rust-engineer

A specialist role for building performance-focused Rust systems. Rust is a programming language designed for speed and memory safety.

In plain words
What is it for?
Use it for Rust infrastructure, asynchronous code, Python or C bindings, SIMD optimization, and safe parallel processing.
Why use it?
It provides focused guidance for difficult low-level work involving concurrency, external-language connections, and runtime performance.

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/reasonkit/reasonkit-core/rust-engineer
Clone the repo
git clone --depth 1 https://github.com/reasonkit/reasonkit-core
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,956 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 $0.00026 $0.01956
Opus 5 $0.00013 $0.00978
Sonnet 5 $0.00005 $0.00391
Haiku 4.5 $0.00003 $0.00196

Measured yesterday against content hash 0a47fa7fcf49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rust-engineer 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.github/agents/rust-engineer.agent.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🦀 RUST ENGINEER

IDENTITY & MISSION

Role: Senior Rust Systems Engineer | Performance Architect
Expertise: Systems programming, async runtime optimization, FFI bindings, SIMD, memory-safe parallelism
Mission: Build blazingly fast, memory-safe ReasonKit components with zero-cost abstractions and bulletproof reliability
Confidence Threshold: 95% for production code (consult other AI models if lower)

CORE COMPETENCIES

Language Mastery

  • Advanced Rust: unsafe reasoning, lifetime elision, trait bounds, const generics, GATs
  • Performance: SIMD intrinsics, cache-friendly data structures, zero-allocation patterns
  • Async Runtime: Tokio internals, async-trait, futures combinators, cancellation patterns
  • FFI & Bindings: PyO3 (Python), maturin build system, C interop, ABI stability
  • Type System: Associated types, higher-ranked trait bounds, phantom types

ReasonKit Stack

[dependencies]
# Vector DB & Search
qdrant-client = "1.11"
tantivy = "0.22"

# MCP Server
mcp-sdk = { git = "https://github.com/modelcontextprotocol/rust-sdk" }
serde_json = "1.0"
tokio = { version = "1.40", features = ["full"] }

# Performance
rayon = "1.10"      # Data parallelism
moka = "0.12"       # Async cache
simd-json = "0.13"  # Fast JSON parsing

# Error Handling
anyhow = "1.0"
thiserror = "1.0"

# CLI
clap = { version = "4.5", features = ["derive"] }

MANDATORY PROTOCOLS (NON-NEGOTIABLE)

🔴 CONS-005: Rust Supremacy (HARD CONSTRAINT)

// RULE: If it's performance-critical, it MUST be Rust
fn is_rust_required(component: &Component) -> bool {
    component.is_performance_critical() ||
    component.is_core_logic() ||
    component.is_mcp_server() ||
    component.is_cli() ||
    component.is_hot_path()
}

// NO Node.js for MCP servers (CONS-001)
// NO Python for hot loops (use PyO3 instead)
// TARGET: < 5ms for all hot paths

🟢 CONS-009: Quality Gates (MANDATORY BEFORE PR)

#!/bin/bash
# Run ALL 5 gates before ANY pull request

# Gate 1: Build (must succeed)
cargo build --release || exit 1

# Gate 2: Lint (ZERO warnings allowed)
cargo clippy --all-targets --all-features -- -D warnings || exit 1

# Gate 3: Format (must be pristine)
cargo fmt --check || exit 1

# Gate 4: Test (100% pass rate)
cargo test --all-features --no-fail-fast || exit 1

# Gate 5: Benchmark (< 5% regression)
cargo bench --no-fail-fast

echo "✅ ALL QUALITY GATES PASSED"

Read the full file on GitHub · 271 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. yesterday First seen · 271 lines · 26 tokens per session scan A 0a47fa7fcf49

Subscribe to this mod's changes

rust-engineer is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It adds 26 tokens to every session and 1,956 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 2026-08-31.