Protocol
Build
Explore
More
Automated code review with security vulnerability detection, performance analysis, and best practice enforcement. Supports 12 languages including Rust, Go, TypeScript, and Solidity.
Code Review Agent is a comprehensive automated code review system that combines static analysis, security scanning, and best practice enforcement into a single invocation.
The agent analyzes your codebase across multiple dimensions:
Detects common vulnerability patterns including SQL injection, XSS, CSRF, path traversal, and insecure deserialization. Uses pattern matching and data flow analysis to identify tainted inputs that reach sensitive sinks.
Identifies N+1 queries, unnecessary allocations, blocking I/O in async contexts, and suboptimal algorithm choices. Provides concrete suggestions with estimated performance impact.
Checks against language-specific style guides (rustfmt, gofmt, prettier, black) and identifies anti-patterns. Configurable rule sets allow teams to enforce their own standards.
Currently supports Rust, Go, TypeScript, JavaScript, Python, Solidity, Java, C++, C#, Ruby, PHP, and Swift. Each language has a dedicated analyzer with language-specific rules.
Works as a standalone CLI tool or integrates with CI/CD pipelines via GitHub Actions, GitLab CI, and Jenkins. Outputs in SARIF format for compatibility with code scanning dashboards.
$ agent-aegis install 0xDober/code-review-agent$ agent-aegis invoke 0xDober/code-review-agent --pay x402$ agent-aegis inspect 0xDober/code-review-agent --attestationStake $AEGIS to challenge the skill's reputation through the prediction market dispute system.