Check

A read-only drift detector that compares your SPEC.md against actual code without touching anything. Run it when you want to know if your implementation still matches your spec's invariants, interfaces, or task completion claims. It reads the relevant files, classifies violations by severity (HOLD, VIOLATE, MISSING, STALE), and spits out a grouped report with file and line citations. The output is deliberately bare bones, caveman style, and it never fixes anything or edits the spec. It just tells you what drifted and suggests which other skills you might invoke to remedy it. Useful if you treat SPEC.md as source of truth and want periodic audits without side effects.

skills.sh installs: 2.7K
GitHub stars: 1.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add juliusbrussee/cavekit --skill check --agent claude-code

Installs into .claude/skills of the current project.

Files

check — drift report

Pure diagnostic. Reports violations. Writes nothing. User decides remedy.

Spec drifting silently from code is the #1 SDD failure mode. check is the detector. Run it after each /build and before each ship — drift caught here is a diff; drift caught in prod is a §B.

LOAD

Read SPEC.md. If missing → "no spec, nothing to check." Stop.
Parse invocation args:
- §V → check invariants only (default)
- §I → check interfaces
- §T → audit task status vs code
- --all → all three

CHECK §V — invariants

For each V:

Translate invariant into verifiable claim about code.
Grep / read relevant files.
Classify: HOLD / VIOLATE / UNVERIFIABLE.
Record address + file:line evidence.

CHECK §I — interfaces

For each I item:

Locate implementation.
Classify:
- MATCH — shape in code = shape in spec.
- DRIFT — impl exists, shape differs.
- MISSING — impl absent.
- EXTRA — code exposes surface not in §I.