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.

Pentest Report Generator

01Result

pwndoc/pwndoc ↗

pwndoc/pwndoc AI coding statistics: 4.2%

of 215 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.2% agent · top contributor 55.6%4 contributors
team

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

9
agent commits
206
other considered commits
4
agent contributors
55.6%
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

9assisted
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%21
2026-034.8%21
2026-040%17
2026-057.7%13
2026-063.6%55
2026-075.4%74
2026-087.7%13
2026-090%1

Peak month: 7.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic62.8%
GitHub CopilotGitHub31.4%

03Evidence

Inspect the matches

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

Matched commit samples

  • 4f5c6fd3 on GitHubFix stale backend/frontend README dev setup instructionsClaude Code
  • c716cc91 on GitHubEnforce ai-settings scopes via settings:read/update (Option B)Claude Code
  • 18689908 on GitHubStore-keyed QA run state with in-progress indicator and double-run guardClaude Code
  • dc0ad055 on GitHubPotential fix for pull request finding 'Semicolon insertion'GitHub Copilot
  • b05bed4f on GitHubPotential fix for pull request finding 'CodeQL / Double escaping or unescaGitHub Copilot
  • 7feab804 on GitHubPotential fix for pull request finding 'Unused variable, import, function 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 window248
Merge commits removed−33
CI / dependency bots removed−0
Considered215

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 →JavaScript AI coding statisticsCompare evidence across JavaScript 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 pwndoc/pwndoc

Scan another repository

Try