- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Zero-Config Code Flow for Claude code & Codex
01Result
UfoMiao/zcf ↗UfoMiao/zcf AI coding statistics: 14.8%
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 |
|---|---|---|
| 2026-02 | 20% | 5 |
| 2026-03 | 0% | 13 |
| 2026-04 | 0% | 6 |
| 2026-05 | 50% | 4 |
| 2026-06 | 42.9% | 7 |
| 2026-07 | 24% | 25 |
| 2026-08 | 0% | 21 |
Peak month: 50%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Cursor Agent | Anysphere | 10 | 12.3% |
| Claude Code | Anthropic | 2 | 2.5% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
42635c66on GitHubdocs(skills): replace /zcf: prefix with skill invocation syntaxCursor Agent958eaf10on GitHubdocs(skills): unify command→skills naming across uninstall and docsCursor Agent1e4028e7on GitHubfix(skills): use symlink install for claude-code via skills CLICursor Agent42e2840eon GitHubdocs: update documentationClaude Code93335a5fon GitHubfeat(bmad): upgrade bmad-init template from V4 to V6Claude Code
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 | 81 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 81 |
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 UfoMiao/zcf