- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.
01Result
backnotprop/plannotator ↗backnotprop/plannotator AI coding statistics: 15.4%
A small group is using agents. Adoption has spread beyond one person but is not project-wide.
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 |
|---|---|---|
| 2026-02 | 54.2% | 59 |
| 2026-03 | 55.2% | 192 |
| 2026-04 | 2.9% | 139 |
| 2026-05 | 11.8% | 119 |
| 2026-06 | 4.6% | 87 |
| 2026-07 | 0.7% | 152 |
| 2026-08 | 0.5% | 193 |
| 2026-09 | 0% | 111 |
Peak month: 55.2%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 145 | 13.8% |
| Devin | Cognition | 12 | 1.1% |
| GitHub Copilot | GitHub | 4 | 0.4% |
| OpenAI Codex | OpenAI | 1 | 0.1% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
c8da6345on GitHubfeat(ui): Shift+1-4 shortcuts to switch annotation mode (#1244)Claude Code78dc46b8on GitHubfix(ui): move Save to the first tab stop in the comment popover footer (#1Claude Code1e631ac6on GitHubfix(vscode): bridge clipboard and forward keystrokes in webview (#970)Claude Code127f6c2con GitHubMake /workspaces/ system-themed with a custom dark palette (#788)Devinabca6368on GitHubTighten Nav for mobile (#782)Devin64780211on GitHubHide Blog link in Nav on mobile (#781)Devina0a6edd3on GitHubfeat: print support with export menu integration and keyboard shortcut (#4GitHub Copilot08fcaaf0on GitHubfeat: Interactive checkboxes with annotation tracking (#423)GitHub Copilot2d90d381on GitHubfix: Detect calling agent via env vars and centralize agent config (#418)GitHub Copilot1287bfa5on GitHubDisable bunfig autoload for release binaries (#937)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 | 1,070 |
| Merge commits removed | −12 |
| CI / dependency bots removed | −6 |
| Considered | 1,052 |
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 backnotprop/plannotator