xpowers

Execute a refactor safely with tests staying green

Review implementation was faithfully executed

Configure which AI model each XPowers agent uses

Create detailed implementation plan with bite-sized tasks

Audit test quality - identify tautological tests, coverage gaming, missing corner cases

<claude-mem-context>

Simplification reviewer - detects over-engineering, unnecessary complexity, premature abstractions. Returns PASS or ISSUES_FOUND.

Testing reviewer - evaluates test coverage, test quality, and testing gaps. Returns PASS or ISSUES_FOUND.

Machine-facing reviewer for automated pipelines. Returns structured verdicts (PASS/NEEDS_FIX/APPROVED/GAPS_FOUND) with actionable fix instructions for orchestrators to act on. Can research unclear patterns via web search. Use during continuous execution (ralph, execute-ralph). Contrast with code-reviewer (human-facing, narrative explanations) and review-implementation (spec-focused, requirements checklist).

Human-facing code reviewer for major milestones. Provides detailed explanations, suggestions, and code samples (not just verdicts). Use after completing a logical chunk of work against the original plan. Contrast with autonomous-reviewer (machine-facing, verdict-only) and review-implementation (spec-focused, requirements checklist). Examples: <example>Context: The user is creating a code-review agent that should be called after a logical chunk of code is written. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Great work! Now let me use the xpowers:code-reviewer agent to review the implementation against our plan and coding standards" <commentary>Since a major project step has been completed, use the xpowers:code-reviewer agent to validate the work against the plan and identify any issues.</commentary></example> <example>Context: User has completed a significant feature implementation. user: "The API endpoints for the task management system are now complete - that covers step 2 from our architecture document" assistant: "Excellent! Let me have the xpowers:code-reviewer agent examine this implementation to ensure it aligns with our plan and follows best practices" <commentary>A numbered step from the planning document has been completed, so the xpowers:code-reviewer agent should review the work.</commentary></example>

Use to execute bd tasks iteratively - executes one task, reviews learnings, creates/refines next task, then STOPS for user review before continuing

Use when implementation complete and tests pass - closes bd epic, presents integration options (merge/PR/keep/discard), executes choice

Use when encountering a bug - complete workflow from discovery through debugging, bd issue, test-driven fix, verification, and closure

Use for advanced bd operations - splitting tasks mid-flight, merging duplicates, changing dependencies, archiving epics, querying metrics, cross-epic dependencies

Search long-term memory from previous sessions using memsearch

16 hooks across 7 events