code quality analyzer

    1

    Automated professional code review covering OWASP security, performance, and architectural patterns with remediations.

    $3

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    code quality analyzer

    Example session with this skill installed

    Review this TypeScript function for security and performance: async function loadData(id) { const user = await db.query("SELECT * FROM users WHERE id = " + id); return user; }

    • Read your context and instructions
    • Compiled the code quality analyzer

    I have completed a systematic review of the provided TypeScript function. The analysis identified one critical security vulnerability and one performance suggestion.

    Finding #1 - Security (Critical Severity)

    File: data-loader.ts:1
    Issue: SQL Injection vulnerability. The input id is concatenated directly into the query string without sanitization or parameterization.

    Impact:

    • An attacker can bypass authentication or extract the entire database by passing a crafted string (e.g., 1 OR 1=1).

    Remediation:

    // Before
    const user = await db.query("SELECT * FROM users WHERE id = " + id);
    
    // After
    const user = await db.query("SELECT * FROM users WHERE id = $1", [id]);
    

    Finding #2 - Performance (Low Severity)

    File: data-loader.ts:1
    Issue: Unnecessary data retrieval. Using SELECT * fetches all columns, including potentially large blobs or sensitive fields not required by the caller.

    Impact:

    • Increases memory usage and network latency.

    Remediation:

    // After
    const user = await db.query("SELECT id, username, email FROM users WHERE id = $1", [id]);
    

    Executive Summary

    • Total Findings: 2
    • Critical: 1 | High: 0 | Medium: 0 | Low: 1
    • Overall Risk Rating: CRITICAL

    Top Priorities Before Merge:

    1. Fix SQL Injection in loadData to prevent unauthorized database access.
    2. Implement column selection to optimize data transfer.

    Next steps

    • Apply the parameterized query fix immediately.
    • Define a strict User interface to limit the fields selected from the database.
    • Run a global scan for other instances of string concatenation in database queries.

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

    About this skill

    Manual code reviews are slow, inconsistent, and often miss critical security vulnerabilities. This skill provides a systematic static analysis framework for developers who need production-grade feedback on correctness, security, performance, and architecture without waiting for a human peer.

    What it does

    • Bug Detection identifies off-by-one errors, null dereferences, race conditions, and improper error handling.
    • Security Auditing scans for OWASP Top 10 vulnerabilities including injection, broken access control, and sensitive data exposure.
    • Performance Profiling flags N+1 query patterns, memory leaks, and inefficient algorithms.
    • Maintainability Review detects DRY violations, deep nesting, and complex logic requiring refactoring.
    • Architectural Validation checks for circular dependencies, separation of concerns, and pattern consistency.

    How it works

    1. Context Gathering where the agent reads changed files, commit history, and existing codebase patterns.
    2. Systematic Analysis involving a multi-dimensional scan from correctness to architecture.
    3. Findings Documentation where each issue is logged with severity, impact, and a specific code remediation.
    4. Summary Reporting providing an executive risk rating and a prioritized list of blockers.

    Frameworks & tools

    This skill is language-agnostic with specialized rules for JavaScript, TypeScript, Python, Java, C#, and Go. It is optimized for use within Claude Code, Cursor, and other agentic CLI environments.

    Why this beats prompting it yourself

    Generic prompts often return vague advice or miss domain-specific security risks like XXE or insecure deserialization. This skill enforces a structured severity-based reporting format and a systematic five-pillar review process that ensures no category is overlooked.

    Use cases

    • Pre-merge Quality Gate to catch critical bugs and security flaws before they hit the main branch.
    • Legacy Refactoring to identify technical debt and maintainability issues in old modules.
    • Onboarding Audits to ensure new contributors are following established architectural patterns.
    • Security Hardening for a focused deep-dive into OWASP Top 10 compliance for new features.

    Known limitations

    Does not execute code or perform runtime benchmarking. Security findings are heuristic-based and require manual verification. Architecture suggestions assume standard patterns.

    Static analysis only; no runtime execution. Security findings are heuristic-based. Performance impact is estimated, not benchmarked. Requires manual verification of high-risk vulnerabilities.

    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

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago
    Updated27 days ago

    What's inside

    Frequently Asked Questions

    The analyzer supports all major languages but offers specialized optimization for JavaScript, TypeScript, Python, Java, C#, and Go. It is designed to work seamlessly within agentic environments like Claude Code, Cursor, and other CLI-based AI tools.

    Unlike general prompts that offer surface-level advice, this skill uses a structured five-pillar framework to ensure specific vulnerabilities like OWASP Top 10 risks are never overlooked. It delivers high-density, severity-ranked feedback with specific code remediations rather than vague suggestions.

    The skill performs static analysis to identify potential logic errors, security flaws, and architectural debt, but it does not execute your code. Because it doesn't perform runtime benchmarking, it identifies performance risks (like N+1 queries) based on code patterns rather than live execution data.

    The skill is built to be context-aware, meaning it doesn't just look at isolated files. It analyzes changed files in the context of your existing codebase patterns and commit history to ensure architectural consistency and prevent circular dependencies.

    You receive the complete skill configuration and systematic review framework ready for deployment in your preferred AI agent. This includes the logic for the five-pillar review process (Security, Performance, Correctness, Architecture, and Maintainability) and the structured reporting template.

    New in Security