00-model-router

00-model-router is a cursor rule for Cursor from jonafrank/cursor-multi-model-config. It costs 539 tokens per session, scanned A, original, MIT.

A set of instructions that identifies the kind of coding task being requested and recommends a model from the active configuration.

In plain words
What is it for?
Use it to classify requests and choose a configured model for tasks such as planning, reasoning, refactoring, summarizing, compliance checks, or creating code.
Why use it?
It helps route planning, debugging, refactoring, summarization, and implementation requests according to their different needs.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/jonafrank/cursor-multi-model-config/00-model-router
Clone the repo
git clone --depth 1 https://github.com/jonafrank/cursor-multi-model-config

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 00-model-router

README.md
[![agentmods](https://agentmods.dev/badge/rules/jonafrank/cursor-multi-model-config/00-model-router.svg)](https://agentmods.dev/rules/jonafrank/cursor-multi-model-config/00-model-router)
Your own site
<a href="https://agentmods.dev/rules/jonafrank/cursor-multi-model-config/00-model-router"><img src="https://agentmods.dev/badge/rules/jonafrank/cursor-multi-model-config/00-model-router.svg" alt="Measured on agentmods" height="20"></a>
Per session 539 This file is loaded in full into every session.
When invoked 539 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00539 $0.00539
Opus 5 $0.00269 $0.00269
Sonnet 5 $0.00108 $0.00108
Haiku 4.5 $0.00054 $0.00054

Measured 4d ago against content hash 484e424a2ccb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

00-model-router scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/00-model-router.mdc · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Router

You have access to a model configuration system. When responding to user requests, identify the task type and recommend the appropriate model from the active profile.

Active Profile Reference

The current model profile is defined in .cursor/model-profiles/current-profile.json. Read this file to determine which models are configured for each task type.

Task Type Detection

Analyze the user's request to identify the primary task type:

Task Type Trigger Keywords/Patterns
planning "plan", "design", "architect", "structure", "how should I", "what's the best approach"
reasoning "why", "explain", "analyze", "debug", "what's happening", "understand"
refactor "refactor", "clean up", "improve", "optimize", "restructure", "rename"
summarize "summarize", "overview", "what does this do", "explain this code", "tl;dr"
long_context Large file operations, multiple files, entire codebase questions
compliance "review", "check", "validate", "security", "best practices", "standards"
creative "create", "build", "new feature", "implement", "write", "generate"
draft "quick", "draft", "sketch", "rough", "prototype", "poc"

Response Format

When you detect a task type, include a model recommendation at the start of your response:

📍 Task: [task_type] → Recommended model: [model_name]

If the user is already using the recommended model, you can omit this notice.

Profile Awareness

  • If the user mentions "quota", "rate limit", or "too expensive", suggest switching to the fallback or cost_minimized profile
  • If the user needs deep analysis or multi-file work, suggest the completeness profile
  • For batch operations, suggest cost_minimized profile

Model Selection Guidance

When recommending a model switch, explain why:

  • Speed: Some models are faster for quick iterations
  • Depth: Some models provide more thorough analysis
  • Cost: Some models are more cost-effective
  • Context: Some models handle larger contexts better

Read the full file on GitHub · 53 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 53 lines · 539 tokens per session scan A 484e424a2ccb

Subscribe to this mod's changes

00-model-router is a cursor rule published in the GitHub repository jonafrank/cursor-multi-model-config (5 stars, last pushed 8mo ago), licensed MIT. It adds 539 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.