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.

Cataclysm: Bright Nights: A fork/variant of Cataclysm:DDA by CleverRaven with a mod registry at https://mods.cataclysmbn.org/

01Result

cataclysmbn/Cataclysm-BN ↗

cataclysmbn/Cataclysm-BN AI coding statistics: 0.9%

of 1,495 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.9% agent · top contributor 28.6%8 contributors
team

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

14
agent commits
1,481
other considered commits
8
agent contributors
28.6%
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

14assisted
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
2026-010%1
2026-022.4%164
2026-030%118
2026-040%173
2026-051.5%324
2026-060.6%340
2026-070.6%179
2026-080%117
2026-092.5%79

Peak month: 2.5%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic60.4%
GitHub CopilotGitHub40.3%
Cursor AgentAnysphere30.2%
OpenAI CodexOpenAI10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 67258145 on GitHubfix: make rope ladder climbable up and visible from ground again (#9610)Claude Code
  • 1f04b1df on GitHubfix: restore missing starting fire in Really Bad Day scenario (#9185)Claude Code
  • 93a2b268 on GitHubfix: hallu effect scales to actual duration, no longer clipped at 30 m (#9Claude Code
  • f4c57107 on GitHubfix: smoking rack allow removing everything + replace mentions of "food" wGitHub Copilot
  • 9a1bbf5c on GitHubfeat: add lighthouse variants (#8190)GitHub Copilot
  • 580c39e4 on GitHubfeat(balance): apply world category spawn rates to more loot sources (#809GitHub Copilot
  • 325c7930 on GitHubfeat(UI): show monster move points when examining (#10206)Cursor Agent
  • 405dc6df on GitHubfix: keep vehicle cargo on the correct part after splitting (#10208)Cursor Agent
  • 2181994e on GitHubfix: make safe_reference and sounds thread-safe for worker mapgen (#9281)Cursor Agent
  • eb5091f6 on GitHubfeat: add isolated lake cities (#9796)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 window1,586
Merge commits removed−3
CI / dependency bots removed−88
Considered1,495

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →C++ AI coding statisticsCompare evidence across C++ 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 cataclysmbn/Cataclysm-BN

Scan another repository

Try