project-starter

A universal Claude Code workflow plugin with specialized agents, skills, hooks, and output styles for any software project. Compatible with skills.sh — works with Claude Code, Cursor, Codex, and 35+ AI agents.

Quick Start

Option 1: skills.sh (Recommended — Any Agent)

hljs language-bash

npx skills add CloudAI-X/claude-workflow-v2

Installs skills to Claude Code, Cursor, Codex, Windsurf, Cline, and 35+ other AI agents automatically.

Option 2: npx (Claude Code — Full Plugin)

hljs language-bash

npx install-claude-workflow-v2@latest

Installs the complete plugin: agents, commands, skills, and hooks.

Option 3: CLI (Per-Session)

hljs language-bash

# Clone the plugin
git clone https://github.com/CloudAI-X/claude-workflow-v2.git

# Run Claude Code with the plugin
claude --plugin-dir ./claude-workflow-v2

Option 4: Agent SDK

hljs language-typescript

import { query } from "@anthropic-ai/claude-agent-sdk";

for await (const message of query({
  prompt: "Hello",
  options: {
    plugins: [{ type: "local", path: "./claude-workflow-v2" }],
  },
})) {
  // Plugin commands, agents, and skills are now available
}

Option 5: Install Permanently

hljs language-bash

# Install from marketplace (when available)
claude plugin install project-starter

# Or install from local directory
claude plugin install ./claude-workflow-v2

Verify Installation

After loading the plugin, verify it's working:

hljs language-shell

> /plugin

Tab to Installed - you should see project-starter listed. Tab to Errors - should be empty (no errors).

These commands become available:

hljs language-bash

/project-starter:architect    # Architecture-first mode
/project-starter:rapid        # Ship fast mode
/project-starter:commit       # Auto-generate commit message
/project-starter:verify-changes  # Multi-agent verification

What's Included

Component	Count	Description
Agents	7	Specialized subagents for code review, debugging, security, etc.
Commands	26	Slash commands for workflows, output styles, planning, and onboarding
Skills	14	Knowledge domains with on-demand context loading
Hooks	14	Automation scripts for formatting, security, metrics, and notifications

Usage Examples

Commands in Action

Auto-commit your changes:

hljs language-sql

> /project-starter:commit

Looking at staged changes...
✓ Created commit: feat(auth): add JWT refresh token endpoint

Full git workflow:

hljs language-ruby

> /project-starter:commit-push-pr

✓ Committed: feat: add user dashboard
✓ Pushed to origin/feature/dashboard
✓ Created PR #42: https://github.com/you/repo/pull/42

Verify before shipping:

hljs language-yaml

> /project-starter:verify-changes

Spawning verification agents...
├─ build-validator: ✓ Build passes
├─ test-runner: ✓ 42 tests pass
├─ lint-checker: ⚠ 2 warnings (non-blocking)
└─ security-scanner: ✓ No vulnerabilities

Ready to ship!

Agents in Action

Agents spawn automatically based on your request:

You say: "The login is broken, users get 401 errors"

hljs language-csharp

[debugger agent activated]
→ Checking auth middleware... found issue
→ Token validation uses wrong secret in production
→ Fix: Update AUTH_SECRET in .env.production

You say: "Review my changes"

hljs language-csharp

[code-reviewer agent activated]
→ Analyzing 3 files changed...
✓ Logic is correct
⚠ Missing null check on line 42
⚠ Consider adding rate limiting to this endpoint

You say: "Add authentication to the API"

hljs language-markdown

[orchestrator agent activated]
→ Breaking down into subtasks:
  1. Design auth schema (spawning architect)
  2. Implement JWT middleware
  3. Add login/register endpoints
  4. Write tests (spawning test-architect)
  5. Update API docs (spawning docs-writer)

Skills in Action

Skills provide domain knowledge automatically:

You ask: "How should I structure the payment service?"

hljs language-csharp

[designing-architecture skill applied]
→ Recommending hexagonal architecture
→ Payment providers as adapters
→ Core domain isolated from infrastructure

You ask: "Make this endpoint faster"

hljs language-sql

[optimizing-performance skill applied]
→ Adding database indexes
→ Implementing response caching
→ Using pagination for large results

Hooks in Action

Hooks run automatically on events:

Security block (pre-edit):

hljs language-yaml

⛔ BLOCKED: Potential secret detected
   File: src/config.ts, Line 5
   Pattern: API key (sk-...)

   Remove the secret and use environment variables.

Auto-format (post-edit):

hljs language-bash

✓ Formatted with prettier: src/components/Button.tsx
✓ Formatted with black: scripts/deploy.py

Desktop notifications:

hljs language-csharp

🔔 "Claude needs input" - when waiting for your response
🔔 "Task complete" - when finished

Commands Reference

All commands use the format /project-starter:<command>.

Output Styles

Command	Mode
`/project-starter:architect`	System design mode - architecture before code
`/project-starter:rapid`	Fast development - ship quickly, iterate
`/project-starter:mentor`	Teaching mode - explain the "why"
`/project-starter:review`	Code review mode - strict quality

Git Workflow (Inner-Loop)

Command	Purpose
`/project-starter:commit`	Auto-generate conventional commit message
`/project-starter:commit-push-pr`	Commit → Push → Create PR (full workflow)
`/project-starter:quick-fix`	Fast fix for lint/type errors
`/project-starter:add-tests`	Generate tests for recent changes
`/project-starter:lint-fix`	Auto-fix all linting issues
`/project-starter:sync-branch`	Sync with main (rebase or merge)
`/project-starter:summarize-changes`	Generate standup/PR summaries

Verification

Command	Purpose
`/project-starter:verify-changes`	Multi-subagent adversarial verification
`/project-starter:validate-build`	Build process validation
`/project-starter:run-tests`	Tiered test execution
`/project-starter:lint-check`	Code quality checks
`/project-starter:security-scan`	Security vulnerability detection
`/project-starter:code-simplifier`	Post-implementation cleanup

Parallel

Command	Purpose
`/project-starter:parallel-review`	Review multiple files/dirs via subagents
`/project-starter:parallel-analyze`	Multi-perspective analysis via subagents

Planning & Refactoring

Command	Purpose
`/project-starter:plan`	Persistent PLAN.md with phase tracking
`/project-starter:refactor-guided`	4-phase systematic refactoring with safety
`/project-starter:dependency-upgrade`	Safe dependency upgrades with rollback

Onboarding & Knowledge

Command	Purpose
`/project-starter:tutorial`	Interactive guided tutorial for new users
`/project-starter:bootstrap-repo`	10-agent parallel repo exploration
`/project-starter:save-session-learnings`	Persist session discoveries to docs
`/project-starter:metrics`	View agent performance metrics

Agents

Agents are specialized subagents that Claude spawns automatically based on your task.

Agent	Purpose	Auto-Triggers
`orchestrator`	Coordinate multi-step tasks	"improve", "enhance", "build", "architecture", complex tasks
`code-reviewer`	Review code quality	"review", "PR review", "lint", code changes
`debugger`	Systematic bug investigation	Errors, crashes, memory leaks, timeouts, race conditions
`docs-writer`	Technical documentation	README, changelogs, migration guides, release notes
`security-auditor`	Security vulnerability detection	Auth, encryption, secrets, OAuth, JWT, CORS
`refactorer`	Code structure improvements	Tech debt, code smells, complexity reduction
`test-architect`	Design test strategies	Test plans, mocking, flaky tests, integration/E2E

Skills

Skills are knowledge domains that Claude uses autonomously when relevant.

Skill	Domain
`analyzing-projects`	Understand codebase structure and patterns
`designing-tests`	Unit, integration, E2E test approaches
`designing-architecture`	Clean Architecture, Hexagonal, etc.
`optimizing-performance`	Speed up applications, identify bottlenecks
`managing-git`	Version control, conventional commits
`designing-apis`	REST/GraphQL patterns and best practices
`parallel-execution`	Multi-subagent parallel task execution patterns
`web-design-guidelines`	Self-contained UI audit (A11Y, PERF, RD, SEC, I18N)
`vercel-react-best-practices`	React/Next.js performance optimization (45 rules)
`convex-backend`	Convex backend development (functions, schemas, etc.)
`database-design`	Schema design, indexing, query optimization
`devops-infrastructure`	Docker, CI/CD, deployment, IaC, monitoring
`error-handling`	Error patterns, structured logging, retry/circuit
`security-patterns`	Auth, RBAC, secrets, CORS, rate limiting, headers

Hooks

Hooks run automatically on specific events.

Hook	Trigger	Action
Security scan	Edit/Write	Blocks commits with potential secrets
File protection	Edit/Write	Blocks edits to lock files, .env, .git
Auto-format	Edit/Write	Runs prettier/black/gofmt by file type
TypeScript check	Edit/Write	Runs `tsc --noEmit` on .ts/.tsx files
Pre-commit check	Bash	Detects debug statements & temp markers
Branch protection	Bash	Warns on commits to protected branches
Command logging	Bash	Logs to `.claude/command-history.log`
Environment check	Session start	Validates Node.js, Python, Git
Prompt analysis	User prompt	Suggests appropriate agents
Auto-verify	Task complete	Runs tests/lint, reports results
Doc update suggest	Task complete	Suggests CLAUDE.md updates for changes
Session metrics	Task complete	Logs session telemetry to metrics file
Input notification	Input needed	Desktop notification
Complete notification	Task complete	Desktop notification

Examples

For detailed multi-agent orchestration examples, see the examples/ directory:

Example	Description
Comprehensive Code Review	6-agent sequential workflow for thorough code analysis
Parallel Execution	Fan-out multi-subagent workflow for independent tasks

Each example includes:

README.md - Overview and quick start
workflow.md - Exact prompts to use
verification.md - How to verify it works
sample-outputs/ - Example agent outputs

Configuration

Add Permissions to Your Project

Copy the permissions template to your project:

hljs language-bash

mkdir -p /path/to/your/project/.claude
cp templates/settings.local.json.template /path/to/your/project/.claude/settings.local.json

This pre-allows common safe commands so you don't get prompted every time.

Add Team Conventions

Copy the CLAUDE.md template to your project root:

hljs language-bash

cp templates/CLAUDE.md.template /path/to/your/project/CLAUDE.md

Then customize with your:

Package manager commands
Test/build/lint commands
Code conventions
Architecture decisions

MCP Servers

Copy the MCP template to enable integrations like Slack, GitHub, Sentry:

hljs language-bash

cp templates/mcp.json.template /path/to/your/project/.mcp.json

Then configure the environment variables for the servers you want to use.

GitHub Action (@.claude in PRs)

Enable Claude to respond to PR comments by installing the GitHub Action:

hljs language-bash

# In your repository
claude /install-github-action

This enables:

Tag @claude in PR comments to get code suggestions
Auto-update CLAUDE.md during code review
Claude responds to review feedback automatically

Example PR comment:

hljs language-graphql

@claude please add input validation to the email field

Team workflow tip: Use @claude to update your CLAUDE.md with learnings from code review:

hljs language-perl

@claude add a note to CLAUDE.md that we should always validate email format before API calls

Extending the Plugin

Add Custom Commands

Create .md files in commands/:

hljs language-markdown

---
allowed-tools: Bash(git:*), Read, Write
description: What this command does
argument-hint: [optional arguments]
---

[Command instructions here]

Add Custom Agents

Create .md files in agents/:

hljs language-markdown

---
name: my-agent
description: What it does. Use PROACTIVELY when [triggers].
tools: Read, Write, Edit, Bash
model: sonnet
---

[Agent instructions here]

Add Custom Skills

Create subdirectories in skills/ with a SKILL.md file:

hljs language-markdown

---
name: my-skill
description: Guides [domain]. Use when [triggers].
---

[Skill knowledge and patterns here]

Plugin Structure

hljs language-csharp

claude-workflow/
├── .claude-plugin/
│   ├── plugin.json           # Required: Plugin manifest
│   └── marketplace.json      # Optional: Marketplace metadata
├── agents/                   # 7 specialized agents
│   ├── orchestrator.md
│   ├── code-reviewer.md
│   ├── debugger.md
│   ├── docs-writer.md
│   ├── security-auditor.md
│   ├── refactorer.md
│   └── test-architect.md
├── commands/                 # 26 slash commands
│   ├── architect.md          # Output styles
│   ├── rapid.md
│   ├── mentor.md
│   ├── review.md
│   ├── commit.md             # Git workflow
│   ├── commit-push-pr.md
│   ├── quick-fix.md
│   ├── add-tests.md
│   ├── lint-fix.md
│   ├── sync-branch.md
│   ├── summarize-changes.md
│   ├── verify-changes.md     # Verification
│   ├── validate-build.md
│   ├── run-tests.md
│   ├── lint-check.md
│   ├── security-scan.md
│   ├── code-simplifier.md
│   ├── parallel-review.md    # Parallel
│   ├── parallel-analyze.md
│   ├── plan.md               # Planning & refactoring
│   ├── refactor-guided.md
│   ├── dependency-upgrade.md
│   ├── tutorial.md           # Onboarding & knowledge
│   ├── bootstrap-repo.md
│   ├── save-session-learnings.md
│   └── metrics.md
├── skills/                   # 14 knowledge domains
│   ├── analyzing-projects/
│   ├── convex-backend/
│   ├── database-design/
│   ├── designing-apis/
│   ├── designing-architecture/
│   ├── designing-tests/
│   ├── devops-infrastructure/
│   ├── error-handling/
│   ├── managing-git/
│   ├── optimizing-performance/
│   ├── parallel-execution/
│   ├── security-patterns/
│   ├── vercel-react-best-practices/
│   └── web-design-guidelines/
├── hooks/
│   ├── hooks.json            # Hook configuration
│   └── 14 automation scripts # Pre/post tool, session, metrics, notifications
├── templates/                # User-copyable templates
│   ├── CLAUDE.md.template
│   ├── settings.json.template
│   ├── settings.local.json.template
│   ├── mcp.json.template
│   ├── mcp-servers-template.md
│   └── README.md
├── CLAUDE.md                 # Plugin development guidelines
└── README.md

Requirements

Claude Code v1.0.33 or later
Python 3 (for hook scripts)
Node.js (optional, for npm commands)
Git (for version control features)

Multi-Agent Compatibility (skills.sh)

This repo is fully compatible with skills.sh — the universal agent skills platform. Our 14 skills work with 38+ AI coding agents:

Agent	Install Method
Claude Code	`npx skills add CloudAI-X/claude-workflow-v2` or full plugin install
Cursor	`npx skills add CloudAI-X/claude-workflow-v2`
Codex	`npx skills add CloudAI-X/claude-workflow-v2`
Windsurf	`npx skills add CloudAI-X/claude-workflow-v2`
Cline	`npx skills add CloudAI-X/claude-workflow-v2`
35+ more	`npx skills add CloudAI-X/claude-workflow-v2`

Note: npx skills add installs skills only. For the full Claude Code experience (agents, commands, hooks), use npx install-claude-workflow-v2@latest.

Contributing

Contributions welcome! See CONTRIBUTING.md.

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'feat: add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

claude-workflow-v2

project-starter

Quick Start

Option 1: skills.sh (Recommended — Any Agent)

Option 2: npx (Claude Code — Full Plugin)

Option 3: CLI (Per-Session)

Option 4: Agent SDK

Option 5: Install Permanently

Verify Installation

What's Included

Usage Examples

Commands in Action

Agents in Action

Skills in Action

Hooks in Action

Commands Reference

Output Styles

Git Workflow (Inner-Loop)

Verification

Parallel

Planning & Refactoring

Onboarding & Knowledge

Agents

Skills

Hooks

Examples

Configuration

Add Permissions to Your Project

Add Team Conventions

MCP Servers

GitHub Action (@.claude in PRs)

Extending the Plugin

Add Custom Commands

Add Custom Agents

Add Custom Skills

Plugin Structure

Requirements

Multi-Agent Compatibility (skills.sh)

Contributing

Star History

Credits

License

Similar Packages

Tags

Original Author

Publisher