code-review

Review code changes for security, POSIX compatibility, and test coverage.

31|3|Updated Mar 8, 2026
One-click install
npx skills add https://github.com/DataDog/rshell --skill code-review-datadog
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/DataDog/rshell/tree/main/.claude/skills/code-review
Command: npx skills add https://github.com/DataDog/rshell --skill code-review-datadog

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of conducting thorough code reviews, ensuring code quality, security, and compatibility, especially critical for AI agent environments where safety is paramount.

Core Features & Use Cases

  • Security Auditing: Identifies potential sandbox escapes, command injection, and resource exhaustion vulnerabilities.
  • Compatibility Checks: Verifies adherence to bash behavior and POSIX standards.
  • Test Coverage Analysis: Assesses the adequacy of scenario and Go tests for new or modified code.
  • Use Case: Before merging a pull request that modifies the rshell interpreter's command execution logic, use this Skill to perform a deep security and correctness review.

Quick Start

Use the code-review skill to review the changes in the current pull request.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I automate security auditing for AI agent environments before merging a pull request?

Automated security auditing for AI agent environments detects sandbox escapes, command injection, and resource exhaustion vulnerabilities. It reviews code changes against defined security invariants before pull request merges to ensure safety.

How do I check bash compatibility and POSIX standard adherence in my code changes?

Checking bash compatibility and POSIX standard adherence analyzes modified code to verify correct shell behavior. It identifies deviations from POSIX standards and bash execution logic to prevent runtime errors.

What is the best way to analyze test coverage metrics for modified interpreter code?

Analyzing test coverage metrics for modified interpreter code assesses the adequacy of scenario and Go tests. It evaluates whether new or modified code paths have sufficient test coverage to identify untested vulnerabilities.

Does this code review process identify command injection vulnerabilities in shell scripts?

Yes, this code review process identifies command injection vulnerabilities in shell scripts. It performs comprehensive security auditing to detect potential sandbox escapes and command injection flaws in AI agent environments.

Can I use this to perform deep correctness reviews on modified command execution logic?

Yes, you can use this to perform deep correctness reviews on modified command execution logic. It analyzes code changes against defined invariants and identifies bugs with detailed findings and remediation suggestions.

When do I need comprehensive code review for AI agent safety and compatibility?

You need comprehensive code review for AI agent safety and compatibility before merging code changes. It is critical when modifications affect command execution logic, ensuring security invariants, POSIX behavior, and test coverage are verified.