Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    code review pro

    1

    Automated polyglot code review for security vulnerabilities, logic bugs, and performance bottlenecks.

    $7.99

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    Security scanned
    code review pro

    code review pro

    Example session with this skill installed

    Review this Python snippet for a PR

    def get_user(request):
    user_id = request.args.get('id')
    query = "SELECT * FROM users WHERE id = " + user_id
    return db.execute(query)
    • Read your context and instructions
    • Compiled the code review pro

    I have analyzed the provided Python snippet. I found one critical security vulnerability regarding raw SQL execution.

    Code Review: user_fetch.py

    CRITICAL (fix before merge)

    • File: user_fetch.py | Line 3-4
    • Issue: SQL Injection vulnerability.

    Why it matters: The code directly concatenates user-provided input (user_id) into a SQL string. An attacker could provide a crafted ID like 1; DROP TABLE users; to execute arbitrary commands or bypass authentication.

    • Suggested Fix: Use parameterized queries (prepared statements) provided by your database driver.
    
# Fixed Version
def get_user(request):
    user_id = request.args.get('id')
    query = "SELECT * FROM users WHERE id = ?"
    return db.execute(query, (user_id,))

    WARNING (should fix)

    • File: user_fetch.py | Line 4
    • Issue: Missing Error Handling.

    Why it matters: If the database connection fails or the query execution throws an exception, the application will crash or return a 500 error without context.

    • Suggested Fix: Wrap the database execution in a try-except block and log the error.

    INFO

    • Files reviewed: 1
    • Lines analyzed: 5
    • Issue density: 0.4 issues per line

    Next steps

    1. Implement the parameterized query fix immediately.
    2. Add a global exception handler or local try-except block for database operations.
    3. Verify if other endpoints in this module use string concatenation for queries.

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

    What you get

    Identify SQL injection and XSS vulnerabilities before they reach production.Detect memory leaks and unclosed resource handles in Go or Rust code.Flag high cyclomatic complexity and N+1 queries in backend controllers.Provide structured checklists for PR reviewers to speed up merge cycles.

    About this skill

    The problem

    Manual code reviews are slow, prone to human error, and often miss critical security vulnerabilities or subtle concurrency bugs. Developers frequently spend time on trivial style debates while missing deeper architectural flaws and resource leaks.

    What it does

    • Scans for high-risk security flaws including SQL injection, XSS, command injection, and hardcoded secrets.
    • Identifies logic errors such as null reference risks, race conditions, and unhandled exceptions.
    • Detects performance bottlenecks like N+1 query patterns and high cyclomatic complexity.
    • Generates a structured, severity-rated report with specific line numbers and actionable fix snippets.

    Frameworks & tools

    Optimized for Python, JavaScript, TypeScript, Go, Rust, and Solidity. Works with raw source files, diff/patch outputs, and GitHub/GitLab PR URLs.

    Why this beats prompting it yourself

    This skill implements a three-pass analysis strategy that forces the agent to look for specific vulnerability patterns and logic gaps before summarizing. It prevents "hallucinated" security claims by requiring evidence-based citations and maintains a professional signal-to-noise ratio by suppressing minor style nitpicks in favor of critical fixes.

    Use cases

    • Perform pre-merge security checks on pull requests.
    • Audit smart contracts for common Solidity vulnerabilities.
    • Identify memory leaks and unclosed handles in long-running backend services.
    • Enforce quality standards across a polyglot microservices architecture.

    Known limitations

    Does not perform infrastructure-level penetration testing or SOC2/HIPAA compliance audits. Skips minified files, binary artifacts, and generated code.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 23 days ago

    • Passed all security checks, Safe to install

    Listed23 days ago

    What's inside

    Frequently Asked Questions