Toggle the Raven model router. /router enables advisory Haiku-subagent delegation for simple prompts, /router off disables it, /router status shows the current mode. The primary session model is never changed — that is set only via /model.
Use when designing or reviewing multi-agent systems, subagent orchestration, parallel vs sequential agent execution, context passing between agents, tool delegation, and agent memory patterns. Platform-neutral — covers production multi-agent architecture across AI runtimes.
USE PROACTIVELY whenever the user asks for: planning, design, architecture decision, tradeoff analysis, comparing approaches, strategy, system design, refactor scope, deciding what to build, or any non-trivial request needing clarification. Also USE when user says 'should I', 'how do I approach', 'plan this'…
Universal database orchestrator. Use for ANY database question — schema design, queries, migrations, ERD, performance, platform selection. Routes to specialist sub-skills for Postgres and vector DBs. Enforces SQL-file discipline and ERD requirements via agent chaining. Spawns search agent ONLY when explicitly asked…
Use for ANY platform, library, or domain with no curated specialist skill. Reads securitylog.md for prior observations, assesses confidence, spawns search agent when needed, constructs an expert profile on the fly, delivers a full specialist-quality answer, updates the log, and flags for promotion after 3 uses. The…
Use when writing code, adding imports, creating files, committing, or receiving ANY task prompt. First layer of intelligence — reads every prompt, detects intent, routes to the right skill or agent automatically. Always active.
Use when adding or updating documentation. Enforces docstrings on all functions, updates architecture.md on structural changes, and keeps changelog current. Run before any PR merge.
Use when deep expertise is needed — complex architecture decisions, hard debugging, system design, or any task requiring world-class specialist commitment. Activates L99 mode — no hedging, no "it depends", no disclaimers.
Use when planning any new feature, module, service, or refactor. Extends Claude's Plan agent with Giggso architecture-first rules. Forces dependency mapping, file structure, and manifest compliance before any code.
5 2d agoA47 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: