Code Reviewer

    42

    Reviews your code for bugs, security vulnerabilities, logic errors, performance issues, and style violations. Organizes findings by severity and suggests fixes with code examples.

    Free

    2,062 uses4.3 (19 reviews)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Code Reviewer

    Example session with this skill installed

    Review my recent changes in auth.ts. I've just implemented the password hashing logic for the new user registration flow.

    • Read your context and instructions
    • Compiled the code reviewer

    Review Summary

    The PR looks solid, but has one critical security flaw.

    Critical

    auth.ts:15 — Unsalted MD5 used for passwords.

    const hash = crypto.createHash('md5').update(password).digest('hex');
    

    Use Argon2 or bcrypt instead to prevent rainbow table attacks.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Run a structured code review on your recent changes without waiting for a teammate. This skill checks for security vulnerabilities (SQL injection, XSS, authentication bypasses), logic errors, edge cases, performance issues, and style violations.

    Findings are organized by severity: Critical, Warning, and Suggestion. Each finding includes the file, line number, a description of the issue, and a concrete fix. Use it as a first pass before peer review, or as your only reviewer on solo projects.

    • Cannot execute code to find runtime-only bugs.
    • Limited context on very large monorepos (better results on specific diffs).
    • May not catch violations of private/internal proprietary libraries.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    4.3
    19 reviews
    5
    14
    4
    1
    3
    1
    2
    1
    1
    2

    Trust & safety

    Security scan

    Security scan passed 8 months ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Listed8 months ago
    Updated15 days ago

    What's inside

    Frequently Asked Questions

    The agent analyzes code across five key dimensions: logic bugs, security vulnerabilities (like injection and hardcoded secrets), performance bottlenecks, maintainability/readability, and architectural consistency.

    Yes. It can analyze uncommitted changes via `git diff`, review entire feature branches by comparing them to a base branch (e.g., `main...HEAD`), or review specific files and code snippets you provide.

    Findings are categorized into 'Critical' (must fix before merge), 'Suggestions' (maintainability and performance), and 'Nitpicks' (style and minor refactors) to help you prioritize your workflow.

    No. The skill follows the established style and patterns of your existing codebase. It avoids suggesting changes for purely subjective style preferences unless they violate the project's own standards.

    Every finding includes the specific file name, line number, an explanation of why the change matters, and a fenced code block showing exactly how to fix the issue.

    New in Code Quality & Review