The Agents
A multi-agent system where each agent has a distinct role, model, tools, and permission boundary.
System orchestrator and user-facing assistant Claude Opus 4
Responsibilities & Tools
- User-facing assistant β Daily requests, scheduling, reminders, cross-platform messaging (iMessage, Signal, Telegram)
- Multi-agent orchestration β Delegates tasks to specialized agents, monitors progress, reviews output
- System administration β Server monitoring, automated backups, cron jobs, deployments
- Infrastructure β SSH access to remote servers, tmux session management, Docker operations
- Tools β web_search, web_fetch, browser automation, Chrome DevTools MCP, Tavily search, file operations, memory system, Apple Notes/Reminders, TTS, voice calls, nodes (paired device control), cron scheduling, MCP servers (Tavily, TCS time-awareness, Chrome DevTools)
Permissions
βFull server access
βSend messages to any contact
βSpawn sub-agents
βNo financial operations without human approval
βCannot execute destructive server operations
βCannot read CTF solutions
Deep research specialist and opportunity analyst Claude Sonnet 4
Responsibilities & Tools
- Autonomous deep research β Receives broad directions, decomposes into research trees, produces comprehensive reports
- Opportunity discovery β Market analysis, competitive intelligence, trend identification
- Data analysis β Collection, cleaning, analysis with actionable recommendations
- Agent delegation β Can delegate to Coder and Content agents to push research into production
- Tools β web_search, web_fetch, Tavily deep search, file operations, memory system
Permissions
βWeb research
βFile read/write in own workspace
βDelegate to Coder/Content agents
βNo server access
βNo direct user messaging
βNo financial operations
Senior software engineer across Python, TypeScript, and Rust Claude Sonnet 4
Responsibilities & Tools
- Feature development β Builds features, refactors codebases, fixes bugs across Python/TypeScript/Rust
- Workflow β Operates via Claude Code in tmux β full IDE-like workflow with file exploration and iterative development
- Code quality β PR reviews, code audits, test writing
- Tools β Claude Code (via tmux), git, SSH, Docker, all standard dev tooling
Permissions
βFull filesystem access in project dirs
βGit operations
βSSH to dev servers
βNo direct user messaging
βNo financial operations
βMust use Claude Code (not raw file edits)
Social content creator for Xiaohongshu (ε°ηΊ’δΉ¦) Claude Sonnet 4
Responsibilities & Tools
- Content strategy β "Historical figures reborn in modern times" series β Cao Cao, Qin Shi Huang, and others
- Character roleplay β Generates in-character posts, perspectives, and reactions to contemporary events
- Trend tracking β Scans trending topics β matches with historical characters β generates targeted content
- Tools β Xiaohongshu MCP, web_search, image generation tools
Permissions
βContent creation
βSocial media posting via MCP
βImage generation
βNo server access
βNo code execution
βNo financial operations
Real-time voice participant via split-brain architecture Claude Sonnet 4
Responsibilities & Tools
- Voice participation β Joins Microsoft Teams meetings via split-brain architecture (Linux STT/TTS + Mac agent reasoning)
- Real-time Q&A β Answers questions during meetings with ~9 second latency
- Project knowledge β Can explain any project in the ecosystem, discuss architecture decisions, answer technical questions
- Tools β Voice pipeline (Whisper STT + TTS), meeting context memory
Permissions
βVoice participation
βAccess to project documentation
βReal-time Q&A
βCannot disconnect itself from meetings
βNo file modifications
βNo financial operations
The Trinity architecture for CTF competitions. Three specialized agents coordinate through a shared blackboard to solve security challenges autonomously. At BearcatCTF 2026, this system placed #20 out of 362 teams (top 6%), solving 40 of 44 challenges.
Full lifecycle management of CTF challenges Claude Opus 4
Responsibilities & Tools
- Strategic coordination β Task decomposition, progress orchestration, retry strategies
- Blackboard maintenance β Persistent shared state tracking all IPs, ports, credentials, flags, and attempted strategies
- Sub-agent orchestration β Spawns Operator and Librarian as needed
- Retry logging β Records failed approaches to prevent repeated dead ends
- Tools β Sub-agent spawning, blackboard management, file operations, memory system
Permissions
βSpawn Operator/Librarian
βFull challenge management
βCannot read flag files or solutions
βCannot access systems outside CTF scope
Stateless executor β context resets after each task Claude Sonnet 4
Responsibilities & Tools
- Tactical execution β Receives specific sub-tasks from Commander, executes, returns JSON results
- Exploit development β Writes and runs exploit scripts, operates Docker containers
- Micro-level error recovery β Handles permission issues, missing dependencies autonomously
- Tools β Shell commands, Python/script execution, Docker, network tools (nmap, curl, etc.)
Permissions
βCommand execution in CTF containers
βExploit script writing
βCannot attack real external systems
βCannot run untrusted binaries on host macOS
βCannot exceed Commander-assigned scope
Top-3 results only β no redundancy Claude Haiku 4
Responsibilities & Tools
- Knowledge retrieval β Searches local CTFKnowledges database for relevant techniques and methodologies
- Tool lookup β Queries CTFTools for available tools and usage patterns
- Web research fallback β Searches for CVEs, writeups, and technical documentation when local knowledge is insufficient
- Tools β Local knowledge base search, web_search, CTF writeup databases
Permissions
βKnowledge retrieval
βWeb search
βCannot execute system commands
βCannot modify files (except own memory/lessons.md)
βRead-only access