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.

Demisto is now Cortex XSOAR. Automate and orchestrate your Security Operations with Cortex XSOAR's ever-growing Content Repository. Pull Requests are always welcome and highly appreciated!

01Result

demisto/content ↗

demisto/content AI coding statistics: 2.3%

of 1,490 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.3% agent · top contributor 70.6%9 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

34
agent commits
1,456
other considered commits
9
agent contributors
70.6%
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

34assisted
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
2026-020.5%188
2026-031.9%210
2026-042.1%188
2026-052.9%170
2026-061.1%188
2026-073.1%196
2026-083.3%211
2026-093.6%139

Peak month: 3.6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub151%
Claude CodeAnthropic140.9%
Cursor AgentAnysphere60.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 8052ffc1 on GitHubAdd NodeZero pack (#45128)GitHub Copilot
  • f8125442 on GitHubCrtx 236720 aws security hub v2 (#44871)GitHub Copilot
  • 4364e72e on GitHubXSUP-69895 - Rapid7 InsightVM: fix fetch-assets streaming timeout on largeGitHub Copilot
  • afd221dc on GitHubPrisma AIRS 1.0.1: brand spelling fix, DLP UX improvements (#45879)Claude Code
  • 7971f2a6 on GitHubEpartington prisma airs initial pack (#45772)Claude Code
  • d00fbc62 on GitHubUpdate SpyCloud Enterprise Protection pack - add Access Data type (#45699)Claude Code
  • d8455cfc on GitHub[Doppel] API V2 support with OAuth 2.0 client credentials (pack v1.3.0) (#Cursor Agent
  • 380903e0 on GitHub[Doppel] Integration updates: revived-alert reopen, get-alerts filters, clCursor Agent
  • f474ba60 on GitHubfix(CybleEventsV2): improve fetch reliability and incident submission (#45Cursor 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 window1,491
Merge commits removed−1
CI / dependency bots removed−0
Considered1,490

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 demisto/content

Scan another repository

Try