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.

Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.

01Result

amElnagdy/delegate-skills ↗

amElnagdy/delegate-skills AI coding statistics: 33.2%

of 283 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

33.2% agent · top contributor 47.9%13 contributors

org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

agent commits

189

other considered commits

agent contributors

47.9%

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

92assisted

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

Peak month: 66.7%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	71	25.1%
Cursor Agent	Anysphere	21	7.4%
GitHub Copilot	GitHub	2	0.7%

03Evidence

Inspect the matches

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

Matched commit samples

aae393ae on GitHubfix(codex): drop WindowsApps PATH entries for sandboxed runs on WindowsClaude Code
2861b939 on GitHubdocs(agy): document the Windows permission engine trapsClaude Code
d49e5b12 on GitHubfix(test): fail parity when a relay defines a gated symbol off its listClaude Code
09bdaa8f on GitHubfix(relay): disarm the watchdog when the implementer exitsCursor Agent
143ad8b6 on GitHubdocs(omp): say --read-only is a tool-surface limit, not a sandbox.Cursor Agent
8749637b on GitHubAdd omp-delegate for Oh My Pi as a separate implementer.Cursor Agent
1c2f63ea on GitHubfeat: add vibe-delegate skill for Mistral Vibe CLIGitHub Copilot
78dc8af5 on GitHubInitial planGitHub 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	375
Merge commits removed	−92
CI / dependency bots removed	−0
Considered	283

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 →JavaScript AI coding statisticsCompare evidence across JavaScript 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 amElnagdy/delegate-skills

Scan another repository

Try

Month	Agent share	Considered commits
2026-06	66.7%	3
2026-07	14.9%	114
2026-08	48.3%	149
2026-09	17.6%	17