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.

🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.

01Result

junhoyeo/tokscale ↗

junhoyeo/tokscale AI coding statistics: 4.5%

of 1,251 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
4.5% agent · top contributor 10.7%32 contributors
org-wide

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

56
agent commits
1,195
other considered commits
32
agent contributors
10.7%
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

56assisted
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
2026-024.4%319
2026-034.2%144
2026-040%79
2026-052.5%119
2026-066.3%128
2026-075.1%177
2026-084.6%218
2026-099%67

Peak month: 9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic493.9%
Cursor AgentAnysphere50.4%
DevinCognition10.1%
GitHub CopilotGitHub10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 57a040f9 on GitHubfix(pricing): prefer the standard service tier among an author's OpenRouteClaude Code
  • 6a97b5ea on GitHubfix(submit): bound the parser high-water by the store's retention floor (#Claude Code
  • 4b343e43 on GitHubfix(submit): report the parser high-water deficit instead of adding nothinClaude Code
  • 3259d8b9 on GitHubfix(droid): show transcript-dated usage on the web graph (#1267)Cursor Agent
  • ca928f07 on GitHubfix(pricing): resolve OpenAI Daybreak Blue alias (#1140)Cursor Agent
  • 84d67950 on GitHubfix(claude): discover sessions under CLAUDE_CONFIG_DIR instead of a fixed Cursor Agent
  • d3107970 on GitHubfeat(settings): add Danger Zone with self-service data and account deletioDevin
  • cbbd0dff on GitHubfix: handle underscore-format cache token attributes from Copilot CLI OTELGitHub 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 window1,518
Merge commits removed−130
CI / dependency bots removed−137
Considered1,251

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 →Devin commitsBrowse repositories with detected Devin signatures →Rust AI coding statisticsCompare evidence across Rust 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 junhoyeo/tokscale

Scan another repository

Try