Build production-ready software with Claude Code - Plugins and tools that bring best practices, specialized agents, automated quality checks, and safety guardrails to your development process.
This marketplace includes the following plugins:
- dev-workflows - Backend and general-purpose development
- dev-workflows-frontend - React/TypeScript specialized workflows
External:
- metronome - During repetitive tasks, Claude may switch to bulk bash operations under the guise of "working efficiently," potentially breaking files. This plugin detects that behavior and intercepts execution, nudging Claude to slow down and proceed step by step.
Want to contribute a plugin? See CONTRIBUTING.md.
Choose what fits your project:
# 1. Start Claude Code
claude
# 2. Install the marketplace
/plugin marketplace add shinpr/claude-code-workflows
# 3. Install backend plugin
/plugin install dev-workflows@claude-code-workflows
# 4. Restart session (required)
# Exit and restart Claude Code
# 5. Start building
/implement <your feature># 1-2. Same as above (start Claude Code and add marketplace)
# 3. Install frontend plugin
/plugin install dev-workflows-frontend@claude-code-workflows
# 4-5. Same as above (restart and start building)
# Use frontend-specific commands
/front-design <your feature>Install both plugins to get the complete toolkit for backend and frontend work.
# Use fullstack commands for cross-layer features
/fullstack-implement "Add user authentication with JWT + login form"
# Or execute from existing fullstack work plan
/fullstack-buildThe fullstack commands create separate Design Docs per layer (backend + frontend), verify cross-layer consistency via design-sync, and route tasks to the appropriate executor based on filename patterns. See Fullstack Workflow for details.
# Install metronome (prevents shortcut-taking behavior)
/plugin install metronome@claude-code-workflowsNote: If you encounter SSH errors during installation, see SSH Setup FAQ below.
graph TB
A[👤 User Request] --> B[🔍 requirement-analyzer]
B --> |"📦 Large (6+ files)"| C[📄 prd-creator]
B --> |"📦 Medium (3-5 files)"| D[📐 technical-designer]
B --> |"📦 Small (1-2 files)"| E[⚡ Direct Implementation]
C --> D
D --> DR[📋 document-reviewer]
DR --> DS[🔄 design-sync]
DS --> F[🧪 acceptance-test-generator]
F --> G[📋 work-planner]
G --> H[✂️ task-decomposer]
H --> I[🔨 task-executor]
E --> I
I --> J[✅ quality-fixer]
J --> K[🎉 Ready to Commit]
graph LR
P[🐛 Problem] --> INV[🔍 investigator]
INV --> |Evidence Matrix| ASS{Complex?}
ASS --> |Yes| VER[⚖️ verifier]
ASS --> |No| SOL[💡 solver]
VER --> |Validated Conclusion| SOL
SOL --> |Solutions + Steps| R[📋 Report]
graph TB
subgraph Phase1[Phase 1: PRD Generation]
CMD[📜 /reverse-engineer] --> SD[🔍 scope-discoverer unified]
SD --> PRD[📄 prd-creator]
PRD --> CV1[✅ code-verifier]
CV1 --> DR1[📋 document-reviewer]
end
subgraph Phase2[Phase 2: Design Doc Generation]
TD[📐 technical-designer] --> CV2[✅ code-verifier]
CV2 --> DR2[📋 document-reviewer]
DR2 --> DONE[📚 Complete]
end
DR1 --> |"All PRDs Approved (reuse scope)"| TD
- Analysis - Figures out how complex your task is
- Planning - Creates the right docs (PRD, design doc, work plan) based on complexity
- Execution - Specialized agents handle implementation autonomously
- Quality - Runs tests, checks types, fixes errors automatically
- Review - Makes sure everything matches the design
- Done - Clean, production-ready code
| Command | Purpose | When to Use |
|---|---|---|
/implement |
End-to-end feature development | New features, complete workflows |
/fullstack-implement |
End-to-end fullstack development | Cross-layer features (requires both plugins) |
/task |
Execute single task with precision | Bug fixes, small changes |
/design |
Create design documentation | Architecture planning |
/plan |
Generate work plan from design | Planning phase |
/build |
Execute from existing task plan | Resume implementation |
/fullstack-build |
Execute fullstack task plan | Resume cross-layer implementation (requires both plugins) |
/review |
Verify code against design docs | Post-implementation check |
/diagnose |
Investigate problems and derive solutions | Bug investigation, root cause analysis |
/reverse-engineer |
Generate PRD/Design Docs from existing code | Legacy system documentation, codebase understanding |
/add-integration-tests |
Add integration/E2E tests to existing code | Test coverage for existing implementations |
/update-doc |
Update existing design documents with review | Spec changes, review feedback, document maintenance |
| Command | Purpose | When to Use |
|---|---|---|
/front-design |
Create frontend design docs | React component architecture |
/front-plan |
Generate frontend work plan | Component breakdown planning |
/front-build |
Execute frontend task plan | Resume React implementation |
/front-review |
Verify code against design docs | Post-implementation check |
/task |
Execute single task with precision | Component fixes, small updates |
/diagnose |
Investigate problems and derive solutions | Bug investigation, root cause analysis |
/update-doc |
Update existing design documents with review | Spec changes, review feedback, document maintenance |
Tip: Both plugins share
/task,/diagnose, and/update-doccommands with the same functionality. For reverse engineering, use/reverse-engineerwith the fullstack option to generate both backend and frontend Design Docs in a single workflow.
These agents work the same way whether you're building a REST API or a React app:
| Agent | What It Does |
|---|---|
| requirement-analyzer | Figures out how complex your task is and picks the right workflow |
| work-planner | Breaks down design docs into actionable tasks |
| task-decomposer | Splits work into small, commit-ready chunks |
| code-reviewer | Checks your code against design docs to make sure nothing's missing |
| document-reviewer | Reviews single document quality, completeness, and rule compliance |
| design-sync | Verifies consistency across multiple Design Docs and detects conflicts |
| investigator | Collects evidence, enumerates hypotheses, builds evidence matrix for problem diagnosis |
| verifier | Validates investigation results using ACH and Devil's Advocate methods |
| solver | Generates solutions with tradeoff analysis and implementation steps |
| scope-discoverer | Discovers functional scope from codebase for reverse engineering |
| code-verifier | Validates consistency between documentation and code implementation |
| Agent | What It Does |
|---|---|
| prd-creator | Writes product requirement docs for complex features |
| technical-designer | Plans architecture and tech stack decisions |
| acceptance-test-generator | Creates E2E and integration test scaffolds from requirements |
| integration-test-reviewer | Reviews integration/E2E tests for skeleton compliance and quality |
| task-executor | Implements backend features with TDD |
| quality-fixer | Runs tests, fixes type errors, handles linting - everything quality-related |
| rule-advisor | Picks the best coding rules for your current task |
| Agent | What It Does |
|---|---|
| prd-creator | Writes product requirement docs for complex features |
| technical-designer-frontend | Plans React component architecture and state management |
| task-executor-frontend | Implements React components with Testing Library |
| quality-fixer-frontend | Handles React-specific tests, TypeScript checks, and builds |
| rule-advisor | Picks the best coding rules for your current task |
| design-sync | Verifies consistency across multiple Design Docs and detects conflicts |
The backend plugin includes proven best practices that work with any language:
- Coding Principles - Code quality standards
- Testing Principles - TDD, coverage, test patterns
- Implementation Approach - Design decisions and trade-offs
- Documentation Standards - Clear, maintainable docs
These are loaded as skills and automatically applied by agents when relevant.
The frontend plugin has React and TypeScript-specific rules built in.
When building with AI coding assistants, you often run into:
- Context gets exhausted in long sessions
- Code quality drops over time
- Patterns become inconsistent
- You end up fixing test failures and type errors manually
These plugins fix that by:
- Fresh context for each phase - Specialized agents handle different parts without context exhaustion
- Enforced best practices - Language-agnostic rules (backend) and React patterns (frontend) keep quality consistent
- Automated quality checks - Tests, types, and linting run automatically and get fixed if they fail
- Complete lifecycle - From requirements to implementation to review
The frontend plugin is built specifically for React development:
- Component architecture planning with state management decisions
- React Testing Library integration from the start
- TypeScript-first approach with automatic type generation
- Handles build errors, test failures, and type issues automatically
Built in 2 days - 30 TypeScript files with full test coverage, now running in production.
Built in 1.5 days - Complete creative tool with multi-image blending and character consistency.
The right workflow structure + specialized agents = production-quality code at AI speed.
/implement "Add user authentication with JWT"
# What happens:
# 1. Analyzes your requirements
# 2. Creates design documents
# 3. Breaks down into tasks
# 4. Implements with TDD
# 5. Runs tests and fixes issues
# 6. Reviews against design docs/front-design "Build a user profile dashboard"
# What happens:
# 1. Plans React component structure
# 2. Defines state management approach
# 3. Creates work plan
#
# Then run:
/front-build
# This:
# 1. Implements components with Testing Library
# 2. Writes tests for each component
# 3. Handles TypeScript types
# 4. Fixes lint and build errors/fullstack-implement "Add user authentication with JWT + React login form"
# What happens:
# 1. Analyzes requirements (same as /implement)
# 2. Creates PRD covering the entire feature
# 3. Creates separate Design Docs for backend AND frontend
# 4. Verifies cross-layer consistency via design-sync
# 5. Creates work plan with vertical feature slices
# 6. Decomposes into layer-aware tasks (backend/frontend/fullstack)
# 7. Routes each task to the appropriate executor
# 8. Runs layer-appropriate quality checks
# 9. Commits vertical slices for early integrationRequires both plugins installed. The fullstack commands create separate Design Docs per layer and route tasks to backend or frontend executors based on filename patterns (
*-backend-task-*,*-frontend-task-*). For reverse engineering existing fullstack codebases, use/reverse-engineerwith the fullstack option.
/task "Fix validation error message"
# Direct implementation with quality checks
# Works the same in both plugins/review
# Checks your implementation against design docs
# Catches missing features or inconsistencies/diagnose "API returns 500 error on user login"
# What happens:
# 1. Investigator collects evidence from code, logs, git history
# 2. Builds evidence matrix with multiple hypotheses
# 3. Verifier validates findings with ACH and Devil's Advocate
# 4. Solver generates solutions with tradeoff analysis
# 5. Presents actionable implementation steps/reverse-engineer "src/auth module"
# What happens:
# 1. Discovers functional scope (user-value + technical) in a single pass
# 2. Generates PRD for each feature unit
# 3. Verifies PRD against actual code
# 4. Reviews and revises until consistent
# 5. Maps scope to Design Doc targets (no re-discovery)
# 6. Generates Design Docs with code verification
# 7. Produces complete documentation from existing codeWith fullstack option:
/reverse-engineer "src/auth module"
# When prompted, select Fullstack design: Yes
# Additional behavior:
# - Each feature unit gets both backend AND frontend Design Docs
# - Backend Design Doc: API contracts, data layer, business logic
# - Frontend Design Doc: component hierarchy, state management, UI interactions
# - Frontend Design Doc references backend Design Doc for API contractsIf you're working with undocumented legacy code, these commands are designed to make it AI-friendly by generating PRD and design docs. For a quick walkthrough, see: How I Made Legacy Code AI-Friendly with Auto-Generated Docs
claude-code-workflows/
├── .claude-plugin/
│ └── marketplace.json # Manages both plugins
│
├── agents/ # Shared agents (symlinked by both plugins)
│ ├── code-reviewer.md
│ ├── investigator.md # Diagnosis workflow
│ ├── verifier.md # Diagnosis workflow
│ ├── solver.md # Diagnosis workflow
│ ├── scope-discoverer.md # Reverse engineering workflow
│ ├── code-verifier.md # Reverse engineering workflow
│ ├── task-executor.md
│ ├── technical-designer.md
│ └── ... (17 agents total)
│
├── commands/ # Shared commands
│ ├── implement.md
│ ├── design.md
│ ├── diagnose.md # Problem diagnosis
│ ├── reverse-engineer.md # Reverse documentation
│ ├── plan.md
│ ├── build.md
│ └── ... (10 commands for backend, 8 for frontend)
│
├── skills/ # Skills (auto-loaded by agents)
│ ├── ai-development-guide/
│ ├── coding-principles/
│ ├── testing-principles/
│ ├── implementation-approach/
│ ├── typescript-rules/ # Frontend-specific
│ └── ... (11 skills total)
│
├── backend/ # dev-workflows plugin
│ ├── agents/ # Symlinks to shared agents
│ ├── commands/ # Symlinks to shared commands
│ ├── skills/ # Symlinks to shared skills
│ └── .claude-plugin/
│ └── plugin.json
│
├── frontend/ # dev-workflows-frontend plugin
│ ├── agents/ # Symlinks to shared agents
│ ├── commands/ # Symlinks to shared commands
│ ├── skills/ # Symlinks to shared skills
│ └── .claude-plugin/
│ └── plugin.json
│
├── LICENSE
└── README.md
Q: Which plugin should I install?
A: Depends on what you're building:
- Backend, APIs, CLI tools, or general programming → Install
dev-workflows - React apps → Install
dev-workflows-frontend - Full-stack projects → Install both
Both plugins can run side-by-side without conflicts.
Q: Can I use both plugins at the same time?
A: Yes! They're designed to work together. Install both if you're building a full-stack app. Use /fullstack-implement for features that span both backend and frontend — it creates separate Design Docs per layer and routes tasks to the appropriate executor automatically.
Q: Do I need to learn special commands?
A: Not really. For backend, just use /implement. For frontend, use /front-design. The plugins handle everything else automatically.
Q: What if there are errors?
A: The quality-fixer agents (one in each plugin) automatically fix most issues like test failures, type errors, and lint problems. If something can't be auto-fixed, you'll get clear guidance on what needs attention.
Q: SSH authentication error during plugin installation? A: Set up SSH keys for GitHub:
# 1. Check if SSH key already exists
ls ~/.ssh/id_ed25519.pub
# 2. Generate new SSH key (if needed)
ssh-keygen -t ed25519 -C "your_email@example.com"
# → Press Enter to save to default location
# → Enter a strong passphrase when prompted (recommended for security)
# 3. Add SSH key to ssh-agent
eval "$(ssh-agent -s)"
ssh-add ~/.ssh/id_ed25519
# 4. Copy public key to clipboard
cat ~/.ssh/id_ed25519.pub
# → Copy the output
# 5. Add to GitHub
# Go to https://github.com/settings/keys
# Click "New SSH key"
# Paste your public key and save
# 6. Test connection
ssh -T git@github.com
# → Should see: "Hi username! You've successfully authenticated..."This marketplace focuses on plugins that improve control, reliability, and safety in agentic coding. If your plugin helps developers trust and manage AI coding agents in production workflows, we'd like to hear from you.
See CONTRIBUTING.md for submission guidelines and acceptance criteria.
MIT License - Free to use, modify, and distribute.
See LICENSE for full details.
Happy Coding with Claude Code Workflows! 🚀✨
