Audit Deep — Security skill for Claude Code
Full-stack audit: architecture, code quality, performance, UX debt, security, test gaps.
How to install Audit Deep
Installs to ~/.claude/skills/kmshihab7878-claude-code-setup-audit-deep/SKILL.md
mkdir -p ~/.claude/skills/kmshihab7878-claude-code-setup-audit-deep && curl -fsSL https://raw.githubusercontent.com/kmshihab7878/claude-code-setup/HEAD/commands/audit-deep.md -o ~/.claude/skills/kmshihab7878-claude-code-setup-audit-deep/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Deep does
description: "Full-stack audit: architecture, code quality, performance, UX debt, security, test gaps. Produces prioritized fix list. Does not implement — only inspects."
/audit-deep — Full-Stack Audit Mode
Do not implement anything yet. Inspect first, report second.
Audit Dimensions
Evaluate the target area across these dimensions:
1. Architecture
- Module boundaries and coupling
- Abstraction quality (over/under-abstracted?)
- Data flow coherence
- State management consis
Alternatives in Security
- FastAPI Review — Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, secu 243.5k ★
- Tech Debt Skill — Claude Code skill that produces a thorough, file-cited tech debt audit of an entire codebase 590 ★
- Mobile Review — Senior-level deep review of an existing mobile app 107 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Engineering Audit
Full-spectrum engineering health audit: scores Maintainability, Security, Testing, Architecture, Documentation
Simple Onboard
Fast read-only orientation on ANY repo (stack, structure, run/test commands) PLUS a R.Code-suitability verdict
Shipwright
One skill to design, build, test, polish, and ship world-class software. A complete AI coding agent skill cove
Expo Performance Audit
An installable agent skill for reviewing an Expo app before release. It inspects project code and configuratio
Ops Audit
Audit an existing Claude Code harness for runtime assumptions, operational debt, and failure recovery gaps (se
Vibe Guard
Full safety check for AI-generated code before pushing. Runs production resilience, security, and comprehensio
Related Agents
Tuhin
Digital twin of Tuhin Bepari — senior full-stack engineer who implements features exactly as Tuhin would. Use
State Auditor
Deep CURRENT-STATE audit (node C). Inspects the repository and the running product from scratch — what exists,
Security Vulnerability Scanner
Use this agent when you need to identify security vulnerabilities in code, perform security audits, or get a p