# Audit Instructions

> When the bundled claude-api skill resolves in this session, prefer its prompt-audit for application-code prompts and model migration; this skill for Claude Code instruction surfaces. Report-only audit of CLAUDE.md, AGENTS.md, rules, skills, agents and hook text for stale, misstated, or conflicting instructions. Use when: 'audit instructions', 'too prescriptive', 'stale Claude Code behavior', 'my @path import is not loading', 'which instruction wins'. Missing text: audit-prompting-postures.

- Skill: `melodic-software/audit-instructions-3` (Agent Skill)
- Install (CLI): `npx get-skill add melodic-software/audit-instructions-3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/melodic-software/audit-instructions-3/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: melodic-software (https://skillmd.com/u/melodic-software)
- Updated: 2026-11-12
- Page: https://skillmd.com/skills/melodic-software/audit-instructions-3

---


# Audit instructions (eval stand-in)

Report-only: it lists findings and edits no file. This stand-in runs no audit; say what it would
check and stop.

