amux

Run the full code review pipeline on your changes. Creates an agent team of parallel reviewers, aggregates findings, and fixes critical issues.

Use before implementing non-trivial features (researches approaches with Context7, Serper, GitHub MCPs)

Deep research using agent teams, web search, and scraping. Decomposes topics into 8 questions, researches in parallel via teammates, evaluates confidence, iterates until sufficient, and synthesizes with source attribution.

Check structural integrity, pattern consistency, and coupling in code changes.

Review completed work against your plan and coding standards.

Check whether documentation is up-to-date with code changes.

Find bugs, logic errors, security issues, and error handling gaps in code changes.

Check implementation completeness and adherence against the selected plan.

Check framework-specific best practices and deprecated API usage in code changes.

Find coverage gaps, test antipatterns, and missing test cases in code changes.

Check WCAG accessibility, keyboard navigation, and UX patterns in UI changes.

Reviews structural integrity, pattern consistency, and coupling in code changes. Dispatched by the code-review-pipeline skill when new/moved files or structural changes are detected — do not invoke directly.

Reviews completed work against the original plan and coding standards. Invoked standalone via /review-code after completing a major project step. Not part of the code-review-pipeline dispatch — this is a plan-alignment reviewer.

Reviews whether documentation is up-to-date with code changes. Checks READMEs, architecture docs, API docs, changelogs, configuration docs, and inline docstrings for staleness. Dispatched by the code-review-pipeline skill — do not invoke directly.

Reviews code for bugs, logic errors, error handling gaps, and security vulnerabilities. Returns confidence-scored findings. Dispatched by the code-review-pipeline skill — do not invoke directly.

Reviews implementation against the selected plan for completeness and adherence. Checks that all planned items are implemented, no unplanned scope was added, and deviations are justified. Dispatched by the code-review-pipeline skill when plan context is provided — do not invoke directly.

Reviews library-specific best practices for frameworks like Svelte, CodeMirror, React, etc. Has web access to check current docs. Dispatched by the code-review-pipeline skill — do not invoke directly.

Reviews test quality, identifies coverage gaps, and flags test antipatterns. Returns list of missing tests. Dispatched by the code-review-pipeline skill — do not invoke directly.

Reviews UI components for WCAG accessibility and UX usability. Checks keyboard navigation, ARIA, interaction patterns, loading/error states. Dispatched by the code-review-pipeline skill — do not invoke directly.

Creates an agent team of parallel dual-engine code reviewers on your git diff, aggregates findings by severity, and fixes critical/high issues. Each reviewer cross-validates with Codex via MCP. Run after implementing a feature or before committing.

Use before implementing any non-trivial feature - validates approaches against real sources using Context7, Serper, GitHub MCPs, and optionally btca for source-level codebase research. Evaluates with dual engines before committing to an implementation

Use when user explicitly requests deep research or comprehensive analysis requiring 20+ authoritative sources. Creates an agent team for parallel research with source gate enforcement, confidence tracking, and structured synthesis. NOT for simple questions answerable with a single search.

3 hooks across 3 events