A community-driven registry for Claude, Cursor, Windsurf, Cline & more. Not affiliated with Anthropic.
Are you the author? Sign in to claim
Your personal CTO Team for Claude Code . These Subagents will help you challenging yourself while you plan and execute.
Your personal CTO Team for Claude Code - Custom AI subagents that provide strategic technical leadership, system architecture design, and brutally honest feedback on your technical decisions.
Transform how you plan and execute software projects with three specialized AI agents that challenge your thinking, design scalable architectures, and validate your roadmaps before you commit resources.
Once installed, use these slash commands to instantly access CTO-level guidance:
| Command | What It Does | Example |
|---|---|---|
/validate | Ruthlessly validate your plans | /validate my Q2 roadmap |
/design | Design system architecture | /design notification system for 100K users |
/decide | Get help with build vs buy decisions | /decide should we use Auth0 or build custom auth |
/cto | General CTO guidance | /cto our app is slow, users complaining |
| Agent | Role | Best For |
|---|---|---|
| cto-orchestrator | Coordinator & Router | Vague requirements, multi-domain projects, unclear where to start |
| cto-architect | System Designer | New architecture, "How should I build X?", technology decisions, roadmaps |
| strategic-cto-mentor | Ruthless Validator | Validating plans, build vs buy, prioritization, need honest feedback |
The intelligent entry point for complex technical requests. Challenges vague buzzwords, clarifies requirements, and routes work to the right specialist.
Example triggers:
Designs comprehensive system architectures and implementation roadmaps with 15+ years of simulated experience in scalable web/mobile applications with ML/AI integration.
Core expertise:
Deliverables:
Ruthless CTO mentor who stress-tests your ideas until they're bulletproof. Simulates 20+ years of experience with hard lessons from both failed and successful ventures.
Seven-Dimension Evaluation Framework:
Anti-patterns Identified:
User Request
│
▼
┌─────────────────────────────────────────┐
│ cto-orchestrator │
│ Clarifies → Challenges → Routes │
└────────────────┬────────────────────────┘
│
┌────────────┴────────────┐
▼ ▼
┌───────────────┐ ┌─────────────────────┐
│ cto-architect │ │ strategic-cto-mentor│
│ (Design) │───▶│ (Validate) │
└───────────────┘ └─────────────────────┘
Design → Validate: Architect creates design, mentor stress-tests it Validate → Design: Mentor identifies flaws, architect revises
The CTO Team includes 4 custom slash commands for quick access to common CTO workflows:
/validate - Strategic ValidationRuthlessly validate plans, roadmaps, or proposals before committing resources.
/validate my Q2 roadmap: migrate to microservices, add real-time features, launch mobile app
Output: 8-section validation report with verdict (GOOD / NEEDS MAJOR WORK / BAD), critical flaws, blindspots, and concrete next steps.
/design - Architecture DesignDesign comprehensive system architecture with technology recommendations.
/design real-time notification system for e-commerce platform with 100K users
Output: Executive summary, system architecture, technology stack with trade-offs, implementation roadmap, risk assessment.
/decide - Strategic DecisionsGet help with build vs buy, technology choices, and prioritization dilemmas.
/decide should we use OpenAI API or host our own LLM for customer support chatbot
Output: Decision framework, TCO analysis, risk assessment, clear recommendation with rationale.
/cto - General GuidanceGeneral CTO-level guidance for complex or vague requests.
/cto we want to add AI capabilities to improve customer retention
Output: Clarifying questions, routed to appropriate specialist, structured recommendations.
The CTO Team includes 12 specialized skills that enhance agent capabilities:
| Skill | Purpose |
|---|---|
| request-analyzer | Classifies requests, detects vagueness, suggests routing |
| clarification-protocol | Generates targeted clarifying questions |
| delegation-prompt-crafter | Creates structured prompts for specialist agents |
| cost-estimator | Infrastructure and development cost estimation |
| Skill | Purpose |
|---|---|
| architecture-pattern-selector | Select between Monolith, Microservices, Serverless |
| roadmap-generator | Phased implementation plans with Epic/Story breakdown |
| tech-stack-recommender | Technology stack selection by project type |
| scalability-advisor | Scaling stages and capacity planning |
| ml-cv-specialist | ML system design and model selection |
| Skill | Purpose |
|---|---|
| assumption-challenger | Stress-test implicit assumptions in plans |
| antipattern-detector | Detect common failure patterns |
| validation-report-generator | 8-section validation reports with verdicts |
Skills are automatically discovered and used by agents based on context.
Before installing the CTO Team plugin, ensure you have:
Install directly from GitHub with a single command:
claude /plugin install alirezarezvani/claude-cto-team
This installs agents, slash commands, and skills globally - available in all your projects!
If you prefer project-specific installation:
# Clone the repository
git clone https://github.com/alirezarezvani/claude-cto-team.git
# Copy the plugin components to your project's .claude folder
cp -r claude-cto-team/agents /path/to/your/project/.claude/
cp -r claude-cto-team/commands /path/to/your/project/.claude/
cp -r claude-cto-team/skills /path/to/your/project/.claude/
claude-cto-team/
├── .claude-plugin/
│ └── plugin.json # Plugin manifest
├── agents/ # AI subagents
│ ├── cto-architect.md
│ ├── cto-orchestrator.md
│ └── strategic-cto-mentor.md
├── commands/ # Slash commands
│ ├── cto.md
│ ├── decide.md
│ ├── design.md
│ └── validate.md
└── skills/ # Agent skills
├── architecture-pattern-selector/
├── assumption-challenger/
├── antipattern-detector/
├── clarification-protocol/
├── cost-estimator/
├── delegation-prompt-crafter/
├── ml-cv-specialist/
├── request-analyzer/
├── roadmap-generator/
├── scalability-advisor/
├── tech-stack-recommender/
└── validation-report-generator/
The agents and commands are automatically available in Claude Code after installation.
"I want to build a mobile app that uses computer vision to identify plants. We expect 100K users in the first year."
→ Routes to cto-architect for comprehensive architecture design with ML pipeline recommendations
"Here's my draft Q2 roadmap: migrate to Kubernetes, implement real-time features, refactor payments, launch mobile app."
→ Routes to strategic-cto-mentor for ruthless stress-testing and timeline reality check
"Should we use OpenAI's API or host our own LLM? We're processing 50K conversations per month."
→ Routes to strategic-cto-mentor for TCO analysis and trade-off evaluation
Alireza Rezvani
Contributions are welcome! If you have ideas for improving these agents or want to add new capabilities:
git checkout -b feature/new-agent)git commit -m 'Add new agent capability')git push origin feature/new-agent)If this project saved you time or helped you make better technical decisions, consider supporting its continued development:
A star on GitHub also helps others discover this project:
MIT License - Alireza Rezvani
Found this useful? Share it with your network and help others discover AI-powered technical leadership for Claude Code!
Native macOS app to monitor Claude AI usage limits and watch your coding sessions live
npx CLI installing 100+ agents, commands, hooks, and integrations in one command
干净、强大、属于你的 AI Agent 平台 --AI agents, without the clutter.
Pocket Flow: Codebase to Tutorial
