003-code-generation

003-code-generation is a cursor rule for Cursor from Yuhamixli/Law-Crawler-RPA-RAG-MCP. It costs 212 tokens per session, scanned A, original, MIT.

A set of rules for producing complete, runnable code. It covers imports, setup and cleanup, error handling, naming, formatting, performance, tests, logging, and documentation.

In plain words
What is it for?
Generating implementations, validating inputs, handling failures, adding basic tests or usage examples, and documenting functions.
Why use it?
It reduces the chance of receiving incomplete examples, missing dependencies, unclear errors, or code that is difficult to test and maintain.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Generating implementations, validating inputs, handling failures, adding basic tests or usage examples, and documenting functions.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/yuhamixli/law-crawler-rpa-rag-mcp/003-code-generation
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.

Clone the repo
git clone --depth 1 https://github.com/Yuhamixli/Law-Crawler-RPA-RAG-MCP

Made for: Cursor.

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 003-code-generation

README.md
[![agentmods](https://agentmods.dev/badge/rules/yuhamixli/law-crawler-rpa-rag-mcp/003-code-generation/github.svg)](https://agentmods.dev/rules/yuhamixli/law-crawler-rpa-rag-mcp/003-code-generation)
Your own site
<a href="https://agentmods.dev/rules/yuhamixli/law-crawler-rpa-rag-mcp/003-code-generation"><img src="https://agentmods.dev/badge/rules/yuhamixli/law-crawler-rpa-rag-mcp/003-code-generation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 003-code-generation

Your own site · 80×15
<a href="https://agentmods.dev/rules/yuhamixli/law-crawler-rpa-rag-mcp/003-code-generation"><img src="https://agentmods.dev/badge/rules/yuhamixli/law-crawler-rpa-rag-mcp/003-code-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 This file is loaded in full into every session.
When invoked 212 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00212 $0.00212
Opus 5 $0.00106 $0.00106
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured 9d ago against content hash 8c06192b1fd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

003-code-generation 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 9d 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/003-code-generation.mdc · 37 lines

What it actually says

Code Generation Quality Rules

Code Completeness

  • Generate complete, runnable code without placeholders
  • Include all necessary imports and dependencies
  • Provide full implementation, not just function signatures
  • Include proper initialization and cleanup code

Error Handling

  • Implement comprehensive error handling for all functions
  • Use appropriate exception types and error messages
  • Include input validation for all public functions
  • Log errors appropriately for debugging

Code Style

  • Follow consistent indentation and formatting
  • Use meaningful variable and function names
  • Add helpful comments for complex logic
  • Organize code into logical sections with clear separation

Performance Considerations

  • Write efficient algorithms when possible
  • Avoid unnecessary resource usage
  • Include performance comments for complex operations
  • Consider memory management best practices

Testing and Debugging

  • Include basic test cases or usage examples
  • Add debug logging where appropriate
  • Ensure code is easily testable and modular
  • Provide clear documentation for function parameters and return values
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. 9d ago First seen · 37 lines · 212 tokens per session scan A 8c06192b1fd3

Subscribe to this mod's changes

003-code-generation is a cursor rule published in the GitHub repository Yuhamixli/Law-Crawler-RPA-RAG-MCP (31 stars, last pushed 4mo ago), licensed MIT. It adds 212 tokens to every session, about $0.0011 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 2026-08-30.