core-claude-plugin

Create comprehensive PRD through strategic analysis with optional innovation exploration

Audit configurations and standards compliance with complexity-based routing and interactive discrepancy resolution

Build features with TDD workflow using sequential-thinking and full agent chain

Browser debugging and E2E testing workflow using Chrome DevTools MCP

Quick fixes and small tasks using MetaSaver agents without full workflow overhead

(ARCHIVED) Original intelligent MetaSaver router with complexity-based routing

Answer questions using MetaSaver agents without full workflow overhead

Restore MetaSaver workflow context after crash or interruption

Docker Compose (docker-compose.yml) domain expert - validates services, environment variables, volumes, and health checks

Docker ignore (.dockerignore) domain expert - handles build and audit modes

pnpm workspace configuration expert - validates workspace patterns and alphabetical ordering

PostCSS configuration expert - validates plugins, plugin order, and CSS processing chain

Tailwind CSS configuration expert - validates content paths, theme extension, plugins, and CSS files

Turbo.json configuration domain expert - handles build and audit modes

Vite configuration expert - validates plugins, path aliases, build settings, and server configuration

Vitest configuration domain expert - handles build and audit modes

EditorConfig domain expert for monorepo root configuration. Use when creating or auditing .editorconfig files.

ESLint flat config expert for eslint.config.js files. Use when creating or auditing ESLint configurations.

Prettier configuration expert for package.json "prettier" field. Use when creating or auditing Prettier configs in MetaSaver projects.

Commit message validation expert for commitlint.config.js and Copilot instructions. Use when creating or auditing conventional commit standards.

Git attributes (.gitattributes) expert for line ending normalization and cross-platform consistency. Use when creating or auditing file handling rules.

GitHub Actions workflow domain expert - handles build and audit modes

Git ignore (.gitignore) expert for comprehensive ignore pattern management. Use when creating or auditing ignore patterns for security and cleanliness.

Husky git hooks domain expert - handles build and audit modes

CLAUDE.md configuration domain expert - enforces 8-standard compliance with multi-mono awareness

Environment variable specialist - enforces SINGLE OWNERSHIP rule and 5-standard distributed .env.example pattern

Monorepo root structure expert - detects unexpected files and validates directory organization

Nodemon configuration specialist - enforces 5 standards for dev server auto-restart

NPM registry template specialist - enforces 4 standards for .npmrc.template configuration

Node version specialist - enforces 3 standards for .nvmrc LTS version specification

README.md documentation domain expert - handles build and audit modes for repository-specific templates

Repomix configuration (.repomix.config.json) domain expert - achieves 70% token reduction through XML compression and proper include patterns

Root package.json domain expert - orchestrates monorepo scripts, dependencies, and workspace configuration

Scripts directory (/scripts) domain expert - creates and audits utility scripts with cross-platform support

TypeScript configuration domain expert - creates and audits tsconfig.json variants with monorepo support

VS Code settings domain expert - creates and audits .vscode/settings.json with standard workspace configuration

Contracts package domain expert - handles Zod validation schemas, TypeScript type re-exports, barrel patterns, and API request/response contracts

Data service REST API domain expert - handles feature-based service architecture, CRUD operations, validation, authentication, and database integration

Prisma database package domain expert - handles package scaffolding, schema design, migrations, seeding, and type re-exports

React application domain expert - handles app scaffolding, feature-based architecture, routing, and portal/admin app patterns

Meta-level agent specialist for creating, refactoring, and validating .claude/agents/ and .claude/skills/ files. Use for ANY work on agent system documentation, NOT for user application code.

Maps audit targets to appropriate config or domain agents based on files

Lightweight architecture annotator - adds brief inline "Architecture:" subsections to PRD user stories with API endpoints, key files, database models, and component names. Output 50-100 lines max in ~30 seconds.

Backend development specialist with Express, Prisma, and MetaSaver API patterns

Story decomposition specialist. Extracts epics and user stories from annotated PRDs with acceptance criteria, dependencies, and agent assignments.

Codebase exploration specialist using Serena, repomix, and MetaSaver MCP ecosystem for token-efficient research

Technical validation specialist that scales quality checks based on change size and verifies code builds, compiles, and passes automated checks

Implementation specialist enforcing MetaSaver coding standards and SOLID principles

Creates minimal workflow-based slash commands that orchestrate skills - pure orchestration, no inline logic.

Strategic PRD creator focused on high-level requirements, system scope, and business objectives. Uses sequential-thinking for complex analysis and Serena for codebase exploration.

Innovation SME that analyzes PRDs and proposes improvements based on industry standards, best practices, and modern implementations. Returns structured data for iterative user review.

Performance optimization specialist using data-driven profiling and metrics-based improvements

Resource scheduler that transforms plans into Gantt charts and consolidates execution results

Quality gatekeeper for code and documents - validates PRDs, execution plans, user stories before HITL, and enforces MetaSaver code standards

Systematic debugging specialist using evidence-based investigation and hypothesis validation

Text analysis specialist for repository and file scope detection. Analyzes user prompts to identify target repos, reference repos, and audit files.

Security assessment specialist with OWASP expertise and threat modeling

Skill creation specialist for trigger-optimized Claude Code skills. Use when creating, refactoring, or validating .claude/skills/ files, skill YAML frontmatter, or skill directory structure.

Jest testing specialist - writes unit/integration tests achieving ≥80% coverage with AAA patterns

Docker Compose configuration template and validation logic for MetaSaver monorepos. Includes 4 required standards (PostgreSQL service with project-prefixed env vars like RUGBYCRM_POSTGRES_USER or METASAVER_SILVER_POSTGRES_USER for multi-db, project-specific naming for containers and networks, volumes section, service health checks). Use when creating or auditing docker-compose.yml files.

pnpm workspace YAML configuration templates and validation logic for monorepo workspace patterns. Includes 5 required standards (architecture-specific patterns for consumer vs library repos, exact path matching, no missing directories, no extra patterns, alphabetical ordering). Critical distinction between consumer repos (specific paths like packages/contracts/*) and library repos (broad patterns like packages/*). Use when creating or auditing pnpm-workspace.yaml files.

PostCSS configuration template and validation logic for Tailwind CSS processing with Autoprefixer. Includes 4 required standards (required base plugins, critical plugin order with tailwindcss first and autoprefixer last, file naming as postcss.config.js, required dependencies). Use when creating or auditing postcss.config.js files to ensure correct CSS build pipeline.

Turbo.json configuration template and validation logic for Turborepo tasks. Use when creating or auditing turbo.json files to ensure correct task configuration, caching strategy, and the 7 required MetaSaver standards (schema, globalEnv, globalDependencies, required tasks by repo type, build requirements, persistent task cache, clean task cache).

Vite configuration templates and validation logic for React web apps. Includes 5 required standards (correct plugins for React, required path alias

Vitest configuration template and validation logic for test configuration. Standards differ by package type - use package-type specific configs (react-app, react-library, node-library, node-service, contracts, database). Use factory pattern for React packages that need vite.config.ts merging.

EditorConfig file validation and template for enforcing consistent coding styles across editors and IDEs in monorepos. Includes 4 required standards (root declaration, universal settings with UTF-8/LF/2-space defaults, language-specific sections for JS/TS/JSON/YAML/Markdown/Python/Shell/SQL/Docker/Prisma, root-only placement in monorepos). Use when creating or auditing .editorconfig files to ensure consistent code formatting.

ESLint flat config validation and templates for eslint.config.js files in MetaSaver monorepos. Includes 5 required standards (correct config type for projectType, simple re-export pattern from shared library, flat config filename eslint.config.js, shared config dependency, required npm scripts). Use when creating or auditing eslint.config.js files to ensure correct linting configuration.

Prettier configuration validation and templates for package.json "prettier" field in MetaSaver monorepos. Includes 4 required standards (prettier field in package.json with string reference only, no separate prettierrc files, prettier in devDependencies, required npm scripts format and format:check). Use when creating or auditing Prettier configs to ensure consistent code formatting via shared library.

Commitlint configuration and GitHub Copilot commit message instruction templates with validation logic for conventional commit enforcement. Includes 6 required standards (conventional format, relaxed subject rules for Copilot compatibility, optional scope, Husky integration, required dependencies, Copilot instruction consistency). Use when creating or auditing commitlint.config.js and .copilot-commit-message-instructions.md files.

Git attributes configuration for cross-platform line ending normalization and file handling. Includes 8 required pattern categories (global auto-detection, source code, shell scripts, Windows files, Docker files, binary files, lock files, generated files). Critical for Windows WSL compatibility. Use when creating or auditing .gitattributes files to prevent line ending issues and binary corruption.

Git ignore configuration patterns for MetaSaver monorepos. Includes 10 required pattern categories (dependencies, build outputs, environment files with security-critical .env and .npmrc exclusions, logs, testing, IDE, OS, database, cache, temporary files). Use when creating or auditing .gitignore files to prevent secret leakage and repository pollution.

Husky git hooks configuration with smart auto-detection for sensitive files, fail-fast execution, auto-fix workflows, and CI detection. Includes 5 required standards (smart .npmrc detection for multi-mono repos, set -e for fail-fast, pre-commit auto-fix with prettier:fix and lint:fix, pre-push validation with time tracking, clear emoji-enhanced output). Use when creating or auditing .husky/pre-commit and .husky/pre-push hooks.

Docker ignore configuration template and validation logic for optimizing Docker build contexts. Includes 5 required standards (build artifacts, development files, CI/CD and testing, logs and temporary files, root-only placement). Use when creating or auditing .dockerignore files to reduce build context size, improve performance, and ensure security.

Nodemon JSON configuration templates and validation logic for development server hot-reload. Includes 5 required standards (watch patterns, exec command, ignore patterns, development settings, required dependencies). Use when creating or auditing nodemon.json files to enable automatic server restart on file changes.

NPM registry configuration template (.npmrc.template) and validation logic for GitHub Packages authentication with pnpm hoisting settings. Includes 4 critical standards (GitHub Package Registry config with token placeholder, pnpm hoisting for monorepo compatibility, exact version management, security documentation). Use when creating or auditing .npmrc.template files to prevent token leakage.

README.md documentation templates and validation logic for MetaSaver monorepos. Includes repository type detection (library vs consumer), required sections (Title, Description, Installation, Usage, Scripts), and line count guidance (consumer 75-100 lines, library 150-200 lines). Use when creating or auditing README.md files at monorepo root.

Repomix AI-friendly codebase compression configuration (.repomix.config.json) template and validation logic. Achieves 70% token reduction through XML compression and repository-type-specific include patterns. Includes 5 critical standards (XML output format, include patterns by repo type, gitignore integration, exclude patterns, security checks). Use when creating or auditing .repomix.config.json files for optimal LLM context compression.

Root package.json configuration for MetaSaver monorepos. Use when creating or auditing root package.json files to ensure workspace configuration, required scripts (build, dev, lint, test, format, clean), turbo pipeline scripts, packageManager field, and only devDependencies at root (no dependencies except cross-platform binaries).

Utility scripts directory configuration (/scripts) for MetaSaver monorepos including setup automation, environment management, and cross-platform support. Includes 4 critical standards (setup scripts, cross-platform support, error handling, documentation). Use when creating or auditing /scripts directory with Node.js and shell utility scripts.

Tailwind CSS configuration template and validation logic for tailwind.config.js or tailwind.config.ts with src/index.css directives. Includes 5 required standards (required content paths for scanning, must extend default theme not replace, required plugins array, file naming convention for .js or .ts, required dependencies). Ensures proper PostCSS integration and Tailwind directive setup. Use when creating or auditing tailwind.config.js or tailwind.config.ts files for consistent Tailwind CSS setup.

TypeScript configuration (tsconfig.json) for MetaSaver projects with no-barrel architecture support. Use when creating or auditing tsconfig.json files to ensure proper path aliases (baseUrl, paths with

VS Code workspace settings template and validation logic with file cleanup enforcement. Includes 8 required standards (Prettier as default formatter, format on save enabled, ESLint auto-fix, pnpm package manager, terminal configuration, TypeScript workspace SDK, search exclusions, only settings.json required). Critical Rule 8 requires deletion of unnecessary files (extensions.json, launch.json, tasks.json). Use when creating or auditing .vscode/settings.json files and detecting unnecessary workspace files.

Use when mapping audit targets to appropriate config or domain agents. Analyzes file types, patterns, and content to determine which agents should audit each file/target. Returns agents[] needed for audit workflow.

Single source of truth for MetaSaver agent selection and subagent_type mapping

Use when testing web applications with Chrome DevTools MCP. Covers GUI Chrome setup and dev server configuration. Required reading before any browser automation.

Comprehensive coding standards for MetaSaver TypeScript projects including SOLID principles, DRY/KISS/YAGNI guidelines, error handling with AppError hierarchy, structured logging with Pino, and code organization rules. Use when implementing features, refactoring code, or establishing coding patterns.

Scans new/modified code against multi-mono shared libraries (@metasaver/core-utils, @metasaver/core-service-utils, @metasaver/core-components) to detect DRY violations. Use when auditing code for duplicate functions, types, or components that already exist in shared packages. Returns violation reports with suggested import replacements.

Use when transforming NEVER/DON'T statements into ALWAYS/DO patterns. Provides 20+ before/after examples, decision tree for tone selection, and psychology-backed guidance for effective LLM instruction design.

Post-workflow cache refresh for Repomix. Automatically refreshes compressed codebase representation after files are modified. Ensures next command has accurate context with 70% token savings. Invoke at end of any workflow that modifies source files. Takes ~2.4 seconds when refresh needed.

Use when determining which repositories or files a task affects. Distinguishes between target repos (where changes happen) and reference repos (for learning patterns). Supports both standard mode returning { targets, references } and audit mode detecting specific config files to audit. Returns structured scope object.

Token-efficient code reading protocol using Serena's progressive disclosure pattern (90-95% token savings). Provides mandatory workflow, tool reference, and common patterns for symbol-level code navigation.

Use when validating project structure during Standards Audit phase. Detects package type from package.json metasaver.projectType, loads structure rules from domain skills (react-app-structure, prisma-database, contracts-package), scans created/modified files, and reports violations with fix suggestions. File types: .tsx, .ts, directory layouts.

Validate workflow completion requirements before marking work done. Use when completing stories, closing epics, or claiming work is finished. Checks story file updates, acceptance criteria completion, and HITL approval. Triggers before any completion claim.

Bi-directional comparison workflow for config auditing. Compares what agents expect (from templates/standards) against what repositories actually have, presenting differences with remediation options. Use when agents need to audit configs, validate standards compliance, or identify mismatches between expected and actual configurations.

Use when creating, auditing, or validating MetaSaver contracts packages. Includes Zod validation schemas, TypeScript types, barrel exports, and database type re-exports. File types: .ts, package.json, tsconfig.json.

Use when scaffolding, auditing, or validating MetaSaver data service packages. Covers feature-based structure, service/controller/routes pattern, middleware integration, and API endpoint setup. Requires @metasaver/core-service-utils, {project}-contracts, {project}-database packages. File types: .ts, package.json.

File-to-agent mapping and manifest generation for composite monorepo audits. Provides dynamic discovery of all config agents, generates structured audit manifests with priority-ordered spawn instructions, and handles library vs consumer repo exclusions. Use when performing root-level composite audits that scan repository for all config files and coordinate parallel agent execution across 26+ config domains.

Use when scaffolding, auditing, or validating Prisma database packages in MetaSaver monorepos. Covers package structure, Prisma schema setup, database client initialization, and seed scripts. File types: .prisma, .ts, package.json.

Use when auditing, scaffolding, or validating MetaSaver React portal app directory structure. Includes file organization patterns, domain grouping, feature composition, routing configuration, and Auth0 integration setup. File types: .tsx, .ts, directory layouts.

Standardized remediation workflow presenting three options for handling config violations - Conform to template, Update template, or Ignore. Adapts recommendations based on repository type (library vs consumer). Use when audit violations are found and user needs to decide how to address them.

Verify that implemented code meets acceptance criteria from user stories. Use when validating story completion - performs code inspection, test execution, and manual checks against each AC criterion.

Parallel execution of analysis check skills. Command-specific - /ms uses all 3 checks, /build uses 2, /audit uses 2 different ones. See command for which checks to run.

Takes user stories and enriches them with implementation details, patterns, and file references. Spawns architect to add API endpoints, database models, component names, and cross-cutting concerns. Use when converting high-level stories to architecture-annotated specifications ready for execution.

Use when investigating config file discrepancies during audit. Spawns config agents in waves to compare template standards against actual files. READ-ONLY analysis - agents report findings but make no changes.

Apply approved remediation actions from audit resolution. Implements config file updates, template syncs, and code fixes using appropriate domain/config agents. Use when audit findings have been approved for remediation and need implementation.

Use when presenting audit discrepancies to user for decision (HITL). For each discrepancy show file path, diff (template vs actual), and ask user what to do - [1] apply template, [2] update template (PR), [3] ignore, or [4] custom instruction. Records decisions for remediation phase.

Execute browser debug steps using Chrome DevTools MCP. Navigate to URL, capture baseline snapshots/screenshots, perform interactions (click, fill, hover, press_key), collect console messages and network requests, validate results. Use when executing planned debug interactions with visual/DOM evidence capture.

Create debug test plan from user input. Use when planning browser debug sessions with Chrome DevTools. Parses prompt for URL/target, identifies interactions to test (clicks, inputs, flows), confirms plan with user via HITL, creates specific test steps (navigate, click, fill, verify). Outputs URL and test plan for debug execution.

Design phase with validation gates. Annotates PRD, creates story outlines, builds execution plan (via execution-plan-creation skill), validates artifacts via reviewer. NO HITL in this phase - single HITL happens after all docs complete.

Validate workflow documents against templates. Use when verifying PRD, execution plan, or user story files before HITL approval - checks required frontmatter fields and sections against templates.

Create or update epic retrospective documents. Use when user mentions "postmortem", "post-mortem", "post mortem", "retrospective", or "retro" for a completed epic or feature. Distinct from workflow-postmortem which tracks execution issues.

TDD-paired Gantt-style execution with compact waves. Each story gets tester agent (writes tests) BEFORE implementation agent (passes tests). Waves execute continuously with /compact between each wave. Respects dependencies, spawns up to 10 concurrent agents. Use when orchestrating parallel implementation workflows with test-first discipline.

Guide execution plan creation using the standard template. Execution plan organizes user stories into waves with agent assignments and verification gates. Use when PM agent drafts or updates an execution plan, or when validating wave structure and dependencies.

Use when presenting a plan/summary to user and requesting explicit approval before proceeding. Generic approval gate for /audit, /build, /architect, /debug commands. Checks for auto-approve conditions ("do without approval" in prompt).

Analyze PRD for innovation opportunities, present each with HITL selection loop (Implement/Skip/More Details), update PRD with selections. Use when /architect workflow reaches innovation phase after vibe-check. Always runs for /architect (unlike /build where innovation is optional).

Take enriched user stories and create execution plan with waves for parallel execution. Groups stories by dependencies into execution waves, assigns domain agents, and produces Gantt-style task schedule. Use when planning implementation workflow after architecture annotations.

Human validation of complete plan (PRD + Stories + Execution Plan) before execution. User sees full picture then approves or requests changes. Required for complexity ≥15.

Guide PRD document creation using the standard template. PRD contains REQUIREMENTS ONLY - no user stories (those are extracted separately). Use when EA agent drafts or updates a PRD, or when validating PRD structure.

Use when verifying code is production-ready. Runs build, lint, and test commands to check compilation, code quality, and test suite. Essential validation step for /build and /audit commands.

Final reporting and sign-off workflow. Spawns business-analyst for PRD completion verification, project-manager to consolidate results into executive report with metrics and recommendations. Use when finalizing and summarizing workflow results.

PRD creation with EA agent using AskUserQuestion for clarification, validation with reviewer, then BA extracts stories. NO HITL in this phase - continues to design-phase.

Save PRD artifacts to epic directory after approval. Creates docs/epics/in-progress/{prefix}-{name}/ with prd.md, user-stories/, execution-plan.md, innovations-selected.md, and architecture-notes.md. Use when persisting approved PRD from /architect command.

Helper methods for PM agents to read, write, and update workflow-state.json files consistently during workflow execution. Use when managing workflow state persistence, tracking wave progress, handling HITL stops, or resuming workflows.

Execute TDD workflow for user stories - spawn tester agent to write tests (RED), then coder agent to implement (GREEN). Use when executing stories in test-first discipline with parallel wave-based orchestration.

Updates template files in metasaver-marketplace as the source of truth before applying changes elsewhere. Use when standardizing configs across repos - updates template FIRST, then uses it for remediation. For config skills and domain skills with templates.

Guide user story creation using the standard template. User stories contain acceptance criteria, agent assignments, and technical details. Use when BA agent extracts stories from PRD, creates new stories, or validates story structure.

Quality validation after execution. Runs confidence-check skill (if complexity ≥15), spawns code-quality-validator for build verification, and reviewer agent for quality assessment. Scales checks based on change size.

Validate PRD quality and coherence before innovation phase using vibe-check MCP tool. Checks for requirement clarity, user story completeness, and identifies gaps. Returns coherent flag and issues list.

Dual-mode workflow issue logger. Use with mode=log to append mistakes during waves. Use with mode=summary at workflow end to review accumulated issues. Use when completing /build, /audit, or /ms workflows.