Pulse
2026-09-18-v3.0
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.

secator - the pentester's swiss knife

01Result

freelabz/secator ↗

freelabz/secator AI coding statistics: 53.5%

of 254 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
53.5% agent · top contributor 97.1%3 contributors
individual

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

136
agent commits
118
other considered commits
3
agent contributors
97.1%
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

136assisted
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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-020%12
2026-0325%8
2026-0455.7%61
2026-0528.6%21
2026-0656%84
2026-0770.4%27
2026-0858.3%24
2026-0982.4%17

Peak month: 82.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic13352.4%
GitHub CopilotGitHub41.6%

03Evidence

Inspect the matches

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

Matched commit samples

  • c6996565 on GitHubperf(cli): stream workspace summary queries (memory bounded) (#1388)Claude Code
  • 68885a51 on GitHubfix+perf(query): --uniq/--count/--group render correctly and stream (memorClaude Code
  • a2f3bf97 on GitHubfeat(cli): workspace summary counts UNIQUE vulnerabilities by default (#13Claude Code
  • 76f782e9 on GitHubdocs: add CONFIG.md and debug documentation to CONTRIBUTING.md (#781)GitHub Copilot
  • 6510ab50 on GitHubfix: divide rate_limit by chunk count when tasks are chunked (#759)GitHub Copilot
  • cb27f559 on GitHubci(security): only allow read permissions for tests.yml workflow (#956)GitHub 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 window254
Merge commits removed−0
CI / dependency bots removed−0
Considered254

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 freelabz/secator

Scan another repository

Try