# Audit

> Load and follow the **multica-ops** skill (`../mops/SKILL.md`), executing

- Skill: `jamillazarev/audit` (Agent Skill)
- Install (CLI): `npx skillmds@latest add jamillazarev/audit`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jamillazarev/audit/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: jamillazarev (https://skillmd.com/u/jamillazarev)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/jamillazarev/audit

---


Load and follow the **multica-ops** skill (`../mops/SKILL.md`), executing
its `/multica-ops:audit` flow. Health AND opportunities: token burn, limit-killed runs, tier misfits, stalls, hygiene, mention cycles, secrets, design-system hygiene; plus process improvements. Finding → recommendation → impact.
A full sweep is **dispatched** — an autopilot in `create_issue` mode with a member subscriber —
and the console stays answerable while it runs.