# Vet

> Use when the user wants a security and trust-boundary review of the current design before implementation or release.

- Skill: `justinedevs/vet` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add justinedevs/vet`
- Raw SKILL.md: https://api.skillmd.com/api/skills/justinedevs/vet/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: JustineDevs (https://skillmd.com/u/justinedevs)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/justinedevs/vet

---


# Vet

Use this skill inside Codex to review security posture before the build lane. `$vet` remains the sole security gate even as Meta-Architect ships deeper native security playbooks.

## Output

Produce:
- `decision`, `status`, `evidence`, `blockers`, `next_allowed_triggers`
- trust boundaries
- authn/authz expectations
- sensitive data paths
- abuse cases and likely failure modes
- concrete mitigations
- accepted risks
- release blockers vs acceptable risks
- exact next trigger, usually `$vibe`

## Rules

- Prioritize material risks over exhaustive but low-value checklists.
- Use `references/security-playbooks.md` when you need the native security playbook set for common trust-boundary reviews.
- Keep security guidance product-owned and lane-aware. Do not introduce a second umbrella or a separate security release gate.
- Call out missing assumptions that affect security posture.
- Distinguish between must-fix blockers and documented accepted risk.