CyberBrain

Use when installing, reinstalling, auditing, or preparing Brain-managed Superpowers, Spec Kit, and OpenSpec workflow arsenals under a project-local `.brain/vendor` directory so Brain can inspect and route them without exposing their raw Codex skills/prompts at the project root.

Use when the user asks to check, add, or manage macOS Calendar events.

Use when the user asks to send an email via the macOS Mail app.

Use when the user asks to send a text message or iMessage via the macOS Messages app.

Use when a task involves web search, current information, source verification, citations, or entity/person/paper/project disambiguation.

Use when the task involves `exec_command` escalation, `prefix_rule`, sandbox permissions, writable roots, or Codex platform-specific operational patterns.

Use when a task asks to run calculations, simulations, model training, computational searches, benchmarks, optimizations, workflows, agents, pipelines, or other tool-heavy execution before the scientific question and interpretation boundary are clear.

Use at the start of every primary-agent and subagent conversation — the top-level skill controller. Always activates whole-object-responsibility and state-machine foundations, then routes to domain brain skills and external skill arsenals including superpowers.

Always-active project-state foundation for primary agents and subagents. Use to create a working-directory-local state node, track claim-bearing state transitions, and escalate from lightweight ledger entries to an explicit state machine for long, ordered, resumable, or multi-agent work.

Use when the user asks to run Aider CLI in non-interactive mode or references Aider for AI pair programming, code editing, or git-integrated development.

Use when the user asks to run Cline CLI in non-interactive mode or references Cline for AI-assisted coding or task-based development.

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, code review, or automated editing

Use when tasks benefit from Gemini CLI for code generation, review, analysis, web research, a second AI perspective, codebase architecture analysis, parallel code generation, or when the user explicitly requests Gemini operations.

Use when the user asks to run GitHub Copilot CLI in non-interactive mode or references Copilot CLI for AI-assisted coding, file editing, or shell commands.

Use when the user asks to run Kimi CLI in non-interactive mode or references Kimi for AI-assisted coding or agent tasks.

Use when the user asks to run Kiro CLI in non-interactive mode or references Kiro for AI chat, shell translation, or agent management.

Use when the user asks to run OpenCode CLI in non-interactive mode (opencode run) or references OpenCode for AI-assisted coding tasks.

Use when the user asks to run Qwen CLI in non-interactive mode or references Qwen Code for AI-assisted coding tasks.

Use when evaluating complex systems, agent OS design, workflow engines, automation, HPC, infrastructure, distributed systems, protocols, organizations, division of labor, responsibility gaps, bypass paths, hidden state, or local compliance with unclear global ownership.

Use when coordinating multi-agent work, delegating tasks, managing agent teams, or making strategic decisions as team lead.

Use when reading papers, evaluating AI4S systems, reviewing scientific claims, judging benchmark or dataset results, checking claims about understanding/discovery/reasoning/autonomy, or repairing inflated scientific claims.

Use when the user asks to show notes, create stickies, or read existing Stickies notes on macOS.

Use when the user asks to be notified, alerted, or reminded via push notification.