cursorrules

A set of rules for using GDB, a tool that runs programs step by step to find bugs, through an MCP server.

In plain words
What is it for?
Use it to inspect failing Rust programs with GDB and work through common Rust compiler errors.
Why use it?
It gives the coding agent access to debugging actions and Rust-focused guidance for understanding and correcting compiler errors.

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/pansila/mcp_server_gdb/cursorrules
Clone the repo
git clone --depth 1 https://github.com/pansila/mcp_server_gdb

Made for: Cursor.

Per session 5,013 This file is loaded in full into every session.
When invoked 5,013 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 $0.05013 $0.05013
Opus 5 $0.02507 $0.02507
Sonnet 5 $0.01003 $0.01003
Haiku 4.5 $0.00501 $0.00501

Measured 2d ago against content hash a4826c791568, 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 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.

.cursorrules · 634 lines

How it starts

The opening of the file, as written. The whole thing — 634 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "metadata": {
    "name": ".cursorrules",
    "pseudonym": "Rust-Eze",
    "version": "1.7.2",
    "description": "Advanced Rust code analysis and correction system with enhanced context-specific error resolution strategies",
    "maintainers": [
      "[email protected]"
    ],
    "author_github": "Lord Xyn <https://github.com/arcmoonstudios/Rust-Eze>",
    "last_updated": "2024-12-06",
    "changelog": {
      "1.3.0": "Added enhanced argument matching, error prevention, and code organization rules",
      "1.3.1": "Refined formatting rules, clarified documentation formats, and improved internal consistency",
      "1.4.0": "Introduced common error pattern recognition and heuristic-driven suggestions for complex compiler errors",
      "1.5.0": "Expanded patterns to handle no-variant errors, conflicting implementations, `?` operator misuse, and missing structure fields",
      "1.6.0": "Added patterns for invalid type category usage, invalid trait references, and invalid self parameter usage",
      "1.7.0": "Enhanced to handle trait bound failures, ambiguous items, and additional missing `default` method scenarios",
      "1.7.1": "Re-implemented prior correcting implementations that were erroneously removed, added author and github links to metadata",
      "1.7.2": "Added extensive performance optimization, IDE integration, LSP support, and memory management configurations"
    }
  },
  "language": "rust",
  "performance": {
    "caching": {
      "enable": true,
      "max_cache_size": "512MB",
      "cache_duration": "24h",
      "cache_invalidation": "on_file_change"
    },
    "parallel_processing": {
      "enable": true,
      "max_threads": 4,
      "priority_tasks": ["error_analysis", "code_completion"]
    },
    "lazy_loading": {
      "enable": true,
      "modules": ["documentation", "advanced_analysis"]
    }
  },
  "ide_integration": {
    "cursor_specific": {
      "completion_triggers": [".", "::", "(", "{", "["],
      "hover_documentation

Read the full file on GitHub · 634 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. 2d ago First seen · 634 lines · 5,013 tokens per session scan A a4826c791568

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository pansila/mcp_server_gdb (68 stars, last pushed 11mo ago), licensed MIT. It adds 5,013 tokens to every session, about $0.0251 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.