Bradley Windybank

Conduct deep code reviews using 23 specialized agents to ensure thorough analysis of PRs, MRs, or branch comparisons.

Trace data from input to storage, validating transformations and checking for data loss or PII leaks.

Analyze test coverage to identify critical gaps and assess test quality.

Trace state mutations from code changes to identify unintended side effects.

Analyze dependency and import graphs to identify issues before they reach production.

Expertly analyze type design to ensure strong invariants and encapsulation.

Detects out-of-scope code changes in PRs/MRs to ensure relevance to stated purposes.

Fetch and analyze review comments from previous PRs/MRs to surface relevant feedback.

Ensure architectural integrity by checking for layer violations and inappropriate coupling.

Analyze code performance with platform-specific insights and best practices.

Detect parallelism bugs like race conditions and deadlocks that other agents overlook.

Use this agent to merge and deduplicate findings from all 23 specialist agents into a unified report with normalized severity, conflict resolution, and executive summary. <example> Context: 23 specialist agents have completed their reviews. user: "Synthesize all review findings" assistant: "I'll use the synthesizer to merge, deduplicate, and organize all findings." <commentary> 23 agents may flag the same issue from different angles - the synthesizer resolves this. </commentary> </example>

Ensure code comments are accurate and informative to prevent misleading documentation.

Verify code changes against explicit project guidelines to ensure compliance.

Adversarially challenge findings in synthesized reports to ensure accuracy and reliability.

Review API contracts for breaking changes and schema validation.

Ensure code changes align with existing project style patterns for consistency.

Analyze git blame and commit history to uncover code churn and historical patterns.

Ensure code changes comply with inline comment directives to maintain code integrity.

Detect memory leaks, retain cycles, and resource exhaustion in code changes.

Ensure code is properly instrumented for production debugging with logging and observability checks.

Identify silent failures and inadequate error handling in code reviews.

Conduct deep code reviews using 23 specialized agents for thorough analysis of PRs, MRs, or branch comparisons.

Detect deep bugs by tracing full call graphs of changed functions.

Use this agent for comprehensive security review covering OWASP Top 10 and beyond. Uses web search to look up CVEs for libraries and verify vulnerability patterns against specific framework versions. <example> Context: A PR adds user input handling to an API endpoint. user: "Review this for security" assistant: "I'll use the security-auditor to check for injection, auth, and input validation issues." <commentary> New user input handling requires OWASP-level security analysis. </commentary> </example>

Identify and reduce unnecessary complexity in code with this agent.

Identify deployment risks related to migrations and configuration changes.