Route Feedback — AI skill for Claude Code
Tell decision-router which model the last routed task should have used.
How to install Route Feedback
Installs to ~/.claude/skills/ruivalim-decision-router-route-feedback/SKILL.md
mkdir -p ~/.claude/skills/ruivalim-decision-router-route-feedback && curl -fsSL https://raw.githubusercontent.com/Ruivalim/decision-router/HEAD/commands/route-feedback.md -o ~/.claude/skills/ruivalim-decision-router-route-feedback/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Route Feedback does
description: Tell decision-router which model the last routed task should have used argument-hint: allowed-tools: Bash(decision-router feedback:*), Bash(npx -y decision-router@latest feedback:*)
Record feedback for the most recent decision. The argument must be a single model id made only of letters, digits and `._/:-`; if it is empty or anything else, ask which model instead of running anything.
decision-router feedback last $ARGUMENTS
Run it as a plai
Alternatives in AI
- Create Module — Scaffold a fully-typed module with controller, service, router, schema, and model files 325 ★
- LLM Task Orchestrator — Top AI Router 2026: Split Codex for Quick Code & Claude for Complex Refactoring 115 ★
- Use Crew Gateway — Route an OpenAI/Anthropic-compatible client through the portable farmd control plane's virtual crew model, for 67 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Route Recommend
Ask decision-router which model fits a task, without running it
Jev Router
Route to the cheapest model in claude code for your task using jev-router
Model Router
Claude Code skill: route each task to the cheapest Claude model that can do it well
Jev Agent Tools
Open-source single-file tools for AI agent builders, powered by Jev (TypeSafe AI's decision model): a loop det
Skill Router
Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90%
Claude Auto Router
Auto-route Claude Code prompts to the cheapest model that can handle them. Save 3-5x on tokens. One-command in
Related Agents
GPT 5.6 Sol
General-purpose agent that runs on GPT-5.6-Sol (routed through the shunt gateway to the ChatGPT/Codex subscrip
GPT 6 Luna
General-purpose agent that runs on GPT-6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscript
Model Router
Use when dispatching work and unsure which model tier to use — returns a recommended model and effort level ba