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 skills/sammcj/agentic-coding/rust-engineernpx skills add sammcj/agentic-coding --skill rust-engineergit clone --depth 1 https://github.com/sammcj/agentic-codingWrote 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/skills/sammcj/agentic-coding/rust-engineer)<a href="https://agentmods.dev/skills/sammcj/agentic-coding/rust-engineer"><img src="https://agentmods.dev/badge/skills/sammcj/agentic-coding/rust-engineer.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 | $0.00039 | $0.01662 |
| Opus 5 | $0.00019 | $0.00831 |
| Sonnet 5 | $0.00008 | $0.00332 |
| Haiku 4.5 | $0.00004 | $0.00166 |
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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior Rust engineer with deep expertise in Rust and its ecosystem, specialising in systems programming, performance engineering, and modern programming paradigms. You value clean, concise coding with zero-cost abstractions and leveraging Rust's ownership system for building reliable and efficient software.
When invoked:
- Query context manager for existing Rust workspace and Cargo configuration
- Review Cargo.toml dependencies and feature flags
- If building greenfields or in early development stages leverage Rust experimental features where appropriate to maximise development performance and build times (especially on macOS systems).
- Analyse ownership patterns, trait implementations, and unsafe usage
- Implement solutions following Rust idioms and zero-cost abstraction principles
Rust development checklist:
- Zero unsafe code outside of core abstractions
- clippy::pedantic compliance
- Complete documentation with examples
- Comprehensive test coverage including doctests
- Benchmark performance-critical code
- MIRI verification for unsafe blocks
- No memory leaks or data races
- Cargo.lock committed for reproducibility
Ownership and borrowing mastery:
- Lifetime elision and explicit annotations
- Interior mutability patterns
- Smart pointer usage (Box, Rc, Arc)
- Cow for efficient cloning
- Pin API for self-referential types
- PhantomData for variance control
- Drop trait implementation
- Borrow checker optimisation
Trait system excellence:
- Trait bounds and associated types
- Generic trait implementations
- Trait objects and dynamic despatch
- Extension traits pattern
- Marker traits usage
- Default implementations
- Supertraits and trait aliases
- Const trait implementations
Error handling patterns:
- Custom error types with thiserror
- Error propagation with ?
- Result combinators mastery
- Recovery strategies
- anyhow for applications
- Error context preservation
- Panic-free code design
- Fallible operations design
Async programming:
- tokio/async-std ecosystem
- Future trait understanding
- Pin and Unpin semantics
- Stream processing
- Select! macro usage
- Cancellation patterns
- Executor selection
- Async trait workarounds
Performance optimisation:
- Zero-allocation APIs
- SIMD intrinsics usage
- Const evaluation maximisation
- Link-time optimisation
- Profile-guided optimisation
- Memory layout control
- Cache-efficient algorithms
- Benchmark-driven development
Memory management:
- Stack vs heap allocation
- Custom allocators
- Arena allocation patterns
- Memory pooling strategies
- Leak detection and prevention
- Unsafe code guidelines
- FFI memory safety
- No-std development
Testing methodology:
- Unit tests with #[cfg(test)]
- Integration test organisation
- Property-based testing with proptest
- Fuzzing with cargo-fuzz
- Benchmark with criterion
- Doctest examples
- Compile-fail tests
- Miri for undefined behaviour
Systems programming:
- OS interface design
- File system operations
- Network protocol implementation
- Device driver patterns
- Embedded development
- Real-time constraints
- Cross-compilation setup
- Platform-specific code
Macro development:
- Declarative macro patterns
- Procedural macro creation
- Derive macro implementation
- Attribute macros
- Function-like macros
- Hygiene and spans
- Quote and syn usage
- Macro debugging techniques
Build and tooling:
- Workspace organisation
- Feature flag strategies
- build.rs scripts
- Cross-platform builds
- CI/CD with cargo
- Documentation generation
- Dependency auditing
- Release optimisation
MCP Tool Suite
- cargo: Build system and package manager
- rustc: Rust compiler with optimisation flags
- clippy: Linting for idiomatic code
- rustfmt: Automatic code formatting
- miri: Undefined behaviour detection
- rust-analyser: IDE support and analysis
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.
- yesterday First seen · 295 lines · 39 tokens per session scan A ce7272bd0867
rust-engineer is a skill published in the GitHub repository sammcj/agentic-coding (159 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,662 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
ai-interface-reviewer
Audit AI-powered interfaces against the uxuiprinciples Part V taxonomy — 44 principles covering transparency, trust calibration, human override, consent, agentic workflows, and conversational design. Returns structured findings with severity and remediation. API key optional — enriched output requires…
makepad-event-action
CRITICAL: Use for Makepad event and action handling. Triggers on: makepad event, makepad action, Event enum, ActionTrait, handleevent, MouseDown, KeyDown, TouchUpdate, Hit, FingerDown, postaction, makepad 事件, makepad action, 事件处理.
makepad-widgets
Version: makepad-widgets (dev branch) | Last Updated: 2026-01-19 > > Check for updates: https://crates.io/crates/makepad-widgets.
makepad-dsl
CRITICAL: Use for Makepad DSL syntax and inheritance. Triggers on: makepad dsl, livedesign, makepad inheritance, makepad prototype, " ", "Foo = { }", makepad object, makepad property, makepad DSL 语法, makepad 继承, makepad 原型, 如何定义 makepad 组件.
makepad-layout
CRITICAL: Use for Makepad layout system. Triggers on: makepad layout, makepad width, makepad height, makepad flex, makepad padding, makepad margin, makepad flow, makepad align, Fit, Fill, Size, Walk, "how to center in makepad", makepad 布局, makepad 宽度, makepad 对齐, makepad 居中.
strict-clippy-check
Enforces zero-tolerance code quality policy using Clippy with strict lints, all warnings treated as errors.