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/Mnemosyne-OS/Mnemosyne-Neural-OSWrote 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/mnemosyne-os/mnemosyne-neural-os/cursorrules)<a href="https://agentmods.dev/rules/mnemosyne-os/mnemosyne-neural-os/cursorrules"><img src="https://agentmods.dev/badge/rules/mnemosyne-os/mnemosyne-neural-os/cursorrules/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/mnemosyne-os/mnemosyne-neural-os/cursorrules"><img src="https://agentmods.dev/badge/rules/mnemosyne-os/mnemosyne-neural-os/cursorrules.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 | $0.00633 | $0.00633 |
| Opus 5.5 | $0.00253 | $0.00253 |
| Sonnet 5.5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
cursorrules 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 2mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mnemosyne Module — AI Governance Rules (Liquid Glass Design System)
Generated by MnemoForge CLI · https://github.com/Mnemosyne-OS/Mnemosyne-Neural-OS
You are an AI agent building the module: {{MODULE_NAME}} This module is part of the Mnemosyne Neural OS ecosystem by XPACEGEMS LLC.
DESIGN SYSTEM: Liquid Glass
All UI must follow the Mnemosyne "Liquid Glass" aesthetic:
- Surfaces: Translucent backgrounds (
bg-surface/60),backdrop-blur-md - Borders: Subtle (
border-border/50), never solid hard borders - Accents: Violet spectrum (
violet-400,violet-500,purple-400) - Typography: Inter or system-ui, sharp tracking for headings
- Shadows: Layered glow effects (
shadow-violet-500/20) - Dark-first: Design in dark mode; light mode is optional
STYLING RULES
- Tailwind CSS ONLY — No inline
style={{ }}unless binding to a dynamic JS value - No arbitrary magic numbers — Use Tailwind spacing scale
- Framer Motion for ALL transitions:
- Entry:
initial={{ opacity: 0, scale: 0.95 }}/animate={{ opacity: 1, scale: 1 }} - Use
<motion.div layout>for list animations - Hover:
whileHover={{ scale: 1.02 }}
- Entry:
- Micro-animations on interactive elements — hover glow, pulse, or scale
- Responsive — Mobile-first with
sm:,md:,lg:breakpoints
ARCHITECTURE RULES
- State: Zustand only. No Redux, no Context API for shared state.
- TypeScript: Strict mode. No
any. All props typed with interfaces. - Icons:
lucide-reactexclusively for UI metaphors. - Components: Decompose into
components/subdirectory — no 300-line monoliths. - No placeholders: Every generated file must be complete and deployable.
- Imports: Named exports preferred over default exports.
QUALITY STANDARD
Every component must make a developer say:
"This looks like a Sovereign Command Center from 2030."
If it looks like a generic SaaS dashboard template, you have failed.
MNEMOSYNC INTEGRATION (Optional)
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.
- 2mo ago First seen · 56 lines · 633 tokens per session scan A b079a4b43d73
cursorrules is a cursor rule published in the GitHub repository Mnemosyne-OS/Mnemosyne-Neural-OS (20 stars, last pushed today), licensed MIT. It adds 633 tokens to every session, about $0.0025 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
dreamd-recall
Search dreamd at the start of a task and quote a hit. Append when the user corrects you or states a decision.
agents
A project rulebook that mirrors the instructions in AGENTS.md and points to the project's development, task-process, and architecture documents. It also identifies where the project's reusable skills are stored.
teams
A Cursor rule for building teams of AI agents with the Agno framework. A team is a group of agents with different roles, such as researching and writing, that collaborate on one task.
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.