root-problem-identification

A rule that makes an AI describe the underlying business problem before proposing a code change. It also asks the AI to clarify requirements and compare possible approaches.

In plain words
What is it for?
Use it when asking an AI to fix, implement, change, update, or create something, such as improving a slow database query.
Why use it?
It helps prevent solving the visible symptom while missing the real need. It adds business context before implementation begins.

Cursor rule for Cursor

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/seanlf/weather-mcp/root-problem-identification
Clone the repo
git clone --depth 1 https://github.com/SeanLF/weather-mcp

Made for: Cursor.

Per session 372 This file is loaded in full into every session.
When invoked 372 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 $0.00372 $0.00372
Opus 5 $0.00186 $0.00186
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 2d ago against content hash 5910ab8e2654, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

root-problem-identification 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 2d 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.

.cursor/rules/root-problem-identification.mdc · 70 lines

What it actually says

filters:

  • type: event pattern: "ai_suggestion_request"
  • type: content pattern: "(?i)(fix|implement|change|update|create)"

actions:

  • type: transform pattern: "^.*$" replacement: |

    Problem Analysis

    Business Context

    {infer_business_context_from_request}

    Underlying Problem

    {extract_root_problem}

    Requirements

    {explicit_and_implicit_requirements}

    Implementation Plan

    {original_content}

  • type: suggest message: | Before implementing a solution:

    1. Identify the underlying business problem
    2. Clarify any unstated requirements
    3. Consider alternative approaches
    4. Choose the solution with highest business value and lowest complexity

examples:

  • input: | Can you optimize this database query? It's running slowly. output: |

    Problem Analysis

    Business Context

    This query appears to be affecting application performance, potentially impacting user experience or system reliability.

    Underlying Problem

    The database query is performing inefficiently, likely due to missing indexes, suboptimal join conditions, or retrieving unnecessary data.

    Requirements

    • Improve query performance
    • Maintain exact same result set
    • No schema changes unless absolutely necessary

    Implementation Plan

    Let me analyze this query to find optimization opportunities...

metadata: priority: critical version: 1.0

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. 2d ago First seen · 70 lines · 372 tokens per session scan A 5910ab8e2654

Subscribe to this mod's changes

root-problem-identification is a cursor rule published in the GitHub repository SeanLF/weather-mcp (2 stars, last pushed 1y ago), licensed MIT. It adds 372 tokens to every session, about $0.0019 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.