robertsolves

Audit Slop — Security skill for Claude Code

Security community

Read-only audit for the anti-patterns AI coding agents repeatedly introduce (hallucinated APIs, missing ownership checks, swallowed errors, silent fallbacks, fake tests, drift, prose slop in comments.

How to install Audit Slop

Installs to ~/.claude/skills/robertsolves-agent-commands-audit-slop/SKILL.md

Terminal

mkdir -p ~/.claude/skills/robertsolves-agent-commands-audit-slop && curl -fsSL https://raw.githubusercontent.com/robertsolves/agent-commands/HEAD/commands/audit-slop.md -o ~/.claude/skills/robertsolves-agent-commands-audit-slop/SKILL.md

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

What Audit Slop does

description: Read-only audit for the anti-patterns AI coding agents repeatedly introduce (hallucinated APIs, missing ownership checks, swallowed errors, silent fallbacks, fake tests, drift, prose slop in comments and UI strings), then sweep the rest of the codebase for the same mistakes. Run on a diff before merging, or with `all` for a full sweep. Not for fixing band-aids with the user — use /find-bandaids; not for Dart-only rulebook checks — use /dart-audit-code; not for comment accuracy a

Alternatives in Security

Security Ownership Map — Map people-to-file ownership, compute bus factor, and identify risks 14.6k ★
Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
Skill Code Review — Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis 2.8k ★