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 skills add EmilLindfors/a2a-rs --skill architectural_reviewgit clone --depth 1 https://github.com/EmilLindfors/a2a-rsWrote 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/emillindfors/a2a-rs/architectural_review)<a href="https://agentmods.dev/skills/emillindfors/a2a-rs/architectural_review"><img src="https://agentmods.dev/badge/skills/emillindfors/a2a-rs/architectural_review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/emillindfors/a2a-rs/architectural_review"><img src="https://agentmods.dev/badge/skills/emillindfors/a2a-rs/architectural_review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00082 | $0.01024 |
| Opus 5 | $0.00041 | $0.00512 |
| Sonnet 5 | $0.00016 | $0.00205 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
architectural_review 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural Review (Rust)
This skill helps you perform an architectural review of Rust code based on advanced patterns found in the "Rust Patterns & Engineering How-Tos" guide. When asked to review system architecture or suggest broad improvements in a Rust project, apply these architectural patterns: https://microsoft.github.io/RustTraining/rust-patterns-book/
Capability Mixins (Composition over Inheritance)
- Rust doesn't have class inheritance. Instead, use traits with associated types and default method implementations to compose behaviors.
- Define "Ingredient" traits containing primitive operations (e.g.
HasBus { type Bus; fn bus(&self) -> &Self::Bus; }). - Define "Mixin" traits that require ingredient traits as supertraits, and provide default implementations for domain logic (e.g.
trait FeatureMixin: HasBus). - Use blanket implementations (
impl<T: HasBus> FeatureMixin for T {}) so any type with the ingredient automatically gets the mixin behavior at compile time with zero overhead.
Typed Commands (GADT-style Return Types)
- Avoid "Untyped Swamp" signatures where generic byte buffers (
Vec<u8>) are passed around indiscriminately. - Create Domain Newtypes to represent physical/logical constraints strongly (e.g.,
Celsius(f64),Rpm(u32)). - Use a Command Trait where the associated type dictates the specific return type of that command (e.g.,
trait Command { type Response; }). - When a command is executed, its concrete type ensures the correct return format is parsed and returned natively, turning unit-confusion runtime errors into compile-time errors.
Concurrency and Parallelism
- Understand the distinction between concurrency (tasks making progress) and parallelism (simultaneous execution).
- Threads vs. Rayon: Use OS threads (
std::thread::spawn) for long-running background tasks. Userayon::par_iter()for data parallelism when processing collections. Use scoped threads (std::thread::scope) to safely borrow stack variables across short-lived parallel tasks. - Shared State: Use
Mutex<T>for exclusive access in short critical sections. UseRwLock<T>for read-heavy workloads with rare writes. UseAtomicU64and similar atomic types for simple flags/counters to avoid lock overhead. - Message Passing: Prefer
crossbeam-channeloverstd::sync::mpscin production for multi-consumer support and select macros. Use bounded channels to implement backpressure and avoid OOM issues. Employ the Actor pattern with channels to encapsulate complex shared mutable state instead of wrapping everything in a Mutex.
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.
- 10d ago First seen · 47 lines · 82 tokens per session scan A 96ef803a198b
architectural_review is a skill published in the GitHub repository EmilLindfors/a2a-rs (87 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 1,024 once invoked, about $0.0004 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.
Other skills, from other repositories
architecture-audit
Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…
rust-review
A Rust code-review skill for services, checking for crashes, unsafe SQL construction, exposed credentials, ignored errors, and unfinished code.
rust-skills
Comprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, concurrency, unsafe code, API design, memory optimization, performance, numeric safety, conversions, serde, pattern matching, macros…
adversarial-rust
Use this skill when reviewing or refactoring existing Rust code that carries an alien mental model — OO/enterprise ceremony from Java/C#, garbage-collected object graphs, exception-style control flow, or imperative loops ported onto the borrow checker. It is the adversarial, architecture-level counterpart to…
writing-rust
Idiomatic Rust development. Use when writing Rust code, Cargo crates/workspaces, Rust tests, or rustfmt/clippy/cargo workflows. Emphasizes ownership, Result errors, small APIs, stdlib-first dependencies, fast cargo feedback, and behavior tests. NOT for Go, Python, TypeScript, shell scripts, or infra-only work.
m15-anti-pattern
Use when reviewing code for anti-patterns. Keywords: anti-pattern, common mistake, pitfall, code smell, bad practice, code review, is this an anti-pattern, better way to do this, common mistake to avoid, why is this bad, idiomatic way, beginner mistake, fighting borrow checker, clone everywhere, unwrap in production…