- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
git push no-mistakes
01Result
kunchenguid/no-mistakes ↗kunchenguid/no-mistakes AI coding statistics: 3.3%
Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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 |
|---|---|---|
| 2026-04 | 0% | 211 |
| 2026-05 | 0% | 41 |
| 2026-06 | 8.7% | 46 |
| 2026-07 | 2.8% | 72 |
| 2026-08 | 4.5% | 89 |
| 2026-09 | 11.9% | 59 |
Peak month: 11.9%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 11 | 2.1% |
| Cursor Agent | Anysphere | 5 | 1% |
| GitHub Copilot | GitHub | 1 | 0.2% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
bace1586on GitHubfeat(eval): auto-ingest fixed CI misses (#1012)Claude Codef0a88580on GitHubfeat(pipeline): add live validation to the test gate (#999)Claude Code80ab4d88on GitHubfix(pipeline): attest PR heads before pushing (#994)Claude Code5173f42aon GitHubfix(deps): bump golang.org/x/text to v0.41.0 for CVE-2026-56852 (#1073)Cursor Agent68ae62f1on GitHubfix(daemon): refuse reruns that differ from the clean caller HEAD (#972)Cursor Agentd0c4feb4on GitHubfeat(config): make gate reconcile timings configurable (#862)Cursor Agentaedb3a14on GitHubfeat(agent): add GitHub Copilot CLI agent backend (#318)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 | 675 |
| Merge commits removed | −1 |
| CI / dependency bots removed | −156 |
| Considered | 518 |
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 kunchenguid/no-mistakes