Orchestrate full-cycle feature development via 6-phase SDLC pipelines with plan persistence and verification, conduct cached deep technical research across projects, systematically debug issues, verify code changes with git diffs and quality gates, and delegate complex reasoning or architecture to specialized agents.
Systematic debugging with deep reasoning. Use for: investigating errors, tracing bugs, analyzing stack traces, or methodically diagnosing unexpected behavior. Example: "/debug TypeError: Cannot read property 'map' of undefined"
Unified 6-phase SDLC with plan persistence, resume mode, and autonomous execution
Thorough technical discussion with context-aware clarifying questions
Comprehensive verification with automated quality gates, confession gathering, and confidence-based issue filtering. Default: self-review with gates. --deep: multi-agent review via code-reviewer agent. Use before committing, after fixing bugs, or to validate feature completeness.
Deep research on technical topics with intelligent caching. Supports: research, promote, refresh, and list operations. Example: "/research domain-driven design" or "/research promote ddd"
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing comprehensive implementation blueprints with specific files to create/modify, component designs, data flows, and build sequences
Deeply analyzes existing codebase features by tracing execution paths, mapping architecture layers, understanding patterns and abstractions, and documenting dependencies to inform new development
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter
Deep research specialist using EXA tools for comprehensive topic investigation. Use when needing to research patterns, architectures, technologies, or best practices. Manages a two-tier cache system for cross-project reuse and team knowledge sharing.
Elite reasoning partner for complex logical problems, multi-step reasoning, and strategic decisions. Use PROACTIVELY when facing architectural choices, difficult tradeoffs, or decisions with significant long-term implications. Trigger when user asks "should I", "what are the tradeoffs", "help me decide", "think through", or needs to evaluate multiple options.
Deep research on technical topics using EXA tools with intelligent two-tier caching. Use when user asks to research a topic, investigate best practices, look up information, find patterns, or explore architectures. Also invoked by /research command. Triggers: "research", "look up", "investigate", "deep dive", "find information about", "what are best practices for", "how do others implement".
Orchestrates 6-phase SDLC pipeline (discovery, requirements, architecture, workstreams, implementation, summary) for guided feature development. Use when user runs /core:develop command, requests spec-driven development, wants to create implementation plans with architecture decisions, or mentions "SDLC", "spec-driven", "plan feature", "development pipeline". Supports plan persistence, wave-based resume, autonomous mode, and architecture/implementation verification.
Coordinate structured thinking and multi-agent parallel execution for complex tasks. Use when tackling multi-step projects, planning parallel work, breaking down complex problems, coordinating specialist tasks, facing architectural decisions, or when user mentions "workflow", "orchestration", "multi-step", "coordinate", "parallel execution", "structured thinking", "break this down", "plan this out", "how should I approach", or needs help planning complex implementations.
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses bash pre-commands but Bash not in allowed tools
Uses bash pre-commands but Bash not in allowed tools
Supercharge Claude Code with 109 specialized components — from deep reasoning and autonomous dev loops to
DDD architecture, design system enforcement, and git workflow automation. 22 agents, 32 commands, 55 skills across 13 modular plugins.
| Plugin | Description | Key Components | Docs |
|---|---|---|---|
| 🧠 Core | 6-phase SDLC pipeline with multi-agent orchestration and deep research. | deep-think-partner, deep-researcher, /develop, /research | View |
| 🤖 AI | AI engineering toolkit for production LLM apps, RAG, and prompt optimization. | ai-engineer, prompt-engineer, lyra, /improve-agent | View |
| 📝 Doc | Documentation generation with diagrams, ADRs, RFCs, and Johnny.Decimal management. | rfc-critic, adr-critic, doc-coauthoring, /diagram, /rfc | View |
| 🔍 Review | Code quality, security, and design reviews with pragmatic standards. | pragmatic-code-review, design-review, false-positive-verifier | View |
| 🧵 Stitch | Atomic UI prompt authoring and MCP-powered Google Stitch screen generation. | /prompt, /stitch-generate, generating-stitch-screens | View |
| 🔀 Git | Workflow automation with smart commits, PRs, changelogs, and Dependabot triage. | /commit, /create-pr, /changelog, dependabot-review | View |
| 📐 Design Intent | Visual React prototyping from Figma/mockups with persistent pattern memory. | design-intent-specialist, /design-intent, /save-patterns | View |
| 💻 Lang | Production-grade language-specific skills (Bash/Shell). | scripting-bash, POSIX compliance, ShellCheck | View |
| 🎭 Playwright | Browser automation via Playwright CLI for testing and screenshots. | playwright-cli, /playwright-setup | View |
| 🍃 Spring Boot | DDD with Spring Boot 4, Modulith 2.0, Security 7, and OpenTelemetry. | 10 skills: DDD, data, web-api, modulith, security, observability, testing, flyway | View |
| 🔄 Ralph | Autonomous development loop with fresh context, task sets, and memory system. | ralph-agent, /ralph, /create-prd, Hat-lite system | View |
| 🗺️ Roadmap | Product management, roadmap analysis, and solution architecture. | product-manager, system-architect, roadmap-analyst | View |
| 🔧 Devtools | Developer tooling: SOPS encryption, Claude Code environment setup, quality stack. | sops-setup, code-env-setup, quality-stack | View |
Option A: Install directly from GitHub (recommended)
/plugin marketplace add joaquimscosta/arkhe-claude-plugins
Option B: Clone and install locally
git clone https://github.com/joaquimscosta/arkhe-claude-plugins.git
/plugin marketplace add ./arkhe-claude-plugins
You can install all plugins at once:
npx claudepluginhub joaquimscosta/arkhe-claude-plugins --plugin coreDomain-Driven Design with Spring Boot 4 (DDD patterns, Spring Data, REST APIs, Spring Modulith)
Language-specific programming skills for production-grade code (Bash)
Autonomous development loop with fresh context per iteration, Hat-lite builder/verifier system, task sets, and persistent memories
Startup idea validation pipeline with 6-stage analysis, decision gates, and domain presets
Product management, roadmap analysis, and solution architecture with multi-agent orchestration
Verification-first engineering toolkit for Claude Code. 15 skills across a 5-phase spine (Investigate → Design → Implement → Verify → Ship), 8 specialist agents, an interactive setup wizard. Every skill has rationalizations + evidence requirements. Built for senior ICs and tech leads.
Code transformation: Dev SDLC orchestrator (code-shipping pipeline), plan, assert, audit, review, test, refactor, debug, for-sure. Hosts engineering agents.
Use Claude Code As Is - native plugin leveraging built-in architecture
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Plugin de ingeniería de software completa: 10 agentes de núcleo y 9 opcionales con personalidad propia, memoria persistente por proyecto, quality gates y flujos automatizados desde la idea hasta producción.
Helder's personal SDLC toolbelt for AI coding agents — from PRD to ship. Bundles the tracer-bullet workflow alongside TDD, code review, audits, and shipping skills.