model-routing

A set of rules for choosing which Cursor coding agent should handle development work. It classifies a task, such as debugging, documentation, or prototyping, before delegation.

In plain words
What is it for?
Routing plans, reviews, complex development, debugging, documentation, prototypes, and simple development tasks through the project's Cursor agent system.
Why use it?
It gives development tasks a consistent route to an appropriate agent and model. The selected route does not expand the task's permissions or remove the need for validation.

Cursor rule

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/vinilana/invokta/model-routing
Clone the repo
git clone --depth 1 https://github.com/vinilana/invokta
Per session 173 This file is loaded in full into every session.
When invoked 173 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 $0.00173 $0.00173
Opus 5 $0.00086 $0.00086
Sonnet 5 $0.00035 $0.00035
Haiku 4.5 $0.00017 $0.00017

Measured 2d ago against content hash cf2de31aaa66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-routing 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 2d 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.

examples/cursor-agent-routing-engine/cursor-config/rules/model-routing.mdc · 24 lines

What it actually says

Before delegating development work, classify it as exactly one of these use cases:

  • plan
  • review
  • complex-development
  • debug
  • documentation
  • prototype-development
  • simple-development

Call the MCP tool developer-work_route-cursor-task with that useCase. Invoke the custom subagent named by agent.invocation and give it a self-contained task. Keep read-only agents read-only. Use fallbackModel only when the primary model is unavailable for the current account, region, or organization policy.

The routing result selects an agent and model; it does not authorize broader scope, destructive actions, or skipped repository validation.

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. 2d ago First seen · 24 lines · 173 tokens per session scan A cf2de31aaa66

Subscribe to this mod's changes

model-routing is a cursor rule published in the GitHub repository vinilana/invokta (120 stars, last pushed 8d ago), licensed MIT. It adds 173 tokens to every session, about $0.0009 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 2026-08-30.