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/ekakit/lightfast-mcpWrote 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/ekakit/lightfast-mcp/project-architecture)<a href="https://agentmods.dev/rules/ekakit/lightfast-mcp/project-architecture"><img src="https://agentmods.dev/badge/rules/ekakit/lightfast-mcp/project-architecture/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/ekakit/lightfast-mcp/project-architecture"><img src="https://agentmods.dev/badge/rules/ekakit/lightfast-mcp/project-architecture.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 | $0.00494 | $0.00494 |
| Opus 5.5 | $0.00198 | $0.00198 |
| Sonnet 5.5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
project-architecture 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.
What it actually says
Project Architecture
Core Structure
src/lightfast_mcp/ # Core MCP server implementations
├── core/ # Base classes (BaseServer, ServerConfig), shared server utilities
├── servers/ # MCP server implementations
│ ├── blender/ # Blender MCP server
│ │ ├── server.py
│ │ └── __init__.py
│ ├── mock/ # Mock MCP server for testing
│ │ ├── server.py
│ │ ├── tools.py
│ │ └── __init__.py
│ ├── blender_mcp_server.py # Blender server entry point script
│ └── mock_mcp_server.py # Mock server entry point script
└── utils/ # Shared utilities for MCP servers (e.g., logging)
src/tools/ # Development and orchestration tools
├── orchestration/ # Multi-server orchestration (ServerOrchestrator, ServerRegistry, ConfigLoader)
├── ai/ # AI integration tools (ConversationClient, AI providers)
├── common/ # Common utilities specific to the tools package
└── __init__.py # Tools package exports
Entry Points
lightfast-mcp-orchestrator: Main CLI for orchestrating multiple serverslightfast-blender-server: Direct Blender server entry pointlightfast-mock-server: Direct mock server entry point
File Patterns
servers/{app}_mcp_server.py: Entry point scriptsservers/{app}/server.py: Main server implementationservers/{app}/tools.py: Tool implementationsservers/{app}/resources.py: Resource implementations (if applicable)config/servers.yaml: Server configurationtests/unit/test_{module}.py: Unit teststests/integration/test_{feature}.py: Integration teststests/e2e/test_{workflow}.py: End-to-end tests
Configuration Files
.cursor/mcp.json: Cursor MCP integration configpyproject.toml: Project configuration and dependenciesconfig/servers.yaml: Server configuration
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 · 50 lines · 494 tokens per session scan A 11d650f870ff
project-architecture is a cursor rule published in the GitHub repository ekakit/lightfast-mcp (2 stars, last pushed 1y ago), licensed MIT. It adds 494 tokens to every session, about $0.0020 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 2026-08-31.
Other cursor rules, from other repositories
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.