"Token-saver router: elige modelo (cheap/default/pro) y usa
Scanned 9/7/2026
Install to Claude Code
npx -y skills add modbender/skill-library-mcp --skill arya-model-router --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Arya Model Router?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/modbender-arya-model-router)More formats (shields.io, HTML) on the badges page.
---
name: arya-model-router
description: "Token-saver router: elige modelo (cheap/default/pro) y usa
sub-agentes para tareas pesadas. Incluye compresión/briefing opcional."
---
# Arya Model Router (Token Saver)
Router de modelos para OpenClaw: decide cuándo usar un modelo barato vs uno más fuerte, reduciendo costo y tokens.
## Objetivos
- Mantener el chat diario barato.
- Escalar a un modelo superior solo cuando la tarea lo amerite.
- Evitar pasar contexto enorme al modelo caro: primero crear un **brief**.
## Enfoque
- El agente principal (main) se mantiene en un modelo económico.
- Para tareas pesadas, el router recomienda (o ejecuta) **sub-agentes** con un modelo superior.
## Niveles (por defecto)
- cheap: `openai/gpt-4o-mini`
- default: `openai/gpt-4.1-mini`
- pro: `openai/gpt-4.1`
## Uso (conceptual)
- "Router: responde esto en modo cheap" (forzado)
- "Router: analiza esto" (auto)
## Archivos
- `router.py`: clasificador + reglas
- `rules.json`: reglas editables
- `README.md`: documentación completa
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
Audit, review, clean up, and prune Codex memories. Use when the user asks about ~/.codex/memories, stale or noisy memories, memory pollution, cross-repo rule leakage, sensitive memory contents, memory config tuning, cleanup plans, or whether entries belong in memory, AGENTS.md, repo docs, skills, config, or deletion. Do not use for ordinary repo docs cleanup.