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.

This repo hosts Prowler OSS (CLI and Local Server). Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment for Humans and AI Agents.

01Result

prowler-cloud/prowler ↗

prowler-cloud/prowler AI coding statistics: 4.3%

of 1,508 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.3% agent · top contributor 36.9%24 contributors
org-wide

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

65
agent commits
1,443
other considered commits
24
agent contributors
36.9%
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

65assisted
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
2026-023.5%170
2026-033.9%228
2026-046.4%219
2026-055.6%198
2026-065.9%219
2026-071.6%244
2026-083.9%180
2026-092%50

Peak month: 6.4%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic453%
GitHub CopilotGitHub140.9%
Cursor AgentAnysphere60.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 13a31d92 on GitHubfeat(mcp): raise instead of returning error objects in the Prowler Docs toClaude Code
  • 9898cf73 on GitHubfeat(m365): add defender_domain_dmarc_records_published check (#11936)Claude Code
  • 6e71dee8 on GitHubfeat(awslambda): add awslambda_layer_no_secrets_in_content check (#12233)Claude Code
  • 02df22ca on GitHubfix(html): escape provider identity fields in report header (#12424)GitHub Copilot
  • e15f6970 on GitHubfix(ci): use PROWLER_BOT_ACCESS_TOKEN for release freeze (#12295)GitHub Copilot
  • 2375f1d9 on GitHubfix(api): uvicorn worker keepalive (#11663)GitHub Copilot
  • 1b228d59 on GitHubfeat(compliance): replace FedRAMP 20x pilot KSI with Consolidated Rules 20Cursor Agent
  • 2646068e on GitHubfix(app): correct the worker KEDA PostgreSQL scaler (#12055)Cursor Agent
  • f5fe9c7b on GitHubci(helm): publish immutable chart versions on release (#12056)Cursor Agent

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 window1,592
Merge commits removed−0
CI / dependency bots removed−84
Considered1,508

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 →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 prowler-cloud/prowler

Scan another repository

Try