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.

Malware Configuration And Payload Extraction

01Result

kevoreilly/CAPEv2 ↗

kevoreilly/CAPEv2 AI coding statistics: 7.5%

of 711 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

7.5% agent · top contributor 39.6%12 contributors

org-wide

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

agent commits

658

other considered commits

agent contributors

39.6%

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

53assisted

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: 20%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Gemini CLI	Google	32	4.5%
Claude Code	Anthropic	21	3%

03Evidence

Inspect the matches

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

Matched commit samples

6819fac1 on GitHubApply suggestions from code reviewGemini CLI
3b5c2dd6 on GitHubUpdate web/web/guac_settings.pyGemini CLI
756dde85 on GitHubUpdate web/web/guac_settings.pyGemini CLI
68ee09da on GitHubFix Elasticsearch reporting when MongoDB is also enabled + ignore SuricataClaude Code
310f5a6b on GitHubfix(processing): lazy-import imagehash to keep prefork supervisor kernel-sClaude Code
d2719935 on GitHubfix(peepdf): lazy-import STPyV8/V8 bindings (was spawning 16 native threadClaude 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	864
Merge commits removed	−108
CI / dependency bots removed	−45
Considered	711

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 →Gemini CLI commitsBrowse repositories with detected Gemini CLI 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 kevoreilly/CAPEv2

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	11.6%	69
2026-03	2.8%	36
2026-04	20%	40
2026-05	5.4%	129
2026-06	10.7%	103
2026-07	6.4%	265
2026-08	2%	51
2026-09	0%	18