rust-engineering

A set of engineering practices for writing, reviewing, refactoring, and debugging Rust code. Rust is a programming language designed to catch many memory and concurrency mistakes before a program runs.

In plain words
What is it for?
Use it when building Rust libraries, applications, or command-line tools, especially for API design, borrowing and lifetime errors, Tokio-based asynchronous code, testing, performance, and linting.
Why use it?
It helps developers make deliberate choices about data types, ownership, errors, asynchronous work, and verification instead of relying on ad hoc fixes.

Command for Gemini CLI

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 commands/mfmezger/ai_agent_dotfiles/rust-engineering
Clone the repo
git clone --depth 1 https://github.com/mfmezger/ai_agent_dotfiles

Made for: Gemini CLI.

Per session 117 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 951 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 $0.00117 $0.00951
Opus 5 $0.00059 $0.00476
Sonnet 5 $0.00023 $0.00190
Haiku 4.5 $0.00012 $0.00095

Measured 2d ago against content hash 75dfc763a9c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-engineering 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.

gemini/.gemini/commands/rust-engineering.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rust Engineering

Produce Rust that is safe, explicit, and maintainable under review. Default to stable language features, minimal unsafe, narrow APIs, and code that passes formatting, linting, and tests.

Workflow

  1. Identify the artifact. Library: optimize for explicit API boundaries, typed errors, docs, and semver-safe design. Application or CLI: optimize for operability, context-rich errors, tracing, and clear failure modes.
  2. Model types before writing control flow. Prefer enums, newtypes, and private fields over ad hoc strings, flags, or loosely related values.
  3. Choose ownership deliberately. Accept borrowed inputs where practical, return owned outputs when crossing boundaries, and make cloning explicit.
  4. Choose the failure model early. Libraries usually use thiserror; applications usually use anyhow at the outer boundary and typed errors internally when helpful.
  5. Choose the concurrency model deliberately. Use synchronous code unless async is justified by I/O concurrency needs. When async is justified, use Tokio and design cancellation, timeouts, and shutdown explicitly.
  6. Verify before finalizing. Run cargo fmt --check, cargo clippy --all-targets --all-features, and relevant tests. Address warnings instead of normalizing them.

Load References By Need

Need Reference
Project setup, crate structure, CLI patterns, tracing references/workflow.md
Error model, thiserror vs anyhow, context, path/file failure handling references/errors.md
Ownership, API boundaries, newtypes, traits, visibility, serde-facing types references/api-and-types.md
Tokio, cancellation, timeouts, shared state, task spawning, async traits references/async-and-concurrency.md
Unit/integration/doc/property tests, benchmarks, temp files, review checklist references/testing-and-quality.md
Allocation control, data layout, slices, Cow, boxing, profiling references/performance-and-memory.md
Common footguns and review traps references/footguns.md

Read the full file on GitHub · 69 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 · 69 lines · 117 tokens per session scan A 75dfc763a9c5

Subscribe to this mod's changes

rust-engineering is a command published in the GitHub repository mfmezger/ai_agent_dotfiles (5 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 951 once invoked, about $0.0006 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 2026-08-31.