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.

An unofficial rules engine for the world's greatest card game.

01Result

Card-Forge/forge ↗

Card-Forge/forge AI coding statistics: 12.1%

of 1,938 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
12.1% agent · top contributor 67.9%20 contributors
team

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

234
agent commits
1,704
other considered commits
20
agent contributors
67.9%
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

234assisted
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
2026-0212.4%267
2026-036.5%230
2026-0413.9%252
2026-0521.5%214
2026-067.8%282
2026-0715%293
2026-089.4%255
2026-0910.3%145

Peak month: 21.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic22511.6%
GitHub CopilotGitHub80.4%
Cursor AgentAnysphere10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • e1137b9f on GitHubList all four supported providers in the deck URL ghost textClaude Code
  • 08881e61 on GitHubFix translated ability text landing on the wrong ability (#11814)Claude Code
  • 3aa9a9fd on GitHubAdventure: let New Game+ offer the main quest againClaude Code
  • 70a3f2cd on GitHubDon't count mana sources against the cost when reserving them (#11487)GitHub Copilot
  • cf68a4ff on GitHubStop the AI locking its own Room for no reason (#11447)GitHub Copilot
  • a337237f on GitHubPrefer winning sooner and losing later (#11458)GitHub Copilot
  • cda00a3b on GitHubRefactor: CantGainControl and LethalDamageByPower off hidden keywords (#33Cursor 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 window2,271
Merge commits removed−333
CI / dependency bots removed−0
Considered1,938

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 →Java AI coding statisticsCompare evidence across Java 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 Card-Forge/forge

Scan another repository

Try