- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Review-first terminal diff viewer for agentic coders
01Result
modem-dev/hunk ↗modem-dev/hunk AI coding statistics: 11.8%
One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
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
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-03 | 2.3% | 256 |
| 2026-04 | 1.7% | 58 |
| 2026-05 | 3.7% | 107 |
| 2026-06 | 17.5% | 57 |
| 2026-07 | 35.9% | 92 |
| 2026-08 | 22.5% | 191 |
| 2026-09 | 5% | 101 |
Peak month: 35.9%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 96 | 11.1% |
| OpenAI Codex | OpenAI | 4 | 0.5% |
| GitHub Copilot | GitHub | 2 | 0.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
6d4440a5on GitHubfix(keys): match alt across terminal protocols (#991)Claude Codec6d15c06on GitHubfix(ui): keep suspended jobs alive upon fg (#996)Claude Codebfbfac8don GitHubfix(pager): stop CPU pegging and truncation on large piped documents (#978Claude Codec42a5e33on GitHubfix(build): prevent caller bunfig autoload (#456)OpenAI Codex71e2ff77on GitHubdocs: document auto theme selection (#451)OpenAI Codexc0cf6371on GitHubfix(build): prevent caller bunfig autoload (#452)OpenAI Codex65a27400on GitHubfeat: highlight .mts and .cts files as TypeScript (#485)GitHub Copilotf8bae973on GitHubfeat: complete native Windows 11 support (#285)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 window | 874 |
| Merge commits removed | −6 |
| CI / dependency bots removed | −6 |
| Considered | 862 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
Continue exploring
Related coding-agent evidence
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 modem-dev/hunk