afrexai-code-reviewerEnterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any language, any repo, no dependencies required.
Install via ClawdBot CLI:
clawdbot install 1kalin/afrexai-code-reviewerGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Calls external URL not in known-safe list
https://afrexai-cto.github.io/context-packs/AI Analysis
The skill definition itself contains no instructions for sending user data to external servers, credential harvesting, or overriding safety. The flagged signals are from a rule-based scan of the text, not active malicious code. The 'eval()' mention is within a security checklist as a negative example, and the external URL appears to be a documentation link for context packs, not an active data exfiltration endpoint.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 5, 2026
Automatically review pull requests in GitHub repositories for security vulnerabilities, performance issues, and code quality. This is ideal for development teams using CI/CD pipelines to enforce code standards before merging, reducing manual review effort and catching critical issues early.
Review staged changes or specific files in a local repository to identify errors and architectural smells before committing. This helps individual developers or small teams maintain code hygiene and prevent bugs from reaching version control, especially in fast-paced agile environments.
Analyze code files or diffs for security flaws like SQL injection, hardcoded secrets, and authentication bypasses in financial software. This scenario is critical for banks and fintech companies to comply with regulations and protect sensitive customer data from breaches.
Review entire codebases or large files to uncover performance bottlenecks, error handling gaps, and architectural issues in legacy systems. This supports enterprises migrating to newer technologies by identifying refactoring priorities and ensuring reliability during transitions.
Offer the code review engine as a cloud-based service with tiered pricing based on usage, such as number of reviews per month or repository size. This model targets small to medium businesses seeking scalable, low-maintenance solutions without infrastructure overhead.
Sell on-premise or private cloud licenses to large organizations requiring customization, data privacy, and integration with existing tools like Jira or Slack. This includes support contracts and training for seamless adoption in regulated industries.
Provide a free version for individual developers or small teams with basic reviews, while charging for advanced features like detailed SPEAR scoring, priority support, and team collaboration tools. This drives user acquisition and upsells to paid tiers.
💬 Integration Tip
Integrate via GitHub Actions or CLI tools to automate reviews in CI/CD pipelines, ensuring consistent checks across all code changes without manual intervention.
Scored May 16, 2026
Write, run, and manage unit, integration, and E2E tests across TypeScript, Python, and Swift using recommended frameworks.
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Provides AI agents with authoritative knowledge on modern software development, emerging technologies, AI, AI systems, and applied engineering practices.