Use this agent when reviewing code for Clean Architecture compliance. This includes evaluating dependency rules, layer separation, and architectural boundaries. Typically called as part of a code review process alongside other review agents.\n\nExamples:\n\n \nContext: User has just written or modified code in the…
Use this agent when you need to evaluate code changes against clean code principles and best practices. This agent analyzes code for readability, maintainability, and adherence to clean code standards across all categories including naming, functions, comments, formatting, error handling, and boundaries. It provides…
Use this agent when you need an opinionated, thorough code review of Rust code from a principal engineer perspective. This includes reviewing for design quality, functionality correctness, complexity management, test coverage, naming conventions, comments, style guide compliance, and overall code health. Particularly…
Automate terminal UI (TUI) apps with agent-tui for testing, inspection, demos, and scripted interactions. Use when automating CLI/TUI flows, regression testing terminal apps, verifying interactive behavior, or extracting structured text from terminal UIs. Also use when asked what agent-tui is, how it works, or to demo…
Discover and replay terminal UI paths using agent-tui. Use when you need to launch a TUI app, explore navigation with bounded BFS, generate markdown acceptance tests, and verify those tests repeatedly. Do not use for web or desktop GUI automation.
Use when starting a long-running or interactive CLI command with oly, especially when it may need later input, should be detachable, or should keep durable logs for supervision and resume.
A remote-terminal workflow for managing local or SSH connections, opening terminals, running commands, viewing output, taking snapshots, and transferring files. SSH is a secure way to operate another computer over a network.
Drive a running WinkTerm backend over HTTP: list SSH connections, open local/SSH terminals, run commands and read output, take terminal snapshots, and transfer files via SSH. Requires a reachable WinkTerm backend.
Drive a running WinkTerm backend — prefer the winkterm-mcp MCP server when available; otherwise use the winkterm CLI (WebSocket long-connection, so long-running commands aren't cut by a reverse proxy's idle timeout) with HTTP as fallback. Manage SSH connections (create/read/update/delete), open local/SSH terminals…
Full-stack zero-human deployment specialist. Builds projects from scratch (Next.js + self-hosted Convex), creates GitHub repos, configures Dokploy, sets up Hostinger DNS, generates JWT keys, and deploys Convex schema automatically. Use for any new project deployment or from-scratch build task.
Main orchestrator for VPS Control Room. Analyzes tasks, delegates to specialist agents (vps-frontend, vps-convex, vps-host-agent), generates new skills when repetitive patterns emerge. Use for planning, multi-component tasks, or when unsure which specialist to use.
Host agent specialist for VPS Control Room. Creates and modifies collectors, executor, allowlist, validators, config, health endpoint, and graceful shutdown. Use for all work under agent/.
Drive the local vps-cr CLI from Claude Code — start/stop, doctor, config, device approval (acc/list/revoke), status, secret. Usage: /vps-cr [args], e.g. /vps-cr --acc or /vps-cr doctor --fix.
Instructions for rahmanef63/control-room: The single source of truth for every coding agent (Claude, Codex, Gemini) is CLAUDE.md in the repo root. Read it before starting any task.
19 2d agoA99 tokens
originalMIT
At most 3 mods per repository are shown here — the rest are on their repository pages: