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.

Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

01Result

mksglu/context-mode ↗

mksglu/context-mode AI coding statistics: 38.9%

of 1,519 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate

38.9% agent · top contributor 81.6%37 contributors

individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

591

agent commits

928

other considered commits

agent contributors

81.6%

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

581assisted

10autonomous

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

Peak month: 77.6%. Bars are scaled to that peak, not to 100%.

Which agents

Agent	Vendor	Commits	Share
Claude Code	Anthropic	574	37.8%
GitHub Copilot	GitHub	11	0.7%
OpenAI Codex	OpenAI	6	0.4%

03Evidence

Inspect the matches

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

Matched commit samples

d1ae5625 on GitHubfix(security): confine ctx_execute_file to the project boundary (#852)Claude Code
2608e344 on GitHubrefactor(antigravity-cli): one-command agy plugin install (drop npm wrappeClaude Code
77e22a46 on GitHubfix(lifecycle): reap idle MCP bridge children to stop pi/omp accumulation Claude Code
a510c37e on GitHubFix Windows path compatibility in ctx-debug.sh (#553)GitHub Copilot
70a9c257 on GitHubInitial planGitHub Copilot
24cbf506 on GitHubReview fixes: add lifecycle hooks to constants, remove internal plan/spec GitHub Copilot
3d8db08b on GitHubfeat: add runtime storage override (#617)OpenAI Codex
572d451f on GitHubfix(codex): harden plugin hook routing (#575)OpenAI Codex
637d0bd4 on GitHub[codex] Fix stale better-sqlite3 ABI repair (#446)OpenAI Codex

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 window	2,186
Merge commits removed	−165
CI / dependency bots removed	−502
Considered	1,519

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 →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →TypeScript AI coding statisticsCompare evidence across TypeScript 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 mksglu/context-mode

Scan another repository

Try

Month	Agent share	Considered commits
2026-02	68.7%	83
2026-03	77.6%	388
2026-04	64.1%	295
2026-05	6%	562
2026-06	5.2%	191