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.
git clone --depth 1 https://github.com/mathisk2095/jko-claude-pluginsWrote 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/commands/mathisk2095/jko-claude-plugins/rust-types)<a href="https://agentmods.dev/commands/mathisk2095/jko-claude-plugins/rust-types"><img src="https://agentmods.dev/badge/commands/mathisk2095/jko-claude-plugins/rust-types/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/commands/mathisk2095/jko-claude-plugins/rust-types"><img src="https://agentmods.dev/badge/commands/mathisk2095/jko-claude-plugins/rust-types.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.00761 |
| Opus 5.5 | $0.00014 | $0.00304 |
| Sonnet 5.5 | $0.00007 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
rust-types 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 1mo 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust Types — Strengthen the Domain Model
Push runtime checks into the type system. Every runtime assert!, if !valid, or "this should never happen" comment is a type waiting to be born.
Preparation
- Read the target code and identify the domain concepts.
- Look for primitive types carrying domain meaning (
Stringfor emails,u64for IDs,boolfor states).
Strengthening Steps
Step 1: Find Primitive Obsession
Run in the shell:
rg --type rust 'fn \w+\(.*: (String|&str|u32|u64|i32|i64|bool|f64)' src/ -n | head -30
For each function taking raw primitives that represent domain concepts:
Stringfor an email →struct Email(String)with validation in constructoru64for an ID →struct UserId(u64),struct OrderId(u64)(distinct types!)f64for money →struct Currency { amount: i64, code: CurrencyCode }(never float for money)
Step 2: Replace Booleans with Enums
Run in the shell:
rg --type rust 'fn \w+\(.*: bool' src/ -n
For each boolean parameter:
// Before: process(data, true, false) — what do these mean?
// After:
enum Direction { Forward, Backward }
enum OutputMode { Raw, Formatted }
fn process(data: &Data, dir: Direction, mode: OutputMode)
Step 3: Make Illegal States Unrepresentable
Look for:
- Structs with fields that can be in inconsistent states → use an enum
Option<A>+Option<B>where exactly one must be Some → use an enum- State transitions modeled with mutable fields → use the typestate pattern
// Before: can be in invalid state (title set but no body)
struct Post { title: Option<String>, body: Option<String>, published: bool }
// After: invalid states are compile errors
enum Post {
Draft { title: String },
Review { title: String, body: String },
Published { title: String, body: String, url: Url },
}
Step 4: Validated Constructors
For every newtype, ensure construction goes through validation:
pub struct Email(String);
impl Email {
pub fn new(s: impl Into<String>) -> Result<Self, ValidationError> {
let s = s.into();
if !s.contains('@') { return Err(ValidationError::InvalidEmail); }
Ok(Self(s))
}
}
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.
- 1mo ago First seen · 96 lines · 35 tokens per session scan A 509873b1dbbf
rust-types is a command published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 761 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other commands, from other repositories
rust-review
Rust code review for ownership, safety, and idiomatic patterns.
ccc-python-review
Review changed Python code for security, type safety, error handling, idioms and framework pitfalls, with static analysis results and a merge verdict. Use after editing .py files, before committing Python changes, or when reviewing a Python pull request.
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
codex-review
Run OpenAI Codex code review on current changes or a specific branch/commit.
fec-smell
Diagnose frontend code smells with evidence and candidate refactorings without changing business code.
rust-review
Lightweight Rust code review using clippy.