- Dataset
- 2026-10-27-catalog-ai-v2
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-10-27
- Window
- February–September 15, 2026
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap jobs to build it. Whoever built it never grades it.
01Result
chaseai-yt/claudex-loop ↗chaseai-yt/claudex-loop AI coding statistics: 82.6%
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 |
|---|---|---|
| 2026-06 | 100% | 2 |
| 2026-07 | 100% | 4 |
| 2026-08 | 92.9% | 14 |
| 2026-09 | 0% | 3 |
Peak month: 100%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 19 | 82.6% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
f8c111deon GitHubdocs: four-phase framing everywhere — SKILL.md, plugin + marketplace manifClaude Code17fc75c1on GitHubdocs: four-phase framing — BUILD + cross-inspection promoted to the phase Claude Codee7d187bbon GitHubdocs: drop formerly-crucible line from heroClaude 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 | 23 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 23 |
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 chaseai-yt/claudex-loop