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 hexagonal_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/hexagonal_review)<a href="https://agentmods.dev/skills/emillindfors/a2a-rs/hexagonal_review"><img src="https://agentmods.dev/badge/skills/emillindfors/a2a-rs/hexagonal_review.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 5.1 | $0.00065 | $0.01147 |
| Opus 5 | $0.00032 | $0.00574 |
| Sonnet 5 | $0.00013 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
hexagonal_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 7d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hexagonal Review (Rust)
Audit a Rust codebase against the ports-and-adapters discipline defined in rules/hexagonal_architecture.md. This skill complements architectural_review (which covers Rust patterns generally) by focusing specifically on layering, boundaries, and dependency direction.
What to inspect
Work through the codebase systematically. For each layer, check:
Domain layer
- Are domain types free of I/O, async runtimes, and framework imports?
- Are domain errors defined with
thiserroras exhaustive enums? - Are invariants enforced at construction (
TryFrom, newtypes) rather than re-validated everywhere? - Does the domain compile with no feature flags enabled?
Port layer
- Is each port a narrow capability trait, not a technology trait?
- Do port method signatures use domain types only — never
reqwest::Response,sqlx::Row,axum::extract::*, rawserde_json::Valueblobs, or generic byte buffers? - Do port return types use the domain error type, not adapter errors or
Box<dyn Error>/anyhow::Error? - Are sync and async variants both warranted? (Don't duplicate by reflex.)
- Is the port trait object-safe only if you actually use
dyndispatch on it? If not, drop the constraint and gain flexibility.
Application / service layer
- Do services depend on port traits only, never on concrete adapter types?
- Are concrete adapters constructed elsewhere (in
main, in a wiring module) and injected into the service? - Is the service free of
#[cfg(feature = "…")]gates? Feature gating belongs at the adapter boundary.
Adapter layer
- Are adapters grouped by technical concern (
transport/,storage/,auth/) rather than by port name? - Does each adapter convert its lower-level errors (
reqwest::Error,sqlx::Error) into the domain error before returning across the port boundary? - Are framework-specific re-exports at the crate root properly
#[cfg(feature = "…")]-gated? - Is there an in-memory adapter for every port, available outside
#[cfg(test)]so downstream users can test against it too?
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.
- 7d ago First seen · 71 lines · 65 tokens per session scan A e3712ca44476
hexagonal_review is a skill published in the GitHub repository EmilLindfors/a2a-rs (87 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 1,147 once invoked, about $0.0003 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…
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…
unsafe-checker
A review guide for unsafe Rust code and foreign-function interfaces, which let Rust call code written in languages such as C. It covers raw pointers, memory layout, `extern` functions, safety comments, and undefined behavior.