deep-review

Coordinate multi-agent security reviews across Go and Rust codebases.

8|2|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/psaab/xpf --skill deep-review-psaab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-review
Source: https://github.com/psaab/xpf/tree/main/.claude/skills/deep-review
Command: npx skills add https://github.com/psaab/xpf --skill deep-review-psaab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the challenge of performing comprehensive, deep-dive security and quality reviews on large, complex codebases by automating the coordination of specialized subagents.

Core Features & Use Cases

  • Distributed Review: Fans out analysis across the entire repository using domain-specific personas for Rust and Go subsystems.
  • Worktree Isolation: Ensures review integrity by using detached git worktrees, preventing interference with the main working directory.
  • Use Case: Use this to conduct a full-coverage defensive security audit of a high-performance networking project to identify memory safety, concurrency, and policy enforcement vulnerabilities before deployment.

Quick Start

Run the deep-review skill to initiate a full-coverage defensive security audit of the current repository.

Frequently Asked Questions about deep-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform a defensive security audit on a large Go and Rust codebase?

A defensive security audit on large Go and Rust codebases can be performed by partitioning the repository into expertise-based batches and executing isolated analysis subagents to generate a unified triage report.

What is multi-agent code review and how does it identify memory safety vulnerabilities?

Multi-agent code review is a distributed analysis mechanism that uses domain-specific personas to evaluate codebases, identifying memory safety vulnerabilities by executing isolated subagents that target architectural and concurrency flaws.

Does deep code review work with high-performance networking projects written in Rust and Go?

Deep code review works with high-performance networking projects by using domain-specific personas to analyze Rust and Go subsystems, specifically targeting concurrency and policy enforcement vulnerabilities.

What's the best way to automate reproducible security assessments across complex repositories?

Automating reproducible security assessments across complex repositories is best achieved by fanning out analysis using detached git worktrees, which prevents interference with the main working directory and ensures review integrity.

How do duplicate suppression and freshness gating work in automated code reviews?

Duplicate suppression and freshness gating work in automated code reviews by applying automated checks during the triage phase, ensuring that the generated report contains only unique, up-to-date architectural and memory-safety vulnerability findings.