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 fusengine/agents --skill rust-core-languagegit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/rust-core-language)<a href="https://agentmods.dev/skills/fusengine/agents/rust-core-language"><img src="https://agentmods.dev/badge/skills/fusengine/agents/rust-core-language/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/fusengine/agents/rust-core-language"><img src="https://agentmods.dev/badge/skills/fusengine/agents/rust-core-language.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 | $0.00058 | $0.01436 |
| Opus 5.5 | $0.00023 | $0.00574 |
| Sonnet 5.5 | $0.00012 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
rust-core-language 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 22d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
It also covers correcting the recurring failure modes of machine-generated Rust: the clone tax (cloning to silence the borrow checker instead of redesigning ownership), unwrap/expect infestation, String vs &str misuse, indexed loops instead of iterators, and over-annotated lifetimes the compiler could elide.
Out of scope: error-type design (thiserror vs anyhow) belongs to rust-error-handling; async runtime questions belong to rust-async-concurrency; SOLID/file-layout rules belong to fuse-solid:solid-rust.
Rust Core Language
Idiomatic Rust for stable 1.98.1, edition 2024. This skill covers what the compiler will not catch for you: ownership design that avoids gratuitous cloning, and the recurring failure modes of machine-generated Rust.
Agent Workflow (MANDATORY)
- fuse-ai-pilot:research-expert — confirm the current stable version and any feature's stabilization release before relying on it (versions move fast).
- fuse-ai-pilot:explore-codebase — read the crate's
editioninCargo.tomland its existing ownership conventions before adding code. - After writing code, run fuse-ai-pilot:sniper and
cargo clippy.
Never state a stabilization version from memory — verify against
doc.rust-lang.org/releases.html.
Overview
| Topic | When |
|---|---|
| Edition 2024 features | Setting up a crate, using let chains / async closures |
| Ownership & borrowing | Designing function signatures and data flow |
| LLM pitfalls | Reviewing or repairing generated Rust before merge |
Critical Rules
- Borrow before you own. Take
&T/&str/&[T]in parameters unless the function must keep the value. See ownership-borrowing.md. .clone()needs a reason. A clone to silence a borrow-checker error is a design smell (the "clone tax"). Redesign ownership first; clone only when a second owner genuinely exists.- No
.unwrap()/.expect()on fallible values without a written justification. Grep for them before merge. Prefer?,match, or a documented invariant. Arc::clone(&x)overx.clone()for reference-counted handles — it makes the cheap pointer-copy explicit and distinguishes it from a deep clone.- Iterators over indexed loops. Prefer
iter()/map()/filter()/collect()tofor i in 0..len { v[i] }— no bounds-check noise, no off-by-one. - Let elision work. Do not annotate lifetimes the compiler can infer.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago Changed · +6 lines 100bffed4e3d
- 1mo ago First seen · 100 lines · 58 tokens per session scan A a7a6287df832
rust-core-language is a skill published in the GitHub repository fusengine/agents (33 stars, last pushed 7d ago), licensed MIT. It adds 58 tokens to every session and 1,436 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
polars
High-performance DataFrame library for Python ETL, analytics, and pandas migration. It supports expression-based data manipulation with lazy query optimization, parallel execution, streaming out-of-core processing, Arrow interoperability, and optional GPU execution.
pinocchio-development
Comprehensive guide for building high-performance Solana programs using Pinocchio - the zero-dependency, zero-copy framework. Covers account validation, CPI patterns, optimization techniques, and migration from Anchor.
building-telegram-bots
Writes correct, version-aware Telegram bot code. Use when writing, extending, or debugging a Telegram bot in python-telegram-bot, aiogram, grammY, or Telegraf. Not for Telegram client API (TDLib), languages other than Python and Node.js, or non-Telegram platforms.
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
architect
Design the idiomatic Elixir architecture for a rewrite: set the compatibility bar (ADR-000), consult phx specialists on open questions, then build contexts, ledger and ADRs. Use after /rewrite:analyze.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).