About — Undercut
Undercut is a free, MIT-licensed SKILL.md that coding agents (Claude Code, Codex, Cursor, Copilot, OpenCode) follow at dispatch time. A six-flag rubric assigns each unit of work a base model tier; three objective triggers — a failed verification, a measured disagreement between two cheap-tier attempts, or an explicit uncertainty flag — are the only things allowed to escalate it. Nothing escalates on a vibe or a self-reported confidence score.
It is not a proxy and does not sit on the network path between your agent and its model calls — it's a policy file your agent reads locally, composable with whatever gateway or compression layer you already run.
Every cost and pass-rate claim on the landing page traces to a public, reproducible benchmark harness (evals/ in the source repo), run against official test cases with deterministic graders — no LLM judge, no cherry-picked runs. See testing/README.md for the full methodology and raw results, or run it yourself for free with node src/main.js --mock.
Justin Winter — founder and builder. Contact links, source, and license are in humans.txt.
Free for individuals, forever. Pro ($9/mo or $59/yr — real-time pooled model testing, effort-level routing, category reporting, a hosted dashboard) and Teams ($349/mo including 12 seats — the same bundle on every seat, plus org-wide policy enforcement, a shared dashboard, and seat management) are a paid layer above the free skill, not a gate in front of it. Pro starts with a trial of the full bundle; Teams is onboarded personally by the founder — see pricing and the money-back guarantee. Enterprise is contact-only.
Updated 2026-08-20. Back to Undercut · Privacy · Terms · Accessibility · Brand