build
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.
> /plugin marketplace add JuliusBrussee/cavekit > /plugin install ck@cavekit-marketplace
How it fires
How this command gets triggered: by you, by Claude, or both.
/reviewContext preview
What this command does when you run it.
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.
description: Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate. argument-hint: [§T.n | --all]
Invoke the **review** skill (`skills/review/SKILL.md`). Construct a senior reviewer whose authority comes from the codebase, §R, and live best-practice, then try to refute the spec (§G §C §I §R §V §T). Every finding cites evidence — file:line or source; flag unverifiable ones `[unverified]`. Draft §V lines for HARDEN findings and hand them to spec. End on an explicit GO / NO-GO gate.
Frozen — compressed spec-driven development plugin for Claude Code. Still works; active development moved to JuliusBrussee/caveman.
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
Sharpen a fuzzy idea into §G/§C before spec. Calibrated interrogation, one question at a time.
Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.