Use when someone asks to build, create, design, optimize, or audit a Claude Code subagent (an .claude/agents/*.md file), says "make me an agent", "build a subagent", "audit my agents", or wants help deciding whether something should be an agent at all. Runs a decision gate and Discovery Interview before writing files.
Use to design and launch a Claude Code agent team (2–5 specialized agents that share a task list, talk peer-to-peer, work in parallel). Triggers — "build an agent team", "design a team of agents", "set up a Claude agent team", "I need a multi-agent crew", "create an agent team for X", "spin up a team of teammates", "build me a Claude team", or `/agents-team-builder`. Sibling of `/skill-builder`, `/agent-builder`, `/routines-builder`, `/workflow-builder`, `/plugin-builder` — this one is the agent-teams specialist.
Use when someone asks for an AIOS audit, asks to score their setup against the Four Cs, or says "is my AIOS working" / "audit my setup" / "find gaps in my AIOS" / "/aios-audit". Produces a Four-Cs scoreboard with top-3 fixes ranked by leverage.
Use PROACTIVELY whenever the user is working something OUT OF THEIR HEAD rather than asking a quick question — mulling or scoping a plan/design/decision, describing how they do something, or floating a half-formed idea to capture. Natural signals: "I've been thinking about…", "I have an idea for…", "I want to build/plan/figure out…", "let me think this through", "help me scope this", "here's how I do X". Also the explicit "grill me", "interrogate me", "stress-test this", "/grill-me". One-question-at-a-time extraction into a durable doc. SAFETY: unless they explicitly asked to be grilled, OFFER first and wait for yes — never silently launch a long interview on a quick question.
Use when the user asks to design, build, optimize, or audit Claude Code HOOKS — event-driven shell commands in settings.json that fire on SessionStart, PreToolUse, PostToolUse, Stop, etc. Triggers — "build a hook", "add a hook", "run X every time I edit/commit/start a session", "block tool X when…", "audit my hooks", or `/hooks-builder`. Sibling of `/skill-builder`, `/agent-builder`, `/routines-builder`, `/agents-team-builder`, `/plugin-builder` — this one is the event-driven-local specialist (the hooks lane `/routines-builder` hands off to).
Use weekly to find and ship one new automation. Walks the 3Ms interview — Mindset (find the candidate) → Method (scope one) → Machine (build it). Trigger on "let's level up", "what should I automate next", "find me leverage this week", or as a Friday ritual. One run = one shipped artifact, or a logged decision to stop.
Multi-LLM auto-router. Your main assistant orchestrates and routes a sub-task to a different model ONLY when that model fits the job better; the user talks to one assistant the whole time. The roster is yours to fill in. Fires automatically when a routing rule matches. NO-SELF-REVIEW LAW: when the user asks you to "check / review / verify / sanity-check / second-opinion" ANY work YOU just produced, route the review to a model from a DIFFERENT lineage if one is on the roster. Triggers: "check your work" · "review what you just did" · "is this right?" · "second opinion" · "sanity check" · "double-check" · "make sure this works".
Use on Day 1 of an AIOS install, when someone says "set me up", "onboard me", "let's get started", "fill in my AIOS", or has just cloned the kit. Combined wizard — runs the 7-question intake AND scaffolds the Day-1 file set at the end. Idempotent — re-run any time; the working aios-intake.md resets to placeholders after each run (your durable answers live in context/).