Run this repository's audits per release: the release audit of the diff since the last tag, before tagging, and after it the rotation audit of one area read whole and the guidance audit of each runtime's published guidance. Writes the briefs for read-only readers, then files what they confirm.
Installs into .claude/skills of the current project.
Are you the author of Audit Repository?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/ejryan89-audit-repository)
---
name: audit-repository
description: >-
Run this repository's audits per release: the release audit of the diff since the last tag, before tagging, and
after it the rotation audit of one area read whole and the guidance audit of each runtime's published guidance.
Writes the briefs for read-only readers, then files what they confirm.
argument-hint: "release [--since REF] | rotation [--record TAG] | guidance [--record TAG]"
disable-model-invocation: true
allowed-tools: ["Bash(python -B .claude/skills/audit-repository/scripts/audit_repository.py *)", "PowerShell(python -B .claude/skills/audit-repository/scripts/audit_repository.py *)"]
---
Read and follow `../../../.claude/skills/audit-repository/SKILL.md`, a path relative to this file, as the authoritative workflow.
Run its commands from the repository root, the folder that holds `.agents` and `.claude`, and resolve every relative path it names from there.
A command that writes a shim under `.agents` needs an approval to run outside Codex's sandbox, which keeps `.agents` read-only.
