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 offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

01Result

delibae/claude-prism ↗

delibae/claude-prism AI coding statistics: 61.7%

of 214 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

61.7% agent · top contributor 68.9%5 contributors

team

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

132

agent commits

other considered commits

agent contributors

68.9%

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

132assisted

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: 74.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	130	60.7%
GitHub Copilot	GitHub	2	0.9%

03Evidence

Inspect the matches

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

Matched commit samples

fcbcbc4c on GitHubchore: bump version to v1.1.5Claude Code
52cfd79e on GitHubchore: bump version to 1.1.4Claude Code
6434f176 on GitHubfix: address Copilot review — refactor git-bash detection and improve erroClaude Code
4a951609 on GitHubUpdate apps/desktop/src/components/workspace/editor/latex-editor.tsxGitHub Copilot
e37afc5a on GitHubUpdate apps/desktop/src/lib/latex-compiler.tsGitHub 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 window	306
Merge commits removed	−81
CI / dependency bots removed	−11
Considered	214

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 →TypeScript AI coding statisticsCompare evidence across TypeScript 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 delibae/claude-prism

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	19.4%	36
2026-03	74.3%	167
2026-04	9.1%	11