Skip to content
Everything Claude Code

rust-test

Command View source on GitHub

Enforce TDD workflow for Rust. Write tests first, then implement. Verify 80%+ coverage with cargo-llvm-cov.

Rust TDD Command

This command enforces test-driven development methodology for Rust code using #[test], rstest, proptest, and mockall.

What This Command Does

  1. Define Types/Traits: Scaffold function signatures with todo!()
  2. Write Tests: Create comprehensive test module (RED)
  3. Run Tests: Verify tests fail for the right reason
  4. Implement Code: Write minimal code to pass (GREEN)
  5. Refactor: Improve while keeping tests green
  6. Check Coverage: Ensure 80%+ coverage with cargo-llvm-cov

When to Use

Use /rust-test when:

  • Implementing new Rust functions, methods, or traits
  • Adding test coverage to existing Rust code
  • Fixing bugs (write failing test first)
  • Building critical business logic
  • Learning TDD workflow in Rust

TDD Cycle

RED     -> Write failing test first
GREEN   -> Implement minimal code to pass
REFACTOR -> Improve code, tests stay green
REPEAT  -> Next test case

Example Session

User: /rust-test I need a function to validate user registration


Agent:
# TDD Session: Registration Validator


## Step 1: Define Interface


```rust
// src/validator.rs
pub struct RegistrationRequest {
    pub name: String,
    pub email: String,
    pub password: String,
}


pub enum ValidationResult {
    Valid,
    Invalid(Vec<String>),
}


pub fn validate_registration(request: &RegistrationRequest) -> ValidationResult {
    todo!()
}
```


## Step 2: Write Tests (RED)


```rust
#[cfg(test)]
mod tests {
    use super::*;


    #[test]
    fn valid_registration_returns_valid() {
        let request = RegistrationRequest {
            name: "Alice".into(),
            email: "alice@example.com".into(),
            password: "SecureP@ss1".into(),
        };
        assert!(matches!(validate_registration(&request), ValidationResult::Valid));
    }


    #[test]
    fn blank_name_returns_invalid() {
        let request = RegistrationRequest {
            name: "".into(),
            email: "alice@example.com".into(),
            password: "SecureP@ss1".into(),
        };
        match validate_registration(&request) {
            ValidationResult::Invalid(errors) => {
                assert!(errors.contains(&"Name is required".to_string()));
            }
            ValidationResult::Valid => panic!("expected Invalid"),
        }
    }


    #[test]
    fn invalid_email_returns_invalid() {
        let request = RegistrationRequest {
            name: "Alice".into(),
            email: "not-an-email".into(),
            password: "SecureP@ss1".into(),
        };
        assert!(matches!(
            validate_registration(&request),
            ValidationResult::Invalid(_)
        ));
    }


    #[test]
    fn short_password_returns_invalid() {
        let request = RegistrationRequest {
            name: "Alice".into(),
            email: "alice@example.com".into(),
            password: "short".into(),
        };
        assert!(matches!(
            validate_registration(&request),
            ValidationResult::Invalid(_)
        ));
    }
}
```


## Step 3: Run Tests — Verify FAIL


```bash
$ cargo test
running 4 tests
test tests::valid_registration_returns_valid ... FAILED (not yet implemented)
test tests::blank_name_returns_invalid ... FAILED
test tests::invalid_email_returns_invalid ... FAILED
test tests::short_password_returns_invalid ... FAILED
```


Tests fail as expected (todo! panic).


## Step 4: Implement Minimal Code (GREEN)


```rust
pub fn validate_registration(request: &RegistrationRequest) -> ValidationResult {
    let mut errors = Vec::new();


    if request.name.trim().is_empty() {
        errors.push("Name is required".into());
    }
    if !request.email.contains('@') {
        errors.push("Invalid email format".into());
    }
    if request.password.len() < 8 {
        errors.push("Password must be at least 8 characters".into());
    }


    if errors.is_empty() {
        ValidationResult::Valid
    } else {
        ValidationResult::Invalid(errors)
    }
}
```


## Step 5: Run Tests — Verify PASS


```bash
$ cargo test
running 4 tests
test tests::valid_registration_returns_valid ... ok
test tests::blank_name_returns_invalid ... ok
test tests::invalid_email_returns_invalid ... ok
test tests::short_password_returns_invalid ... ok


test result: ok. 4 passed; 0 failed
```


All tests passing!


## Step 6: Check Coverage


```bash
$ cargo llvm-cov
Coverage: 100.0% of lines
```


Coverage: 100%


## TDD Complete!

Test Patterns

Unit Tests

#[cfg(test)]
mod tests {
    use super::*;


    #[test]
    fn adds_two_numbers() {
        assert_eq!(add(2, 3), 5);
    }


    #[test]
    fn handles_error() -> Result<(), Box<dyn std::error::Error>> {
        let result = parse_config(r#"port = 8080"#)?;
        assert_eq!(result.port, 8080);
        Ok(())
    }
}

Parameterized Tests with rstest

use rstest::{rstest, fixture};


#[rstest]
#[case("hello", 5)]
#[case("", 0)]
#[case("rust", 4)]
fn test_string_length(#[case] input: &str, #[case] expected: usize) {
    assert_eq!(input.len(), expected);
}

Async Tests

#[tokio::test]
async fn fetches_data_successfully() {
    let client = TestClient::new().await;
    let result = client.get("/data").await;
    assert!(result.is_ok());
}

Property-Based Tests

use proptest::prelude::*;


proptest! {
    #[test]
    fn encode_decode_roundtrip(input in ".*") {
        let encoded = encode(&input);
        let decoded = decode(&encoded).unwrap();
        assert_eq!(input, decoded);
    }
}

Coverage Commands

Terminal window
# Summary report
cargo llvm-cov


# HTML report
cargo llvm-cov --html


# Fail if below threshold
cargo llvm-cov --fail-under-lines 80


# Run specific test
cargo test test_name


# Run with output
cargo test -- --nocapture


# Run without stopping on first failure
cargo test --no-fail-fast

Coverage Targets

Code TypeTarget
Critical business logic100%
Public API90%+
General code80%+
Generated / FFI bindingsExclude

TDD Best Practices

DO:

  • Write test FIRST, before any implementation
  • Run tests after each change
  • Use assert_eq! over assert! for better error messages
  • Use ? in tests that return Result for cleaner output
  • Test behavior, not implementation
  • Include edge cases (empty, boundary, error paths)

DON’T:

  • Write implementation before tests
  • Skip the RED phase
  • Use #[should_panic] when Result::is_err() works
  • Use sleep() in tests — use channels or tokio::time::pause()
  • Mock everything — prefer integration tests when feasible
  • /rust-build - Fix build errors
  • /rust-review - Review code after implementation
  • verification-loop skill - Run full verification loop
  • Skill: skills/rust-testing/
  • Skill: skills/rust-patterns/
← Back to Commands