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/sfc-gh-cconner/support-rules-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/sfc-gh-cconner/support-rules-mcp/ai-collaboration)<a href="https://agentmods.dev/rules/sfc-gh-cconner/support-rules-mcp/ai-collaboration"><img src="https://agentmods.dev/badge/rules/sfc-gh-cconner/support-rules-mcp/ai-collaboration.svg" alt="Measured on agentmods" 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 | $0.01798 | $0.01798 |
| Opus 5 | $0.00899 | $0.00899 |
| Sonnet 5 | $0.00360 | $0.00360 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
ai-collaboration 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 7d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Assistant Collaboration Guidelines
PURPOSE: Best practices for AI assistants working with Snowflake support rules and investigations.
🤖 AI Assistant Behavior
Efficiency & Batching
- Batch multiple tasks in a single response to save tokens
- Use parallel tool calls when operations are independent
- Ask clarifying questions efficiently, don't wait unnecessarily
- Validate results before proceeding
- Fix failures immediately - don't leave broken states
Communication Standards
- Use step-by-step planning for complex tasks
- Be thorough and comprehensive in responses
- Explain technical decisions and rationale
- Provide examples and code snippets when helpful
- Cite sources (rules, documentation, code) accurately
Examples of Good Requests
✅ Good requests:
- "Find the error in GS logs, trace to source code, and explain the root cause"
- "Create a SPCS reproduction for service connectivity issues with full deployment scripts"
- "Query Snowhouse for authentication failures and correlate with source code"
❌ Poor requests:
- "Fix this" (lacks context)
- "Check logs" (too vague, which logs?)
- "Find the issue" (no specifics about symptoms or timeframe)
🎯 Using This MCP Server
Rule Selection
- Start broad: Use meta rules for complete workflows (
_meta/troubleshooting.mdc) - Get specific: Use individual rules for focused tasks
- Combine rules: Multiple rules can be active simultaneously
Tool Usage Priority
- Snowhouse - Always start with log analysis for investigations
- GitHub MCP - Search source code for errors and logic
- Snowflake Docs - Get official documentation for features
- Context7 - Get code examples for implementations
Efficient Investigation Workflow
1. Query Snowhouse for initial data (timestamps, errors, account)
2. Search GitHub MCP for error messages in source code
3. Get full context with file retrieval
4. Cross-reference with Snowflake documentation
5. Validate findings in logs
6. Provide analysis with sources
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.
- 7d ago First seen · 261 lines · 1,798 tokens per session scan A 714eb81d1f10
ai-collaboration is a cursor rule published in the GitHub repository sfc-gh-cconner/support-rules-mcp (0 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 1,798 tokens to every session, about $0.0090 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
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.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.