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.

Autonomous Hacking Agent for Red Team

BitterSecurity/Decepticon ↗

BitterSecurity/Decepticon AI coding statistics: 25.6%

of 940 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
25.6% agent · top contributor 39.4%6 contributors
team

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

241
agent commits
699
other considered commits
6
agent contributors
39.4%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

241assisted
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
2026-03100%65
2026-0470%120
2026-0510.3%358
2026-0611%335
2026-0742.5%40
2026-084.5%22

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

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic23925.4%
GitHub CopilotGitHub20.2%

Inspect the matches

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

Matched commit samples

  • d28993c6 on GitHubdocs: the README plays the new demo film (#792)Claude Code
  • 5e34a6d7 on GitHubfix(kg): make engagement scope a boundary, not a convention (#790)Claude Code
  • 4484f85c on GitHubfeat(llm): make self-hosted vLLM discoverable, matching the Ollama shortcuClaude Code
  • 01b59b89 on GitHubPotential fix for pull request finding 'CodeQL / Module is imported with 'GitHub Copilot
  • 876440fa on GitHubPotential fix for pull request finding 'CodeQL / Empty except'GitHub Copilot

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 window1,216
Merge commits removed−269
CI / dependency bots removed−7
Considered940

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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 BitterSecurity/Decepticon

Scan another repository