More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AI Code Reviewer

    1

    Evidence-first AI code review that discovers, verifies, prioritizes, and explains meaningful code problems.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    6 usesSecurity scanned
    AI Code Reviewer

    AI Code Reviewer

    Example session with this skill installed

    Review the latest changes in auth_service.py for security vulnerabilities and logical errors. Focus on the token validation logic.

    • Read your context and instructions
    • Compiled the ai code reviewer

    [STANDARD REVIEW] **Risk:** HIGH **Findings:** 1 High, 1 Medium **Recommendation:** CHANGES RECOMMENDED **ID:** SEC-01 **Category:** Security **Severity:** HIGH **Confidence:** HIGH **Location:** auth_service.py:42 **Problem:** Missing expiration check on JWT. **Impact:** Tokens remain valid indefinitely. **Rec:** Add 'exp' claim validation.

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

    About this skill

    AI Code Reviewer is an evidence-first, read-only code review Skill designed to help developers discover meaningful problems in code, pull requests, and AI-generated implementations. It analyzes correctness, security, performance, architecture, testing, maintainability, specification compliance, dependency risks, and regression risk. The Skill uses a structured TRACE → VERIFY → RANK workflow to investigate potential issues, evaluate available evidence, suppress weak or speculative findings, deduplicate related problems, and prioritize actionable risks. Each substantive finding includes severity, confidence, evidence, location, impact, root cause when established, recommendation, and suggested testing where useful. The Skill is designed with a least-privilege approach: it does not inherently require network access, secrets, environment variables, external services, or source-code modification. Repository content is treated as untrusted data to resist prompt injection, and the Skill never claims that tests, scanners, compilers, or other tools were executed unless they actually were and were explicitly authorized.

    Read-only static analysis only. Cannot execute tests, benchmarks, or scripts unless the host agent provides explicit authorization and environment. Does not flag subjective style issues.

    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

    6 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 3 months ago

    Permissions

    Read Files

    Read-only by default. This Skill does not require network access, environment variables, secrets, external services, or file-write permissions. It does not modify, delete, commit, push, merge, or deploy project files. Tool execution is only performed when explicitly authorized and actually available; otherwise, reviews remain static and clearly disclose verification limitations. Repository content is treated as untrusted data to reduce prompt-injection risk. Findings are evidence-based and sensitive values are minimized or redacted where possible.

    Listed3 months ago
    Updated24 days ago

    What's inside

    Frequently Asked Questions

    AI Code Reviewer uses a structured TRACE → VERIFY → RANK workflow to filter out noise, ensuring you only receive prioritized, evidence-based feedback on security, performance, and correctness rather than generic stylistic suggestions.

    Yes, the skill is built with a least-privilege, read-only architecture that treats repository content as untrusted data to resist prompt injection and does not require access to your environment variables or secrets.

    This skill is designed for any AI agent capable of file-system or repository access and performs best with models optimized for technical reasoning and long-context windows.

    The skill is language-agnostic and evaluates code based on universal engineering principles like architectural integrity, dependency risk, and specification compliance across various programming languages.

    Each finding includes a detailed breakdown of the severity, confidence level, specific location, impact analysis, and a clear recommendation for remediation.

    No, the skill operates in a read-only capacity to provide analysis and recommendations; it will never modify your source code or commit changes to your repository.

    New in Code Quality & Review