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.

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

01Result

GH05TCREW/pentestagent ↗

GH05TCREW/pentestagent AI coding statistics: 41.5%

of 130 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

41.5% agent · top contributor 87%3 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

87%

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

54assisted

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: 91.3%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	46	35.4%
GitHub Copilot	GitHub	8	6.2%

03Evidence

Inspect the matches

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

Matched commit samples

afa1209d on GitHubfeat(tui): add per-workspace auto-reload session preferenceClaude Code
ae5f2375 on GitHubstyle(tui): apply black formattingClaude Code
9c9dd3ee on GitHubfeat(tui): add Tab-to-autocomplete hint next to slash command inputClaude Code
9183f0bb on GitHubfix(docker): switch to kali-last-releaseGitHub Copilot
f4d7106a on GitHubfix(docker): add --fix-missing to handle kali-rolling mirror sync racesGitHub Copilot
ef9e5739 on GitHubrevert(docker): restore Dockerfile.kaliGitHub 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	204
Merge commits removed	−57
CI / dependency bots removed	−17
Considered	130

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 →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 GH05TCREW/pentestagent

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	0%	33
2026-03	5.6%	18
2026-04	91.3%	23
2026-05	64%	50
2026-07	0%	4
2026-08	0%	2