troubleshooting

troubleshooting is a cursor rule for coding agents from sfc-gh-cconner/support-rules-mcp. It costs 439 tokens per session, scanned A, original, Apache-2.0.

A troubleshooting workflow combining documentation, source-code access, database queries, data mappings, and logs to investigate Snowflake problems. Snowflake is a cloud database platform.

In plain words
What is it for?
Looking up documentation, querying Snowhouse data, inspecting GitHub source code, checking logs, and tracing account-specific ETL issues.
Why use it?
It gives investigations a consistent path from expected behavior to data, implementation details, logs, and a likely root cause.

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/troubleshooting
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 troubleshooting

README.md
[![agentmods](https://agentmods.dev/badge/rules/sfc-gh-cconner/support-rules-mcp/troubleshooting.svg)](https://agentmods.dev/rules/sfc-gh-cconner/support-rules-mcp/troubleshooting)
Your own site
<a href="https://agentmods.dev/rules/sfc-gh-cconner/support-rules-mcp/troubleshooting"><img src="https://agentmods.dev/badge/rules/sfc-gh-cconner/support-rules-mcp/troubleshooting.svg" alt="Measured on agentmods" height="20"></a>
Per session 439 This file is loaded in full into every session.
When invoked 439 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 $0.00439 $0.00439
Opus 5 $0.00219 $0.00219
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 4d ago against content hash 23c734ab8c04, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

troubleshooting 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 4d 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/_meta/troubleshooting.mdc · 57 lines

What it actually says

Troubleshooting Workflow - Complete Ruleset

PURPOSE: Complete investigation workflow combining GitHub MCP, Snowflake Docs, Snowhouse querying, and DPO mappings for systematic troubleshooting.

Meta-Rule: This combines all core Snowflake knowledge with troubleshooting-specific guidance.


📦 Included Rules

This meta-rule includes:

  • ✅ Core: Source code access (GitHub MCP)
  • ✅ Core: Documentation access (Snowflake Docs MCP)
  • ✅ Core: DPO to table mappings
  • ✅ Core: Snowhouse querying patterns
  • ✅ Workflow: Troubleshooting investigation guide

@include core/01-github-mcp.mdc @include core/02-docs-mcp.mdc @include core/04-dpo-mappings.mdc @include core/05-snowhouse-querying.mdc @include workflows/troubleshooting.mdc


🎯 Quick Reference

Investigation Flow

  1. Documentation → Understand expected behavior
  2. Snowhouse → Query for data and context
  3. Source Code → Find implementation details
  4. Logs → Analyze detailed execution
  5. Root Cause → Synthesize findings

Key Principles

  • Always filter by account_id
  • Start with job_etl_v for timestamps
  • Check if objects are stage-backed (image repos, git repos)
  • Use GitHub MCP for source code
  • Use Snowflake Docs MCP for official documentation
  • Correlate across all data sources

Common Objects

Object Table Filter
Image Repo stage_etl_v stage_type = 'IMAGE_REPOSITORY'
Git Repo stage_etl_v stage_type = 'GIT_REPOSITORY'
Query job_etl_v start_time range
Session session_etl_v session_id
Warehouse warehouse_etl_v warehouse_name

Usage: Load this rule in your troubleshooting project's .cursorrules or via MCP.

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. 4d ago First seen · 57 lines · 439 tokens per session scan A 23c734ab8c04

Subscribe to this mod's changes

troubleshooting 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 439 tokens to every session, about $0.0022 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.