Quality

Codex Agent Collaboration uses Codex CLI for second-opinion code reviews, cross-verification, debugging help, and alternative implementation ideas. Use it when you want another coding agent to inspect changes before you apply them.

Local Binary Reverse performs read-only static analysis of user-authorized local binaries and packaged apps. Use it to inspect strings, symbols, dependencies, file types, and version differences without executing the target.

Test-Driven Development enforces writing a failing test before implementation, then using the red-green-refactor cycle to build and change code safely. Use it for new features, bug fixes, and refactors.

Audit runs technical quality checks for accessibility, performance, theming, responsive behavior, and anti-patterns. Use it when you need a scored implementation review with P0-P3 findings and an action plan.

Polish performs a final quality pass to fix alignment, spacing, consistency, and other small issues before shipping. Use it when a UI is functionally complete but still feels off or needs pre-launch review.

Cross-Agent Review asks a different AI backend to review your code, PR, or plan through the repowire mesh. Use it when you want an independent second opinion before merging or committing.

Review Cycle coordinates PR review, CI triage, and requested-changes loops for code that needs independent verification. It helps summarize findings, verify fixes, and decide merge readiness.

Code Review thoroughly checks code or recent changes for bugs, security issues, performance problems, and maintainability concerns. Use it when reviewing implementations or auditing code quality.

Verify checks that a code change works as expected by running the app. Use it when you need to confirm behavior after edits or catch regressions quickly.

Cyber Neo performs a read-only security audit of a local project. It scans for vulnerabilities, secrets, auth flaws, crypto issues, misconfigurations, and supply-chain risks, then produces a prioritized remediation report.

MCP Smoke Test runs an end-to-end check of a local Stata-MCP server. Use it to verify registration, test data and Stata commands, and confirm security boundaries and log access.

Architectural Analysis examines a named module, directory, or feature and produces a structured architecture report. Use it when you need design, behavior, risk, and boundary guidance without changing code.