claude-commands

/4layer - Four-Layer Minimal Repro Testing Protocol

Command system documentation & header requirements

Enhanced Command Aliases

Enhanced /learn Command - Implementation Summary

Enhanced command wrappers provide memory pattern integration for improved execution quality and consistency.

Claude Commands Directory

Claude Commands - Command Library Overview

Claude sometimes responds "I don't recognize command X" without verifying if the command actually exists in `.claude/commands/`.

The orchestrator MUST generate responses.json in this exact format:

**Execute these steps immediately. Use TodoWrite to track multi-phase workflows.**

/adde2e - Add or Update End2End Tests for New Features

/arch Command (Alias)

Architecture Review Command

/auto Command

Automation Audit Skill - Analyze PR automation job runs

Automation Package Publishing Command - Publish both orchestration and automation packages to PyPI

Run all crontab automation jobs and verify they worked

/automation - GitHub PR Automation System Integration

/batchcopilot Command - Batch PR Processing

Branch Cleanup Command

/benchg-ts - TypeScript Migration Benchmark: Genesis vs Ralph

/benchg - Genesis vs Ralph Orchestrator Benchmark

Unified browser automation - intelligently uses Playwright or Superpowers Chrome

Generate large amounts of code using Cerebras (alias for /cerebras)

Generate large amounts of code using Cerebras (alias for /cerebras)

Generate large amounts of code using Cerebras

Context Checkpoint Command

Claude-MD-Analyze Command - Comprehensive Directory Analysis for CLAUDE.md Deployment

Claude-MD-Validate Command - Comprehensive CLAUDE.md Quality Validation Framework

Clone PR, add TDD tests, and push to correct remote branch

Combinations Command

Combo Help Command

/commentcheck Command

/commentfetch Command

Comment Reply Command (Alias)

/commentreply Command

Context Estimation Command (Alias)

/cons Command (Alias)

description: /consensus Command - Multi-Agent Consensus Review

Context Usage Estimation Command

/copilot-expanded - Complete Self-Contained PR Analysis & Enhancement

/copilot-lite - Streamlined PR Processing

/copilot - Orchestrated PR Comment Processing

/copilotl - Copilot Lite Alias

GitHub Copilot Super Command

Coverage Command

Debug Protocol Command

Debug Command

debugp - Alias for Debug Protocol

/deploy

/design - Product & Engineering Design Documentation

e

Execute Command - Plan-Approve-Execute Composition

/experiment - Triple-Blind AI Testing Protocol

/exportcommands - Export Claude Commands to Reference Repository

Fake Code Detection Command

Fake3 Command - Branch-Focused Iterative Fake Code Detection and Fixing

Fake Code Detection Command - /fakel (Light)

/fixpr Command - Intelligent PR Fix Analysis

---

/ghfixtests

/goal - Goal Definition and Validation Command

Alias for /gstatus command

Comprehensive PR status with GitHub MCP orchestration

Generate comprehensive, general-purpose test suites for any system component using systematic test design methodology

Guidelines Command - Centralized Mistake Prevention Consultation

/handoff Command

Header Command

/headless - Enhanced Planning + Headless Development

/history Command

Alias for /investigatedice - Investigate dice integrity warnings for a campaign

Alias for /innovate - Single smartest innovative addition to the current plan

/innovate - Single smartest innovative addition to the current plan

Integration Command

Investigate dice integrity warnings for a campaign. Queries GCP logs, Firestore story entries, and game_state to diagnose dice fabrication issues.

/learn Command

List Commands Command

/localexportcommands - Export Project Claude Configuration Locally

/localserver

/memory Command - Memory MCP Interaction with Query Optimization

Milestones Command

Moltbook Social Network Integration

/newbranch or /nb - Create new branch from latest main

/newbranch or /nb - Create new branch from latest main

Optimize Command

/orch - Alias for /orchestrate

Orchestrate Command

1. **Register MCP Mail Agents**

The Pair Protocol uses MCP mail for asynchronous agent-to-agent coordination while maintaining human-in-the-loop oversight at critical decision points.

Launch dual-agent pair programming with coder + verifier

Legacy Python pair executor (pair_execute.py)

Parallel Tasks vs Subagents Reference Guide

Perp Command - Comprehensive Multi-Search

Plan-Execute Command - Execute with Approval

Playwright browser automation testing for Your Project

PR Command - Complete Development Lifecycle

/pres

/presentation

Principal Engineer Command

Principal Product Manager Command

/processmsgs - Intelligent Agent Message Processing with MCP Agent Mail

/puppeteer Command

Push Command

Push Lite Command (pushl alias)

Push Lite Command - Enhanced Reliability with LLM Intelligence

Legacy alias for Cerebras code generation (redirects to /cerebras)

Roadmap Command (Alias)

Execute Ralph orchestration system for autonomous task execution

Execute Ralph orchestration system for autonomous task execution

Red-Green Debug & Fix Command

/replicate

View Current Requirement

End Requirements Gathering

List All Requirements

Requirements Gathering Reminder

Start Requirements Gathering

Check Requirements Status

Research Command - Academic and Technical Research

Enhanced Code Review Command

Deep Review Alias

/reviewdeep Command

Enhanced Code Review Alias

Review Status Command - Check PR CI and Review Comments

/reviewsuper Command - Critical Architecture Reviewer

Red-Code-Green Debug Command (Alias)

Roadmap Command

/runlocal

Save evidence to /tmp structure

Repository Scaffolding Command

Scratchpad Command

Get multi-model second opinion on design, code review, or bugs

Get multi-model second opinion (alias for /second_opinion)

Alias for /simulate - Predict next user prompt

Async A/B simulation - runs predictions via claude -p subprocess

Predict next user prompt using $USER simulation

/slide

Run MCP smoke tests against preview server or local instance

Clarify Command - Specification Clarification Protocol

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Execute the implementation planning workflow using the plan template to generate design artifacts.

Spec Command - GitHub Spec Kit Integration

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

Split PR Command

Show comprehensive PR status including recent files, CI, merge conflicts, and GitHub state

**Purpose**: Display branch and PR status information using universal composition

/suba Alias - Dual Consultant Validation Sweep

/subagentvalidate Command - Dual Consultant Validation Sweep

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores requirements and design before implementation.

Execute plan in batches with review checkpoints

Create detailed implementation plan with bite-sized tasks

/sync - Synchronize Local Branch with PR

Matrix-Enhanced Test-Driven Development Command

Create a minimax-only agent team with haiku for work

Enhanced Test Command

/teste - End2End Tests (Mock Mode)

/tester - End2End Tests (Real Mode)

/testerc - End2End Tests (Real Mode + Capture)

HTTP Tests (Mock) Command

HTTP Tests (FULL) Command

Integration Test Command

/testllm - LLM-Driven Test Execution Command

/testmcp - MCP Test Suite Execution Command

Test Server Command

Browser Tests (Mock) Command

Intelligent Regression Testing with Playwright MCP

Think Command

Think Ultra Command (Alias)

/timeout Command - Performance Optimizer

Query Firebase for the longest (most entries) campaigns within a date range.

Total Failure Protocol

/usage Command

Reference documentation for understanding and using the custom agent system

Design, test, and optimize AI prompts for NPCs, world generation, quest creation, and narrative elements. Use for any Gemini API prompt engineering.

Specialized agent for large-scale code generation using Cerebras infrastructure. Expert in creating complete implementations, complex algorithms, and multi-file project structures with high quality and performance.

Use this agent when the user explicitly requests Cerebras-assisted code generation, rapid scaffolding, or wants to leverage the `/cerebras` slash command for large or complex implementation tasks. The agent orchestrates Cerebras Model Studio via the official slash-command workflow for ultra-fast code production, architectural drafting, and automated documentation.

Claude CLI-powered pair programming coder. Delegates implementation to Claude CLI (claude --dangerously-skip-permissions) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["claude"]

Claude CLI-powered pair programming verifier. Delegates verification to Claude CLI (claude --dangerously-skip-permissions) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["claude"]

Specialist consultant for consolidating duplicate logic, reusing existing modules, and reducing codebase fragmentation. Defaults to Claude Code CLI, with fallbacks to Codex CLI and Cursor CLI if unavailable.

Specialized AI agent for comprehensive code analysis, security review, and quality assessment. Expert in multi-language code review with focus on bugs, security vulnerabilities, performance issues, and best practices.

Use this agent when the user asks to consult with Codex for code analysis, explanation, or insights. This agent is particularly useful when you need deep code understanding, architectural analysis, or when the user explicitly mentions wanting to 'consult with codex' or 'ask codex about' specific files or code patterns.

Codex CLI-powered pair programming coder. Delegates implementation to Codex CLI (codex exec --yolo) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["codex"]

Codex CLI-powered pair programming verifier. Delegates verification to Codex CLI (codex exec --yolo --skip-git-repo-check) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["codex"]

Specialized PR issue resolution agent focusing exclusively on implementing code fixes for GitHub PR blockers. Expert in file justification protocol, security fixes, runtime errors, test failures, and merge conflicts with actual code implementation.

Independent verification of /copilot run quality. Audits fix accuracy, scope discipline, tracking honesty, and KPI compliance without execution context contamination.

Use this agent when you need a Fresh Data Analysis Specialist who can tap into real-time context, surface emerging trends, and translate the latest signals into actionable guidance. The agent mirrors Cursor's fast-moving perspective by grounding every consultation in the freshest available data.

Cursor CLI-powered pair programming coder. Delegates implementation to Cursor Agent CLI (cursor-agent -f) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["cursor"]

Cursor CLI-powered pair programming verifier. Delegates verification to Cursor Agent CLI (cursor-agent -f) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["cursor"]

Specialized agent for comprehensive technical documentation generation. Expert in creating API docs, user guides, architectural documentation, and code documentation with professional quality and completeness.

Manage Firebase Firestore operations, authentication, security rules, and real-time data synchronization. Use for any database or auth tasks.

Develop and refine D&D 5e game mechanics, combat systems, character progression, and rule implementations. Use PROACTIVELY for any game logic changes.

Use this agent when the user explicitly asks to consult Gemini, seek external AI guidance, or needs a second opinion on technical decisions.

Gemini CLI-powered pair programming coder. Delegates implementation to Gemini CLI (gemini -m ${GEMINI_MODEL:-gemini-3-flash-preview} --yolo) for independent code generation. Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["gemini"]

Gemini CLI-powered pair programming verifier. Delegates verification to Gemini CLI (gemini -m ${GEMINI_MODEL:-gemini-3-flash-preview} --yolo) for independent code review and test validation. Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["gemini"]

Independent goal processing agent for /converge context optimization. Separates goal definition from main workflow to reduce context consumption.

Use this agent when you need a contrarian, unconventional analysis perspective that challenges assumptions and provides direct, practical insights. This agent simulates Grok-style analysis using available AI consultation tools.

Generic agent for medium and long-running tasks (>5 minutes). Executes independently, writes detailed results to files, and provides concise summaries to minimize context usage.

MiniMax-powered pair programming coder. Delegates implementation to Claude CLI with MiniMax API backend (ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic). Works with any pair-verifier teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["minimax"]

MiniMax-powered pair programming verifier. Delegates verification to Claude CLI with MiniMax API backend (ANTHROPIC_BASE_URL=https://api.minimax.io/anthropic). Works with any pair-coder teammate. Reference: orchestration/task_dispatcher.py CLI_PROFILES["minimax"]

Pair programming coder agent for implementation tasks within a Claude Teams session. Works with a pair-verifier teammate: implements code using TDD methodology, then signals completion for verification. Use when orchestrating dual-agent pair programming via Claude Teams (as alternative to pair_execute.py tmux-based orchestration).

Pair programming verifier agent for code review and test validation within a Claude Teams session. Works with a pair-coder teammate: waits for implementation completion signal, then verifies code quality, test coverage, and correctness.

Specialized agent for comprehensive performance analysis and optimization. Expert in algorithmic complexity, database optimization, caching strategies, and system-level performance tuning across all major platforms.

Methodical test specification execution with evidence collection. Expert in browser automation, real authentication testing, and structured evidence packages.

Independent validation of test execution results against original specifications. Critical auditor for evidence analysis and requirement verification.

Generate comprehensive, systematic test suites for any system component using a structured test design methodology. Creates tests that catch real bugs through state lifecycle, integration, and consistency testing.

Use this skill when writing code, implementing features, refactoring, planning architecture, designing systems, reviewing code, or debugging. This skill transforms junior-level code into senior-engineer quality software through SOLID principles, TDD, clean code practices, and professional software design.