model-compatibility

model-compatibility is a cursor rule for Cursor from madebyaris/advance-minimax-m3-cursor-rules. It costs 27 tokens per session (955 once invoked), scanned A, original, MIT.

A guide for choosing models and managing prompts, tools, reading, and context across different coding-agent models.

In plain words
What is it for?
Model selection, long-context tasks, multimodal work involving images or video, tool use, and keeping instructions consistent across models.
Why use it?
It helps the agent select an appropriate model for tasks such as large multi-file changes or visual work and avoid relying on outdated assumptions.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Codex.

Good fit Model selection, long-context tasks, multimodal work involving images or video, tool use, and keeping instructions consistent across models.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/madebyaris/advance-minimax-m3-cursor-rules/model-compatibility
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.

Clone the repo
git clone --depth 1 https://github.com/madebyaris/advance-minimax-m3-cursor-rules

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 model-compatibility

README.md
[![agentmods](https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/model-compatibility/github.svg)](https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/model-compatibility)
Your own site
<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/model-compatibility"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/model-compatibility/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for model-compatibility

Your own site · 80×15
<a href="https://agentmods.dev/rules/madebyaris/advance-minimax-m3-cursor-rules/model-compatibility"><img src="https://agentmods.dev/badge/rules/madebyaris/advance-minimax-m3-cursor-rules/model-compatibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 955 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00027 $0.00955
Opus 5 $0.00014 $0.00477
Sonnet 5 $0.00005 $0.00191
Haiku 4.5 $0.00003 $0.00096

Measured 9d ago against content hash 4de12d7d31e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

model-compatibility 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 9d 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/model-compatibility.mdc · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Transferable Agent Behavior (M3-first, model-resilient)

This repo is tuned for MiniMax M3 first. M3 is a generational shift: 1M-token MSA context, native multimodal input (text, image, video), and higher agentic and coding benchmarks.

The purpose of this file is to define the transferable execution behavior the agent should copy across models: tool-first work, read-before-edit discipline, short prompts, and context-aware problem solving that also maps well to strong GPT/Codex/Composer-style coding agents.

Prompt Hierarchy

Treat the current environment as the source of truth:

  • system instructions and exposed tools win
  • always-on rules should stay short, durable, and canonical
  • requestable rules should carry runtime-specific guidance
  • user instructions still define the task

Do not assume an older rule or prompt shape is still valid just because it appears in this repo. Prefer a single always-on execution spine over duplicated policy spread across multiple files.

Model Selection

Need Default Why
Long context (multi-file refactor, transcript analysis, large retrieval pack, full-repo synthesis) MiniMax-M3 1M-token MSA context
Visual-fidelity work, design parity, error UI triage, screenshot-driven dev MiniMax-M3 Native multimodal input (text, image, video)
Deep agentic / coding (SWE-Bench-class tasks, long-horizon planning) MiniMax-M3 Higher agentic and coding benchmarks
Anything where the user asks for "frontier" by name MiniMax-M3 Positioned as the new frontier default

When the active model is not M3 (for example composer-2.5, GPT, or Claude), the always-on core continues to apply — tool discipline, read-before-edit, scope control, solver loop, status taxonomy. The M3-specific sections (long-context discipline, multimodal input discipline) become inert, and the agent must not promise multimodal or 1M-context behavior. Confirm the model's actual capabilities from the current runtime before relying on them.

Read the full file on GitHub · 79 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. 9d ago First seen · 79 lines · 27 tokens per session scan A 4de12d7d31e0

Subscribe to this mod's changes

model-compatibility is a cursor rule published in the GitHub repository madebyaris/advance-minimax-m3-cursor-rules (125 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 955 once invoked, about $0.0001 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.