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 analysis tool for Python that blurs the line between testing and type systems.

01Result

pschanely/CrossHair ↗

pschanely/CrossHair AI coding statistics: 57.3%

of 211 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

57.3% agent · top contributor 71.9%5 contributors

team

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

121

agent commits

other considered commits

agent contributors

71.9%

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

121assisted

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

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

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	113	53.6%
Cursor Agent	Anysphere	7	3.3%
OpenAI Codex	OpenAI	1	0.5%

03Evidence

Inspect the matches

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

Matched commit samples

474083f1 on GitHubExit 2 from search and diffbehavior on nondeterminismClaude Code
e8e29403 on GitHubUnify analyze_calltree onto the shared exploration loopClaude Code
c812324d on GitHubRoute diff_behavior through explore_pathsClaude Code
7ae467a5 on GitHubFix Sphinx doc build after pyproject.toml author metadata change.Cursor Agent
09026706 on GitHubFix pre-commit after consolidating flake8 config into pyproject.toml.Cursor Agent
61eeab2b on GitHubConsolidate tool configuration into pyproject.toml.Cursor Agent
c066d04f on GitHubfix: resolve issue #282OpenAI 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 window	215
Merge commits removed	−0
CI / dependency bots removed	−4
Considered	211

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →Python AI coding statisticsCompare evidence across Python 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 pschanely/CrossHair

Scan another repository

Try

Month	Agent share	Considered commits
2026-04	2.3%	44
2026-05	44.8%	29
2026-06	66.7%	33
2026-07	83.7%	86
2026-08	33.3%	9
2026-09	100%	10