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.

AI 解说大师 — Agent skill；封装 narrator-ai-cli 供 Claude/Codex 等工具调用

01Result

NarratorAI-Studio/narrator-ai-cli-skill ↗

NarratorAI-Studio/narrator-ai-cli-skill AI coding statistics: 23.8%

of 21 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

Too little recent activity to publish. Only 21 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.

23.8% agent · top contributor 80%2 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

agent commits

other considered commits

agent contributors

80%

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

5assisted

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: 33.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	5	23.8%

03Evidence

Inspect the matches

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

Matched commit samples

f808efe2 on GitHubdocs: update fast-writing pricing to new scheme (#34) (#36)Claude Code
64766465 on GitHubchore: bump version to 1.0.1 for ClawHub re-publish (#14)Claude Code
882952af on GitHubfix: correct metadata format to resolve ClawHub Suspicious scan (#12)Claude Code

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	25
Merge commits removed	−3
CI / dependency bots removed	−1
Considered	21

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 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 NarratorAI-Studio/narrator-ai-cli-skill

Scan another repository

Try

Agent-attributed commit share by month
Month	Agent share	Considered commits
2026-03	0%	4
2026-04	33.3%	15
2026-06	0%	1
2026-07	0%	1