pr Reviewer

    3

    Automated, high-precision code reviews that detect bugs, security flaws, and performance bottlenecks in your PRs.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    2 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    pr-reviewer

    Example session with this skill installed

    Review my recent changes on this branch for security vulnerabilities and bugs before I merge to main.

    • Read your context and instructions
    • Compiled the pr-reviewer

    HIGH

    [auth.ts:42] Possible SQL Injection
    Category: Security
    Issue: User ID is interpolated directly into the query string.

    Suggestion

    const user = await db.execute('SELECT * FROM users WHERE id = ?', [userId]);
    

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

    About this skill

    What it does

    This skill provides an automated, deep-dive code review of your current working branch compared to your base branch (main/master). It systematically analyzes your diff across six critical dimensions: correctness, security, performance, code quality, test coverage, and documentation.

    Why use this skill

    Manual code reviews are time-consuming and prone to human oversight. While standard LLM prompting might catch surface-level issues, this skill follows a rigorous multi-step engineering process: it identifies the merge-base, reads full file context (not just the diff), analyzes commit history quality, and categorizes findings by technical severity. It replaces vague feedback with structured, actionable PR_REVIEW.md files that include specific code suggestions.

    Supported tools

    • Git Integration: Works with any local repository to determine branch diffs and history.
    • Multi-language Support: Analyzes patterns in JavaScript, Python, Java, C++, and more.
    • Contextual Read: Uses local file access to understand the broader codebase surrounding your changes.
    • Automated Reporting: Generates a persistent markdown report in your root directory.

    The Output

    You receive a professional-grade PR_REVIEW.md file categorized by severity (CRITICAL to INFO). It identifies specific line numbers, explains the underlying risk (e.g., N+1 queries, XSS vulnerabilities, or race conditions), and provides logic-ready code blocks for quick fixes.

    • Cannot execute code to verify bugs.
    • Limited context window for massive (1000+ line) diffs.
    • Local repository access required via Bash/Read tools.

    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

    2 uses

    Times used to date

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 7 months ago

    Permissions

    Terminal / Shell
    Listed7 months ago

    What's inside

    Frequently Asked Questions

    Unlike basic LLM prompts that only look at the diff, this skill identifies your merge-base and reads the full surrounding file context. This allows it to detect complex logic errors and architectural inconsistencies that surface-level reviews miss.

    The skill is designed for compatibility with leading developer-focused AI agents that have local file system and Git access. It facilitates the manual review process by automating the heavy lifting of bug detection and documentation.

    No, this skill is language-agnostic. It is optimized to analyze patterns across many popular languages, including Python, JavaScript/TypeScript, Java, C++, and Go, by focusing on cross-language principles of security and performance.

    You receive the fully functional skill ready to be integrated into your AI agent's toolkit. This includes the logic for branch comparison, context-aware file reading, and the structured markdown reporting engine.

    Simply grant the AI agent access to your local repository. The skill automatically handles finding the current branch, identifying the difference from the main branch, and generating the report file in your root directory.

    New in Code Quality & Review