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.

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.

01Result

gadievron/raptor ↗

gadievron/raptor AI coding statistics: 0.5%

of 7,079 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
0.5% agent · top contributor 35.3%12 contributors
org-wide

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

34
agent commits
7,045
other considered commits
12
agent contributors
35.3%
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
2026-0250%2
2026-030%20
2026-045.9%170
2026-050.8%1653
2026-062.9%103
2026-070.1%793
2026-080.2%2934
2026-090%1404

Peak month: 50%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic330.5%
GitHub CopilotGitHub10%

03Evidence

Inspect the matches

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

Matched commit samples

  • 902bdefd on GitHubfeat(cve-env): integrate cve-env as packages/cve_env (Phase 1 lift-and-shiClaude Code
  • 33a4870a on GitHubfix(sandbox): fail closed on the degraded egress tier for untrusted-code cClaude Code
  • 9f22a9f7 on GitHubfix(dataflow): apply the rebind-KILL to the non-Python value-reach in the Claude Code
  • 9c7e89eb on GitHubRewrite README into canonical, user-focused guide and add complete `/projeGitHub 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 window7,213
Merge commits removed−63
CI / dependency bots removed−71
Considered7,079

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 gadievron/raptor

Scan another repository

Try