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.

Official upstream development repository for Cabal and cabal-install

01Result

haskell/cabal ↗

haskell/cabal AI coding statistics: 2%

of 296 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2% agent · top contributor 33.3%4 contributors
team

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

6
agent commits
290
other considered commits
4
agent contributors
33.3%
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

4assisted
2autonomous

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
2026-020%27
2026-030%54
2026-043.2%31
2026-055.4%56
2026-060%44
2026-072.6%39
2026-080%39
2026-0916.7%6

Peak month: 16.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic31%
GitHub CopilotGitHub31%

03Evidence

Inspect the matches

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

Matched commit samples

  • 0e296616 on GitHubDon't use a shallow checkout as a git clone referenceClaude Code
  • b8c5ad6e on GitHubNormalize in-place unit-id versions in golden test output (#12113)Claude Code
  • 3a31161d on GitHubactive-repositories: Don't override fully-deprecated packagesClaude Code
  • 66b5a12c on GitHubAdd `@since` annotations to `LicenseListVersion` constructorsGitHub Copilot
  • e775ba83 on GitHubFix `cabal run`'s handling of `--` under empty targetGitHub Copilot
  • ff9daa26 on GitHubtests: make UserConfig unit tests concurrency-safe with unique tempiles (#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 window554
Merge commits removed−243
CI / dependency bots removed−15
Considered296

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 →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 haskell/cabal

Scan another repository

Try