220-rust

220-rust is a cursor rule for coding agents from d-padmanabhan/agent-engineering-handbook. It costs 18 tokens per session (8,348 once invoked), scanned A, original, MIT.

A set of guidance for writing and reviewing Rust, a programming language designed for memory safety and fast execution. It covers ownership, error handling, asynchronous code, and common Rust patterns.

In plain words
What is it for?
Use it when creating or reviewing Rust programs, especially code involving concurrency, performance, errors, or resource management.
Why use it?
It helps prevent memory errors, data races, unclear failure handling, and code that does not follow common Rust practices.

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/d-padmanabhan/agent-engineering-handbook/220-rust
Clone the repo
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbook

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 220-rust

README.md
[![agentmods](https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/220-rust.svg)](https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/220-rust)
Your own site
<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/220-rust"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/220-rust.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,348 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00018 $0.08348
Opus 5 $0.00009 $0.04174
Sonnet 5 $0.00004 $0.01670
Haiku 4.5 $0.00002 $0.00835

Measured 4d ago against content hash b6bc2e13adc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

220-rust 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/220-rust.mdc · 1,493 lines

How it starts

The opening of the file, as written. The whole thing — 1,493 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rust Programming Best Practices

Audience: engineers writing and reviewing Rust code Goal: Memory-safe, performant, idiomatic Rust following community best practices

Rust Philosophy (Core Principles)

Core Principles:

  • "Memory safety without garbage collection" - Ownership system prevents memory errors at compile time
  • "Zero-cost abstractions" - High-level code compiles to efficient low-level code
  • "Fearless concurrency" - Type system prevents data races at compile time
  • "Explicit over implicit" - No hidden allocations, no magic, everything is explicit
  • "Compile-time guarantees" - If it compiles, it's correct (memory safety, thread safety)
  • "Performance by default" - Fast, predictable performance without optimization flags
  • "Composition over inheritance" - Traits and generics enable flexible design
  • "Fail fast, fail clearly" - Use Result and Option, avoid panics in production

Applying Rust Principles:

// BAD: Unsafe, implicit, error-prone
fn process_data(data: Vec<i32>) -> i32 {
    let mut sum = 0;
    for i in 0..data.len() {
        sum += data[i];  // Potential index out of bounds
    }
    sum
}

// GOOD: Safe, explicit, idiomatic
fn process_data(data: &[i32]) -> i32 {
    data.iter().sum()  // Iterator is safe, explicit, efficient
}

// EXCELLENT: Type-safe, error handling
fn process_data(data: &[i32]) -> Result<i32, ProcessingError> {
    if data.is_empty() {
        return Err(ProcessingError::EmptyInput);
    }
    Ok(data.iter().sum())
}

Guiding Principles

  1. Ownership & Borrowing: Master Rust's ownership system for memory safety
  2. Zero-Cost Abstractions: Write high-level code without runtime overhead
  3. Error Handling: Use Result and Option explicitly, avoid panics
  4. Fearless Concurrency: Leverage Rust's type system for safe concurrency
  5. Idiomatic Rust: Follow community conventions (rustfmt, clippy)

Public API Documentation (MUST)

  • Use //! for crate and module documentation and /// for public items.
  • Document public library APIs without restating types already visible in signatures or documenting obvious private helpers.
  • Document caller-relevant errors, panics, ownership, borrowing, mutation, blocking, cancellation, side effects, thread safety, and resource lifecycle.
  • Use # Examples, # Errors, and # Panics when applicable. Every public unsafe API MUST include # Safety.
  • Every unsafe block MUST have a nearby // SAFETY: comment that states the invariant being upheld.
  • Keep intra-doc links and doctests compiling. Run cargo test --doc, build docs with warnings denied, and run Clippy with warnings denied in CI.

Read the full file on GitHub · 1,493 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. 4d ago First seen · 1,493 lines · 18 tokens per session scan A b6bc2e13adc0

Subscribe to this mod's changes

220-rust is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 8,348 once invoked, about $0.0001 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.