prp-core

Research codebase questions using parallel agents - documents what exists, not what should change

**Target**: $ARGUMENTS

Deep root cause analysis - finds the actual cause, not just symptoms

Execute an implementation plan with rigorous validation loops

Implement a fix from investigation artifact - code changes, PR, and self-review

Investigate a GitHub issue or problem - analyze codebase, create plan, post to GitHub

Create comprehensive feature implementation plan with codebase analysis and research

**Base branch override**: $ARGUMENTS

**Input**: $ARGUMENTS

Cancel active PRP Ralph loop

Start autonomous Ralph loop to execute PRP plan until all validations pass

Design a dynamic research team and plan using agent teams -- analyzes question, composes team, creates executable research plan

Comprehensive PR review using specialized agents - comments, tests, errors, types, code quality, docs, and simplification

Comprehensive PR code review - checks diff, patterns, runs validation, comments on PR

Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.

Identifies code simplification opportunities for clarity and maintainability while preserving exact functionality. Use after writing or modifying code. Focuses on recently changed code unless told otherwise. Reports findings with before/after suggestions. Advisory only - does not modify files or commit.

Use proactively to understand HOW code works. Analyzes implementation details, traces data flow, and documents technical workings with precise file:line references. The more specific your request, the better the analysis.

Comprehensive codebase exploration - finds WHERE code lives AND shows HOW it's implemented. Use when you need to locate files, understand directory structure, AND extract actual code patterns. Combines file finding with pattern extraction in one pass.

Analyzes code comments for accuracy, completeness, and long-term value. Use after generating documentation, before PRs with comment changes, or when auditing for comment rot. Verifies comments match actual code behavior. Advisory only - identifies issues, does not modify code.

Reviews documentation affected by code changes. Identifies stale docs, removed feature references, and missing entries for new user-facing features. Reports findings with specific fixes. Advisory only - does not modify files or commit.

Analyzes PR test coverage for quality and completeness. Focuses on behavioral coverage, not line metrics. Identifies critical gaps, evaluates test quality, and rates recommendations by criticality (1-10). Use after PR creation or before marking ready.

Hunts for silent failures, inadequate error handling, and inappropriate fallbacks in code changes. Zero tolerance for swallowed errors. Use after implementing error handling, catch blocks, or fallback logic. Ensures errors are logged, surfaced to users, and actionable.

Analyzes type design for encapsulation, invariant expression, and enforcement quality. Use when introducing new types, reviewing PRs with type changes, or refactoring existing types. Provides qualitative feedback and ratings (1-10) on four dimensions. Pragmatic focus - suggests improvements that won't overcomplicate.

Need information beyond your training data? Modern docs, recent APIs, or current best practices? Use web-researcher to find answers from the web. Searches strategically, fetches relevant content, and synthesizes findings with proper citations. Re-run with refined prompts if initial results need more depth.

Autonomous iteration execution guide for PRP Ralph loops. Use when .claude/prp-ralph.state.md exists, when continuing Ralph iterations, or when executing plans autonomously until all validations pass. Provides iteration behavior, completion protocol, validation requirements, and progress logging.

2 hooks across 1 event