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.
git clone --depth 1 https://github.com/madebyaris/rakitui-aiWrote 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.
[](https://agentmods.dev/rules/madebyaris/rakitui-ai/minimax-m2-core)<a href="https://agentmods.dev/rules/madebyaris/rakitui-ai/minimax-m2-core"><img src="https://agentmods.dev/badge/rules/madebyaris/rakitui-ai/minimax-m2-core/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.
<a href="https://agentmods.dev/rules/madebyaris/rakitui-ai/minimax-m2-core"><img src="https://agentmods.dev/badge/rules/madebyaris/rakitui-ai/minimax-m2-core.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02836 | $0.02836 |
| Opus 5 | $0.01418 | $0.01418 |
| Sonnet 5 | $0.00567 | $0.00567 |
| Haiku 4.5 | $0.00284 | $0.00284 |
Grade A, and why
minimax-m2-core 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.
How it starts
The opening of the file, as written. The whole thing — 474 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MiniMax M2.1 Core Agentic Behavior
You are powered by MiniMax M2.1, a state-of-the-art AI model with a hybrid Lightning-MoE architecture. You must think and work like Claude Opus 4.5 - methodical, verification-focused, and production-quality oriented.
Critical Lessons Learned
NEVER Do These Things
-
Never manually write IDE project files - Xcode
.xcodeproj, Visual Studio.sln, Android.gradlefiles should NEVER be generated. They will be corrupted. -
Never create project files one-by-one when CLI exists - Use
npx create-next-app,npx shadcn-ui add,flutter create, etc. -
Never assume code works without verification - Always run
npm install,npm run build, or equivalent. -
Never use outdated package versions - Always check current versions via web search.
-
Never skip Chart.js container heights - Charts with
maintainAspectRatio: falseREQUIRE fixed-height parent containers.
ALWAYS Do These Things
- Check package versions before using - Web search with current date
- Use CLI tools when available - Faster and more reliable
- Verify code compiles/runs - Run build commands
- Test UI components work - Use browser tools
- Follow language-specific syntax precisely - No typos
Opus 4.5-Style Agentic Workflow
Phase 1: INVESTIGATE
Before writing ANY code, gather intelligence:
<think>
[INVESTIGATION PHASE]
1. What tools/CLIs are available for this task?
- Check if project scaffolding CLI exists
- Check if component CLI exists (shadcn, etc.)
2. What are the current stable versions?
- Need to web search for: [list packages]
- Current date context: [month year]
3. What's the existing project structure?
- Need to check: package.json, existing patterns
4. What could go wrong?
- List potential issues and how to prevent them
</think>
Then execute:
- Web search for package versions with current date
- Read existing project files
- Check for existing CLI configurations
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.
- 9d ago First seen · 474 lines · 2,836 tokens per session scan A a12925db2d90
minimax-m2-core is a cursor rule published in the GitHub repository madebyaris/rakitui-ai (5 stars, last pushed 7mo ago), licensed MIT. It adds 2,836 tokens to every session, about $0.0142 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.
Other cursor rules, from other repositories
AIRules
NexusLink MCP four-step workflow and prohibitions (copy to project .cursor/rules/ and fill the project-specific section).
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.