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.
npx agentmods add rules/sandraschi/virtualization-mcp/architectgit clone --depth 1 https://github.com/sandraschi/virtualization-mcpWhat 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 | $0.01196 | $0.01196 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade C, and why
architect scanned grade C with 1 finding 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **FORBIDDEN**: `&&`, `||`, `mkdir -p`, `rm -rf`, `cp -r`. This is a copy
94% identical to architect — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛠️ System Context & Environment
- Root Directory:
D:/dev/repos - Owner/GitHub:
sandraschi - Hardware: Local RTX 4090 (24GB) + 64GB RAM | OCuLink-optimized.
- Inference: DeepSeek-R1-Vibe (32B Reasoning Distill).
- Integrations: Unity, Blender, Calibre, Plex, and others. See
D:\Dev\repos\mcp-central-docs\integrations\README.md(or mcp-central-docs/integrations/ in workspace).
🧠 Core Partner Mindset (Materialist/Reductionist)
- Zero-Inference Rule: Prioritize technical truth over agreement. Challenge sub-optimal logic.
- Anti-Gaslight: No mocks, no placeholders. All code must be functional.
- Implementation Lifecycle: During early prototype work, temporary placeholders must be explicit. Before release, every placeholder must be either implemented or return explicit
not_implementedplus clear UI Under construction labeling. - No Conversation Fluff: No emojis, apologies, or "rah-rah." Be academic and direct.
- Slop (LDDO) Prevention: High-density code only. Use early returns and guard clauses.
- Disciplined Programming: ZERO uncaught exceptions. Extensive try-except/try-catch blocks. No silent failures.
- Extensive Logging: Use proper
loggermodules. NO nakedprint()orConsole.Log()statements.
🔌 FastMCP 2.14.4 Engineering (Backend)
- Framework: Use FastMCP 2.14.4 and Python 3.13+.
- Pattern: Leverage
@mcp.tool()for side effects and@mcp.resource()for data loading. - Context Usage: Mandatory
ctx: Contextparameter to utilizectx.info()andctx.report_progress(). - Dialogic returns: Tool responses must be conversational (dialogic); support sampling and AI/agentic workflows per FastMCP 2.14+.
- Packaging: Create
.mcpbpackages in thedist/folder. All bundles must be dependency-free, containing extensive prompt templates and validmanifest.jsonexamples. - Deployment: Design for "Local-First" compatibility with the
sandraschiGitHub hub.
🎨 React & Tailwind Standards (Frontend)
- Architecture: Functional components with TypeScript interfaces. Avoid Enums; use Const Objects/Maps.
- Styling: Tailwind CSS ONLY. Use
cn()utility for conditional classes. No inline CSS. - Mobile-First: Responsive by default using
sm:,md:,lg:breakpoints. - Hooks: Logic must be encapsulated in custom hooks; keep UI components "Beautiful and Dumb."
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.
- yesterday First seen · 65 lines · 1,196 tokens per session scan C c8c62620c5e4
architect is a cursor rule published in the GitHub repository sandraschi/virtualization-mcp (14 stars, last pushed 3d ago), licensed MIT. It adds 1,196 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 94% identical to architect, differing in 1 line, and is treated as a copy.
Other cursor rules, from other repositories
architect
Global Architect rules for sandraschi's dev environment (Unity and other integrations, FastMCP, React). See mcp-central-docs integrations.
architect
Global Architect rules for sandraschi's dev environment (Unity, FastMCP, React).
architect
Global Architect rules for sandraschi's dev environment (Unity, FastMCP, React).
cursorrules
Robot control server. Do not move the physical robot without checking health first.
unity-performance
Cursor rule "unity-performance" from Common-ka/ai-agent-unity-rules, covering unity performance rules, update/fixedupdate/lateupdate, usage rules, object pooling (unityengine.pool) and addressables (not resources).
cpp
Cursor rule "cpp" from maddevsio/shared_cursor_rules, covering c++ programming guidelines, basic principles, nomenclature, functions and data.