technical-decisions

technical-decisions is a cursor rule for coding agents from sfc-gh-cconner/support-rules-mcp. It costs 1,896 tokens per session, scanned A, original, Apache-2.0.

A set of architectural rules for building MCP servers and related tools in Python. MCP is a standard way for an AI assistant to call tools, while the rules themselves are stored in Markdown files.

In plain words
What is it for?
Use it when designing or extending the project’s MCP server, rule folders, Python dependencies, validation, tests, formatting checks, and GitHub Actions workflows.
Why use it?
Projects need consistent choices about dependencies, rule organization, validation, testing, and releases. These decisions give contributors a shared technical baseline.

Cursor rule

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.

agentmods
npx agentmods add rules/sfc-gh-cconner/support-rules-mcp/technical-decisions
Clone the repo
git clone --depth 1 https://github.com/sfc-gh-cconner/support-rules-mcp

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 technical-decisions

README.md
[![agentmods](https://agentmods.dev/badge/rules/sfc-gh-cconner/support-rules-mcp/technical-decisions.svg)](https://agentmods.dev/rules/sfc-gh-cconner/support-rules-mcp/technical-decisions)
Your own site
<a href="https://agentmods.dev/rules/sfc-gh-cconner/support-rules-mcp/technical-decisions"><img src="https://agentmods.dev/badge/rules/sfc-gh-cconner/support-rules-mcp/technical-decisions.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,896 This file is loaded in full into every session.
When invoked 1,896 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01896 $0.01896
Opus 5 $0.00948 $0.00948
Sonnet 5 $0.00379 $0.00379
Haiku 4.5 $0.00190 $0.00190

Measured 3d ago against content hash e2a4f8692881, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-decisions 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 3d 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.

rules/workflows/technical-decisions.mdc · 317 lines

How it starts

The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Decisions & Architecture

PURPOSE: Architectural principles and technical stack decisions for MCP server and tooling development.

🛠️ Technology Stack

Core Technologies

  • Language: Python 3.8+
  • MCP Framework: Model Context Protocol Server
  • Rule Format: Markdown (.mdc files)
  • Code Quality: pre-commit hooks (black, isort, flake8)
  • Testing: pytest with mocking
  • CI/CD: GitHub Actions (when applicable)

Python Ecosystem

# Standard dependencies
python >= 3.8
mcp >= 0.1.0  # MCP server framework
pydantic >= 2.0  # Data validation
pyyaml >= 6.0  # Configuration parsing

🏗️ Architecture Principles

1. MCP Server Design

Principle: Rules are the source of truth for AI assistant behavior.

# Rule structure
rules/
├── core/              # Fundamental patterns
│   ├── 01-*.mdc      # Numbered for ordering
│   └── ...
├── connectors/       # Driver-specific
├── spcs/            # SPCS-specific
├── workflows/       # Process documentation
└── _meta/           # Complete workflows

Benefits:

  • Modular rule organization
  • Easy to add/update rules
  • Clear separation of concerns
  • Rules can include other rules

2. Rule Composition

Principle: Rules can reference and include other rules.

# In a meta rule
@include core/01-github-mcp
@include core/06-snowflake-cli
@include core/08-mono-repo-mcp

This rule combines GitHub MCP, Snowflake CLI, and mono repo
navigation patterns for complete investigations.

Benefits:

  • Reusability
  • Consistency
  • Easier maintenance
  • Logical grouping

3. Separation of Concerns

Principle: Each rule has a single, clear purpose.

# Good - Focused rules
01-github-mcp.mdc → GitHub MCP integration patterns
06-snowflake-cli.mdc → Snow CLI usage
08-mono-repo-mcp.mdc → Mono repo navigation with GitHub MCP

# Bad - Mixed concerns
snowflake-investigation.mdc → Everything about investigating

Benefits:

  • Easier to find relevant rules
  • Simpler to update individual rules
  • Clearer documentation
  • Better testability

Read the full file on GitHub · 317 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. 3d ago First seen · 317 lines · 1,896 tokens per session scan A e2a4f8692881

Subscribe to this mod's changes

technical-decisions is a cursor rule published in the GitHub repository sfc-gh-cconner/support-rules-mcp (0 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 1,896 tokens to every session, about $0.0095 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.