cursorrules

Project rules for handling programming errors at the appropriate layer, meaning the part of the software responsible for responding to them.

In plain words
What is it for?
Deciding where to catch errors, when to let them propagate, how to re-raise them with context, and how to avoid ignoring exceptions.
Why use it?
They reduce duplicate logging, hidden failures, and error messages that lack useful context.

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/nosugarcoffee/youmind-mcp/cursorrules
Clone the repo
git clone --depth 1 https://github.com/NoSugarCoffee/youmind-mcp

Made for: Cursor.

Per session 700 This file is loaded in full into every session.
When invoked 700 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 $0.00700 $0.00700
Opus 5 $0.00350 $0.00350
Sonnet 5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured yesterday against content hash 4a390a79e264, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Error Handling Policy

Core Principle: Only Handle Errors Once

Errors should be handled exactly once. Handling an error means inspecting the error value and making a decision about what to do with it.

Rules:

  1. Handle errors at the appropriate layer

    • Lower-level code (API clients, utilities) should let exceptions propagate naturally
    • Higher-level code (handlers, endpoints) should catch, log, and convert to user-friendly messages
    • Do NOT catch, log, and re-raise the same error at multiple layers
  2. Add context when wrapping errors

    • When catching and re-raising, use exception chaining: raise NewException("context") from original_error
    • Or use raise without arguments to preserve the traceback: raise
    • Add meaningful context that helps debug the issue
  3. Don't ignore errors

    • Never use bare except: clauses
    • Never catch exceptions without handling them
    • If you catch an exception, you must either:
      • Handle it completely (log, convert to user message, return default value)
      • Re-raise it with additional context
      • Let it propagate if you can't add value
  4. Logging and error handling

    • Log errors at the point where you handle them (not where you catch and re-raise)
    • Include relevant context in log messages (request IDs, parameters, etc.)
    • Use appropriate log levels: ERROR for failures, WARNING for recoverable issues
  5. Exception types

    • Use specific exception types when possible (ValueError, TypeError, etc.)
    • Create custom exceptions for domain-specific errors
    • Avoid catching generic Exception unless at the top-level boundary

Anti-patterns to avoid:

# BAD: Handling error twice (logging and re-raising)
def api_call():
    try:
        response = client.get()
    except Exception as e:
        logger.error(f"Error: {e}")  # First handling
        raise  # Re-raising, will be handled again upstream

def handler():
    try:
        api_call()
    except Exception as e:
        logger.error(f"Error: {e}")  # Second handling - duplicate!
        return "Error occurred"

Read the full file on GitHub · 91 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. yesterday First seen · 91 lines · 700 tokens per session scan A 4a390a79e264

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository NoSugarCoffee/youmind-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 700 tokens to every session, about $0.0035 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.