Starlight-Intelligence-System

Codex-native /acos router for the Agentic Creator Operating System, content, creator, music, video, publishing, social, and ACOS workflow routing without loading all Claude command files. Use when prompts mention /acos, the installed /acos prompt shortcut, mobile alias acos:, Agentic Creator Operating System, ACOS, creator/content operations, content calendar, video, Suno/music, blog/social publishing, or creator OS auto-routing.

Codex-native Starlight Intelligence /si router for choosing local agent lanes, building handoff packets, and running explicit read-only fanout or council dispatch across Codex, Claude, Grok, Antigravity, OpenCode, DeepAgent, and image tools. Use when prompts mention /si, the installed /si prompt shortcut, mobile alias si:, starlight si, route, dispatch, fanout, council, which agent/tool, local CLI lanes, or Starlight multi-agent orchestration.

Codex-native Starlight /so orchestrator for Queen-enabled dispatch, durable packets, explicit fanout, verification plans, swarm loops, and multi-lane Starlight coordination. Use when prompts mention /so, the installed /so prompt shortcut, mobile alias so:, starlight so, Starlight Orchestrator, Queen role, orchestrator dispatch, Starlight Swarm, multi-agent routing, multi-lane dispatch, durable handoff packet, dispatch verification, or /so --fanout.

Scaffold a new agent profile under agents/ or verticals/, register it in AGENT_REGISTRY.md and AGENTS.md, and run conformance validation tests.

Distill a completed user interaction or multi-step workflow into a reusable agent skill (SKILL.md + helper script), registering it in skill-rules.json and SKILL_REGISTRY.md.

Use when dispatching the Hermes agent swarm for any multi-IS or complex task — routes to IS-specialist Hermes profiles, coordinates parallel execution, aggregates synthesis, and writes results to vaults. Default skill for Starlight Hermes, Starlight Orchestrator, and Hermes Claw.

Mandatory excellence gates for Grok+ACOS. verification-loop, santa-method, gstack-qa, plan-reviews, repo-mastery, cso, rules-distill. Never ship without evidence (gstack screenshots, metrics). Use on any build/suggest/lead task.

ACOS Grok bridge. SessionStart loads repo-mastery + excellence gates. PreToolUse enforces rules read + suggests harness (claude for plans). Uses gstack for QA, verification-loop/santa-method. Full .claude/ compat + native .grok/. Delegate via terminal when needed. Trigger: setup, harness, grok, excellence.

Automatically detect tasks suited for delegation to other agent harnesses (Claude Code as canonical, agy/antigravity, gemini, cursor, etc.). Leverage shared .claude catalog (skills, commands, agents, hooks, junctions for agy). Embody Frank DNA. Output exact delegation commands (e.g. claude -p "injected rules + task" --cwd ...). Auto-utilize by shelling harness CLIs with full context from rules/catalog. Combine with repo-mastery for ecosystem tasks. Suggest/lead by choosing best harness or running in parallel. Grok .grok personal excellence seeds only (core to others).

Master ACOS, FrankX, Starlight-Intelligence-System, arcanea, claude-code-config and full starlight/repos ecosystem. Architecture, skills/hooks/MCP map, harness integration points. Read CLAUDE.md/AGENTS.md/GROK.md first. Use MCPs (github, fs-starlight), gstack, subagents, grep, terminal. Excellence gates required. Trigger: repo, ACOS, ecosystem, mastery, cross-repo.

Load when working at the Starlight substrate layer — authoring SIP, forging alliances, spawning verticals, or generating SIP-compliant attestations. Not for vertical-specific work (use the vertical's SKILL.md).

Ops health monitor for the machine substrate. Checks Memory Bus, brain_watchdog, Voice Operator, dashboard, audit-log freshness, and scheduled tasks. Cross-cutting skill that any repo can invoke when daemons feel off or before starting a heavy work session.

House-tier skill auto-activates when working inside verticals/crypto-intelligence/alloc/ or invoking any /crypto-alloc-* command. Enforces R5 clause, Kelly-derived sizing, and concentration stress-testing.

House-tier skill auto-activates when working inside verticals/crypto-intelligence/defi/ or invoking any /crypto-defi-* command. Enforces R5 clause, yield deconstruction, and oracle manipulation audits.

House-tier skill auto-activates when working inside verticals/crypto-intelligence/macro/ or invoking any /crypto-macro-* command. Enforces R5 clause, correlation auditing, and macro regime mapping.

House of On-Chain skill. Auto-activates on /crypto-onchain-* commands or work within verticals/crypto-intelligence/onchain/. Enforces R5 non-advisory clause inline, chain-data source citation, mechanism-context grounding, named output artifact discipline.

House-tier skill auto-activates when working inside verticals/crypto-intelligence/res/ or invoking any /crypto-res-* command. Enforces R5 clause, tokenomics auditing, and founder diligence.

Vertical-tier skill auto-activates when working inside verticals/crypto-intelligence/ or invoking any /crypto-* command. Enforces R5 non-advisory clause, voice (architect), refusal patterns, composition-with-Wealth-IS rules, and sovereignty discipline.

House-tier skill auto-activates when working inside verticals/crypto-intelligence/sov/ or invoking any /crypto-sov-* command. Enforces R5 clause, geodistribution checks, and custody segregation.

Use when you need to find, retrieve, or research anything across vaults, repos, or the web — executes semantic search with full provenance, deduplicates across sources, flags contradictions, and returns ranked results sourced to the exact vault atom, file, or URL. Default skill for Starlight Hermes; callable by all agents.

Require explicit user confirmation before any Claw mutates user files outside ~/.starlight/. Produces a plan first; mutations are never the default. Fires on all Claws with filesystem:write_user permission. Default skill for Starlight Sentinel and Bootstrap Claw.

Gate every mutation request against the Claw's declared permission surface — fires before any write to filesystem, vault, or external system. No Claw bypasses this gate. Default skill for Starlight Sentinel and every Claw that carries filesystem or sis_vaults write permissions.

Enforce vault privacy boundaries on every export — only content explicitly marked public leaves the local vault. Prevents accidental private data exposure through attestation records, platform exports, or Creator Claw outputs.

Scan any export, file, or vault batch for credentials, API keys, tokens, and sensitive data before they leave the local machine. Fires automatically on all Claw export operations. Default skill for Starlight Sentinel and Attestation Claw.

Load when working inside the <DOMAIN> vertical. Not for substrate-level work (use Starlight's SKILL.md) and not for sister verticals. This is a Domain Sub-Stack — wraps 4-7 sub-systems composed under one sovereign owner.

The <SUB-SYSTEM> skill inside the <DOMAIN> Domain Sub-Stack. Loads when any /<SLUG>-* command fires or when <SUB-SYSTEM> keywords are detected. Carries the research-grounded protocol this sub-system runs.

Vertical-tier skill for Crypto Intelligence Domain Sub-Stack. Auto-activates inside verticals/crypto-intelligence/ or on /crypto-* commands. Enforces R5 non-advisory clause, voice (architect), refusal patterns, composition with Wealth IS umbrella per Board 2026-05-17. Loads verticals/crypto-intelligence/SKILL.md wrapper for full doctrine.

Catalogs, scaffolds, and audits the per-repo tech stack across every brand (Arcanea, FrankX, Business, Starlight, verticals). Four verbs — audit (walk repos + emit constellation), scaffold (drop STACK.md template into a target repo), assign (bind tools to substrate/reasoning/coding/research/ops tiers), diff (surface drift between STACK.md intent and reality from .mcp.json + .claude/ + settings.json + installed CLIs). Use this skill whenever the user mentions stack architecture, repo inventory, "which AI assistant for which repo", custom GPTs, MCP routing across brands, browser workspaces per project, or asks "do we have a clean view of our tech stack". Default skill for the Starlight Architect when the question spans repos rather than a single one.

Disk audit and dedup-hint skill. Reports repo sizes, oversized files, worktree bloat, and surfaces candidates for archival/cleanup. Cross-cutting machine-layer skill, sibling to /pp and /heart.

Use when synchronizing intelligence, state, or knowledge across the FrankX ecosystem — ensures consistency and coherence across ACOS, Arcanea, AI-Ops, and Starlight. Default skill for Starlight Orchestrator and Starlight Prime.

Use when operations span multiple FrankX ecosystem repositories — bridges Starlight understanding, references, and coordination across ACOS, Arcanea, AI-Ops, and other connected repos. Default skill for Starlight Orchestrator and Starlight Prime.

Use when sending or receiving cross-system communications — manages the Starlight Transmission system that lets intelligence flow between Starlight, ACOS, Arcanea, and AI-Ops. Default skill for Starlight Orchestrator and Starlight Prime.

Use when connecting Starlight to external systems, APIs, or MCP servers — provides a standardized way to integrate with the outside world via the universal connector pattern. Default skill for Starlight Orchestrator and Starlight Architect.

Use when making or advising on decisions with multiple options — provides structured decision-making frameworks that ensure decisions are rational, well-documented, and revisitable. Prevents decision paralysis and gut-only decisions. Default skill for Starlight Navigator and Starlight Prime.

Use when analyzing recurring behaviors, identifying trends, or spotting anti-patterns across code, architecture, strategy, content, or behavior. Distinguishes patterns (good recurring solutions) from anti-patterns (recurring problems). Default skill for Starlight Sage and Starlight Sentinel.

Use when reasoning about strategy, long-term direction, trade-offs, or roadmaps — provides structured analysis that balances ambition with reality, near-term gains with long-term value, and competing priorities. Default skill for Starlight Navigator and Starlight Prime.

Use when reasoning about architecture, holistic analysis, feedback loops, or emergent behavior — sees components, connections, feedback loops, and emergent properties to prevent the tunnel vision of analyzing parts in isolation. Default skill for Starlight Architect and Starlight Prime.

Use when designing daily capture, note-taking, or personal-knowledge operations — defines the discipline of when, what, and where to capture. Tool-agnostic; the practice survives tool changes. Default skill for Starlight Second Brain.

Use when saving context for future sessions or session handoffs — captures decisions, progress, pending work, and relevant state into persistent storage that can be restored. Default skill for Starlight Orchestrator and Starlight Sage.

Use during periodic review sessions (weekly/monthly/quarterly) to turn raw captures into reusable frameworks — patterns captured ≥3 times become named, documented, ready-to-reuse frameworks. Default skill for Starlight Second Brain.