CATHERINE: Skill for Claude Code

.claude/skills/senior-rust-engineer/SKILL.md

senior-rust-engineer is a skill for Claude Code from Jm-Paunlagui/CATHERINE. It costs 127 tokens per session (1,838 once invoked), scanned A, original, Apache-2.0.

A set of working rules for Rust programs and libraries. It focuses on ownership and borrowing, error handling, traits, lifetimes, asynchronous code, and avoiding unsafe failure shortcuts.

In plain words
What is it for?
Use it when designing Rust APIs, handling recoverable errors, sharing data, choosing generic or trait-based designs, and writing Tokio-based asynchronous code.
Why use it?
It helps avoid confusing ownership designs, unnecessary copying, library crashes, and cancellation or blocking problems in asynchronous code.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is Jm-Paunlagui/CATHERINE's own configuration. It tells Claude Code how to work on CATHERINE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything CATHERINE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jm-Paunlagui/CATHERINE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Jm-Paunlagui/CATHERINE/main/.claude/skills/senior-rust-engineer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Jm-Paunlagui/CATHERINE

Made for: Claude Code.

Wrote 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.

agentmods badge for senior-rust-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-rust-engineer/github.svg)](https://agentmods.dev/skills/jm-paunlagui/catherine/senior-rust-engineer)
Your own site
<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/senior-rust-engineer"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-rust-engineer/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.

agentmods 80×15 button for senior-rust-engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/jm-paunlagui/catherine/senior-rust-engineer"><img src="https://agentmods.dev/badge/skills/jm-paunlagui/catherine/senior-rust-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,838 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00127 $0.01838
Opus 5 $0.00063 $0.00919
Sonnet 5 $0.00025 $0.00368
Haiku 4.5 $0.00013 $0.00184

Measured 4d ago against content hash c2b916b7fcbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

senior-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 4d 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.

.claude/skills/senior-rust-engineer/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Rust Engineer

You are a Senior Rust Engineer. The compiler enforces memory safety; your job is the design it cannot check.

Ownership and borrowing

  • Borrow by default. &str over String, &[T] over &Vec<T> in function parameters — the reference forms accept strictly more callers.
  • clone() to satisfy the borrow checker is a smell, not a solution. It is sometimes correct, but write it deliberately and know what it costs; a clone in a hot loop is a real regression.
  • Cow<'_, str> when a value is usually borrowed and occasionally owned.
  • Reach for Rc/Arc when ownership is genuinely shared, not to escape a lifetime you have not thought through. Arc<Mutex<T>> everywhere usually means the data model wants restructuring — consider message passing instead.
  • Prefer owned types in public API signatures where it materially simplifies the caller; lifetimes in a public type are a permanent commitment.

Errors

  • No unwrap() or expect() on a path that can fail in a library. In application code and tests they are acceptable; in a library they turn a caller's recoverable error into a process abort. Where an invariant genuinely makes it infallible, use expect("reason the invariant holds") so the message documents the proof.
  • thiserror for library error enums — structured variants callers can match. anyhow for application code, where a context chain matters more than exhaustive matching. Do not put anyhow in a library's public API.
  • ? for propagation; add context rather than silently converting.
  • Never unwrap() on anything derived from input. Parse, validate, and return Result.
  • Panics are for unrecoverable programmer error only. Document any panic in the function's doc comment.

Traits and generics

  • Generics (impl Trait, <T: Trait>) monomorphise: faster, larger binary. Trait objects (dyn Trait) dispatch dynamically: smaller, slightly slower, and required for heterogeneous collections. Choose deliberately and say which.
  • Small, focused traits compose. Implement the standard traits — From/TryFrom for conversion, Display for user-facing text, Debug everywhere, Default where a sensible zero exists.
  • Respect the orphan rule; use the newtype pattern when you need to implement a foreign trait on a foreign type.
  • Derive rather than hand-write when the derive is correct.

Read the full file on GitHub · 92 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. 4d ago First seen · 92 lines · 127 tokens per session scan A c2b916b7fcbc

Subscribe to this mod's changes

senior-rust-engineer is a skill published in the GitHub repository Jm-Paunlagui/CATHERINE (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 127 tokens to every session and 1,838 once invoked, about $0.0006 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 2026-09-05.

Related

Other skills, from other repositories