- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Coz: Causal Profiling
01Result
plasma-umass/coz ↗plasma-umass/coz AI coding statistics: 80.3%
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 |
|---|---|---|
| 2026-02 | 87.2% | 39 |
| 2026-03 | 27.3% | 11 |
| 2026-04 | 50% | 2 |
| 2026-07 | 95.8% | 24 |
Peak month: 95.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 59 | 77.6% |
| GitHub Copilot | GitHub | 2 | 2.6% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
299ffc13on GitHubci: trigger checks against retargeted baseClaude Code1eb5a372on GitHubScale macOS sample delays by the sampler's measured cadenceClaude Codea84e9cf6on GitHubci: nudge workflow trigger after rebaseClaude Codedc61dd2fon GitHubci: accept both libcoz shared library suffixesGitHub Copilot5259a26eon GitHubci: set least-privilege workflow token permissionsGitHub 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 | 107 |
| Merge commits removed | −31 |
| CI / dependency bots removed | −0 |
| Considered | 76 |
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 plasma-umass/coz