire Go marker counts to plans Status cell parser (Task 119.1)Cursor Agent
  • ffe860e7 on GitHubtest: RED marker count fixture for Status cell parser rewire (Task 119.1)Cursor Agent
  • 2801976c on GitHubfix: count Plans.md markers from Status cells in shell consumersCursor Agent
  • e2e87f3c on GitHubfix(i18n): 出力言語の設定を毎ターン実効化 (PR #247 統合 + Plans.md 整理) (#281)GitHub 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 window1,688
Merge commits removed−170
CI / dependency bots removed−26
Considered1,492

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 →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 Chachamaru127/claude-code-harness

Scan another repository

Try