macanderson

Audit Parity — Security skill for Claude Code

Security community

Run a backend↔frontend capability parity audit and produce a ranked gap backlog.

How to install Audit Parity

Installs to ~/.claude/skills/macanderson-agent-harness-audit-parity/SKILL.md

Terminal
mkdir -p ~/.claude/skills/macanderson-agent-harness-audit-parity && curl -fsSL https://raw.githubusercontent.com/macanderson/agent-harness/HEAD/commands/audit-parity.md -o ~/.claude/skills/macanderson-agent-harness-audit-parity/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Audit Parity does


description: Run a backend↔frontend capability parity audit and produce a ranked gap backlog argument-hint: [scope: whole product, a domain, or an API subtree] allowed-tools: Read, Grep, Glob, Bash

Scope: $ARGUMENTS (default: the whole product)

Delegate to the **parity-auditor** agent for the scoped area. Requirements for this run:

  1. Inventory ALL eight capability sources (endpoints; per-endpoint params — every optional filter/sort/expansion/bulk/pagination flag is a sub-capabi

Alternatives in Security

  • Audit Agent Sessions — Analyze all agent sessions from the last 3 days across Claude, Codex, and Gemini 238 ★
  • Gdpr Review — Audit the codebase (or a given path/feature) for GDPR compliance and produce a prioritized findings report 172 ★
  • Sail Skill — SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, secur 122 ★

Full documentation available on GitHub

View Source Repository