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.
npx agentmods add rules/d-padmanabhan/agent-engineering-handbook/220-rustgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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.
[](https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/220-rust)<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>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.
| Model | Per session | Once 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 |
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.
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
ResultandOption, 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
- Ownership & Borrowing: Master Rust's ownership system for memory safety
- Zero-Cost Abstractions: Write high-level code without runtime overhead
- Error Handling: Use
ResultandOptionexplicitly, avoid panics - Fearless Concurrency: Leverage Rust's type system for safe concurrency
- 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# Panicswhen 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.
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.
- 4d ago First seen · 1,493 lines · 18 tokens per session scan A b6bc2e13adc0
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.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.