Declare and refresh a LOCAL MIRROR — a one-way local copy of a chosen zone of an internal tool (Notion today) replicated into this brain's vault as Markdown, so the LOCAL RAG can search and cite it OFFLINE. A mirror is a 'synchronized source' kept locally: copied once, then refreshed on demand. Use when the user wants…
Switch the ACTIVE UNIVERSE of this brain, or create a new one (ADR 0034). A universe is a soft retrieval scope (e.g. successive employers, clients, spheres): when you work one universe, searches default to its notes plus your cross-cutting ones. Use when the user wants to switch / change / set the current universe /…
Fan-out/fan-in architecture to pull in the DELTA of external sources (Slack, Google Drive / transcripts, Calendar, mail…) via parallel READ-ONLY sub-agents. Internal technical reference — it's the engine of Phase 2 of the main flow (question → sync sources in background) and of a possible morning briefing. Not a user…
Manage setmac releases, semantic-release versioning, signing, notarization, and packaged app hotfixes. Use when working on GitHub Actions release workflows, changelog/version bumps, DMG or standalone CLI artifacts, Gatekeeper issues, or launch failures in shipped builds.
Systematic evidence-based debugging using runtime logs. Generates hypotheses, instruments code with NDJSON logs, guides reproduction, analyzes log evidence, and iterates until root cause is proven with cited log lines. Use when the user reports a bug, unexpected behavior, or asks to debug an issue.
Use when preparing or publishing a kitup release, including release branch preparation, version bumps, manual PR handoff, manual tags, GitHub Actions publishing, and public smoke checks.
Use when integrating the kitup SDK into a CLI that ships a bundled Agent Skill and needs to install it on local agent hosts. Also use when wiring install flags, optional status or uninstall, or the Go Cobra adapter.
Use when the user asks for a multi-agent discussion, panel review, multi-agent review, or multi-agent research session with role selection, round control, and template-based orchestration.
Runtime helper for autonomous-research-loop ledgers plus headless drive, host-owned multi-agent panel phases (--panel on, auto, or off), and the default cross-platform force-loop kit (bootstrap/start/drain with enforce/hard/notify defaults). Use to initialize, append, validate, inspect, smoke-test, drive, or…
Run bounded autonomous research iterations with evidence gates, recovery ledgers, and optional cross-agent handoffs; prefers host-owned multi-agent panel with single-path drive primary; scripted force-loop defaults (Goal Focus enforce, hard goalpriority, notify ON). Use when the user asks to continue research…