Michael's operating + emotional coach. Operational mode — daily startup/shutdown, weekly review, pomodoro, inbox capture, daily notes (auto-loads in ~/ws/notes). Emotional/decision mode (Joe Hudson style) — use on "coach me"/"joe coach", stuck/looping/overthinking, harsh self- or other-judgment, a binary either/or decision that won't resolve, or fear, shame, loneliness, anxiety, burnout, or grief, when Michael wants to be met in a feeling rather than handed advice. Not for clinical crises (refer out).
Use when creating or processing Todoist tasks, triaging inbox items, doing daily task review, calibrating Todoist triage behavior, or turning corrections into reusable preferences. Routes to operations (CLI actions) vs calibrated triage (policy, context recovery, preference memory, evals). Trigger this whenever the user asks what to do with Todoist items, wants better task triage, or is refining how Todoist decisions should work.
Run real Deep Research across ChatGPT, Claude, and Gemini in parallel via the user's own logged-in browser (Chrome extension, zero API cost), save each original report to Notion, then synthesize. Use whenever the user wants a "deep dive", "deep research", a thorough multi-source investigation, or to research a topic across the models and compare what each finds. Drives the paid subscription products, NOT the API. NOT for single-fact lookups or ordinary web search — use web-search for those.
Use when setting up, auditing, or improving AI agent infrastructure in a repo — AGENTS.md/CLAUDE.md files, linters, architectural constraints, feedback loops, context tiering, agent specialization, or entropy management. Also triggers on "harness engineering", "agent-friendly repo", "make my repo work well with coding agents", "set up my repo for agents", or "why is my agent struggling".
Interactive Todoist triage with preference learning. Use when the user says "triage", "process my inbox", "clean up tasks", "triage my todoist", "file these captures", or mentions inbox zero. Also use when the user has a batch of raw items (voice notes, links, ideas) that need classifying and routing to Todoist projects or Obsidian. Runs an interactive confirm/correct loop that learns your routing preferences over time.
Use when the user asks to save session context, identify the current session or thread, create a resumable handoff, or prepare a Todoist/note summary that must include the working directory and session id. Works across Codex and Claude Code by detecting runtime-specific session identifiers and normalizing them into one summary.
Persistent interactive Playwright sessions for fast iterative UI debugging — js_repl lane in Codex, tmux-REPL lane in Claude Code. Use whenever driving a browser incrementally beats edit-script-rerun loops, and ALWAYS consult the no-foreground policy before any Playwright launch.
Create or update a reproducible local Docker test environment for an existing codebase, then launch and verify it with real HTTP / user-facing checks. Use when the user wants to dockerize a repo, replace managed dev infrastructure with local containers, stand up a preview stack, or prove a codebase actually runs locally in Docker.