claudish-usage

Name: claudish-usage
Availability: InStock
Author: MadAppGang

Routes Cubist CLI tasks through sub-agents to prevent context window pollution.

278|29|Updated Nov 4, 2025

Search Tags:#OpenRouter #proxy #claudish #agent-delegation #external-models

Ready to run

npx skills add https://github.com/MadAppGang/claude-code --skill claudish-usage-madappgang

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: claudish-usage
Source: https://github.com/MadAppGang/claude-code/tree/main/shared/skills/claudish-usage
Command: npx skills add https://github.com/MadAppGang/claude-code --skill claudish-usage-madappgang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

Core Features & Use Cases

Agent delegation patterns and decision tree to route Claudish tasks
Step-by-step agent selection for coding, review, and architecture tasks
File-based instructions to minimize prompt size and maintain context

Quick Start

Always route external-model tasks through a sub-agent; run claudemem status and then claudemem search for model recommendations when external models are needed.

Frequently Asked Questions about claudish-usage

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I run Claude models through OpenRouter using Claudish CLI?▼

Claudish CLI enables running Claude Code with external models like Grok, GPT-5, Gemini, and MiniMax via OpenRouter. Always delegate Claudish tasks to a sub-agent rather than executing directly in your main context to prevent context window pollution and maintain clean agent isolation.

When should I use agent delegation instead of running Claudish directly?▼

Route all Claudish and external-model tasks through sub-agents by default. Run Claudish directly in main context only when you explicitly request it. Sub-agent delegation prevents context contamination, maintains workflow clarity, and follows the mandatory delegation pattern for OpenRouter proxy usage.

How do I select the right external model for my task with Claudish?▼

Use claudemem status to check available models, then claudemem search to find model recommendations matching your task needs. The agent selection matrix in Claudish guides routing for coding, review, and architecture work across OpenRouter's available models.

What file-based instruction patterns does Claudish use to minimize context size?▼

Claudish supports file-based instructions that keep prompts lean and maintain context efficiency. Instead of embedding large directives inline, reference external instruction files to reduce token consumption while preserving full workflow context in sub-agents.

Can I use Claudish with models other than Claude through OpenRouter?▼

Yes. Claudish CLI routes to OpenRouter proxy, enabling access to Grok, GPT-5, Gemini, MiniMax, and other external models. Always delegate these cross-model tasks to sub-agents and follow agent selection guidance for optimal routing based on task type.

What happens if I run Claudish in my main context instead of delegating to a sub-agent?▼

Running Claudish directly in main context risks context window pollution and violates the mandatory sub-agent delegation pattern. Claudish is designed for sub-agent execution only; direct execution degrades isolation, reduces context efficiency, and breaks the intended workflow decision tree.