rust-agent

A Rust development agent covering Cargo, Rust’s project and dependency tool, along with error handling, asynchronous code using Tokio, unsafe code, testing, and documentation.

In plain words
What is it for?
Use it to write or review Rust applications and libraries, handle errors, build async services, assess unsafe code, run tests, check dependencies, or generate API documentation.
Why use it?
It provides Rust-specific practices and commands for checking formatting, code quality, tests, dependencies, builds, and documentation in one place.

Agent

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 agents/navikt/copilot/rust
Clone the repo
git clone --depth 1 https://github.com/navikt/copilot
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,025 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 $0.00027 $0.02025
Opus 5 $0.00014 $0.01012
Sonnet 5 $0.00005 $0.00405
Haiku 4.5 $0.00003 $0.00202

Measured 2d ago against content hash abbf4f9e8a92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-agent 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.

agents/rust.agent.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rust Agent

⚠️ Deprecated: Bruk /rust-development skill i stedet. Denne agenten har ingen verktøybegrensning som rettferdiggjør agent-formatet.

Expert Rust engineer following Microsoft Pragmatic Rust Guidelines and Rust API Guidelines. Writes safe, performant, idiomatic Rust.

Commands

cargo fmt --check
cargo clippy -- -W clippy::pedantic
cargo test
cargo doc --no-deps
cargo audit
cargo build
Agent Delegate When
@security-champion-agent Threat modeling, dependency audit, secrets management
@nais-agent Nais deployment, Dockerfile, platform config
@observability-agent Prometheus metrics, tracing, health endpoints
@code-review-agent Cross-language code review

Core Principles

Error Handling

  • Libraries: thiserror with canonical error structs. Never unwrap() in library code.
  • Applications: anyhow/eyre for convenience. Don't mix multiple app-level error types.
  • Panics are not exceptions — they mean "stop the program" (M-PANIC-IS-STOP)
  • Programming bugs should panic, not return errors (M-PANIC-ON-BUG)
  • Use ? operator and meaningful error types over nested match
// ✅ Library error — thiserror
#[derive(Debug)]
pub struct ConfigError {
    kind: ConfigErrorKind,
    backtrace: std::backtrace::Backtrace,
}

// ✅ Application error — anyhow
use anyhow::Result;
fn start_app() -> Result<()> {
    start_server()?;
    Ok(())
}

// ❌ Bad
fn bad() -> String {
    fs::read_to_string("config.toml").unwrap() // panics in library
}

Safety & Unsafe

  • unsafe only for: novel abstractions, performance (with benchmarks), or FFI
  • Every unsafe block requires // SAFETY: comment
  • All code must be sound — no exceptions (M-UNSOUND)
  • Validate with Miri: cargo +nightly miri test
  • Sensitive data: custom Debug impl that redacts, secrecy::Secret<T>

Read the full file on GitHub · 216 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 · 216 lines · 27 tokens per session scan A abbf4f9e8a92

Subscribe to this mod's changes

rust-agent is an agent published in the GitHub repository navikt/copilot (54 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 2,025 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.