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 agentmods add skills/fusengine/agents/rust-async-concurrencynpx skills add fusengine/agents --skill rust-async-concurrencygit 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-async-concurrency)<a href="https://agentmods.dev/skills/fusengine/agents/rust-async-concurrency"><img src="https://agentmods.dev/badge/skills/fusengine/agents/rust-async-concurrency.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 | $0.00057 | $0.01345 |
| Opus 5 | $0.00028 | $0.00673 |
| Sonnet 5 | $0.00011 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00135 |
Grade A, and why
rust-async-concurrency 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 2d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
It also covers the async-fn-in-traits Send problem — why async fn in traits does not give
Send futures by default and how to work around it.
Out of scope: HTTP service structure (routing, extractors, middleware) is owned by rust-web-backend; sync-only ownership and borrowing questions belong to rust-core-language.
Rust Async & Concurrency
Agent Workflow (MANDATORY)
Before writing async code, spawn in parallel:
- fuse-ai-pilot:explore-codebase — find the existing runtime, channel, and lock patterns already in use
- fuse-ai-pilot:research-expert — verify current tokio/crate APIs via Context7/Exa (async APIs churn)
- mcp__context7__query-docs — pull exact signatures for the primitives you touch
After writing, run fuse-ai-pilot:sniper.
Runtime Landscape
| Runtime | Reality |
|---|---|
| tokio | The de-facto standard. Almost every async crate (axum, sqlx, reqwest, tonic) targets it. Default choice. |
| async-std | Niche, effectively in maintenance mode. Do not pick for new work. |
| smol | Niche, small/embeddable. Only for constrained or embedded contexts. |
Default to tokio unless a hard constraint says otherwise.
Critical Rules
std::sync::Mutexfirst — it is faster. Reach fortokio::sync::MutexONLY when the guard must be held across an.await. Otherwise scope the guard so its destructor runs before the await.Arc<Mutex<T>>is not the default — analyze contention first. Read-dominated →RwLock; a simple counter → atomics; work that is itself async → a task + message passing.- Never drop a
JoinHandleyou care about — a droppedtokio::spawnhandle silently swallows the task's panic/error..awaitit, or useJoinSet/tracingto surface failures. spawn_blockingfor heavy sync work — CPU-bound loops or blocking I/O (std file, blocking DB driver) starve the runtime if run on an async worker. Offload them.Sendacross.await— everything held across an await point must beSendfortokio::spawn. Astd::sync::MutexGuardis NOTSend; holding one across an await is a compile error (and async-mutex guards that areSenddeadlock instead).
What ships with it
6 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.
- 2d ago First seen · 128 lines · 57 tokens per session scan A e24f8b84d9fa
rust-async-concurrency is a skill published in the GitHub repository fusengine/agents (25 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,345 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 2026-09-03.
Other skills, from other repositories
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.
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).
phx-document
Generate @moduledoc/@doc for tested Elixir features; may update their README section or ADR. Not for docs lookup, documentation audits/reviews, or capturing standalone decisions.
craftcms
Craft CMS 5 plugin and module development — extending Craft with PHP. Covers elements, element queries, services, models, records, controllers, migrations, queue jobs, console commands, field types, native fields, events, behaviors, Twig extensions, widgets, filesystems, permissions, project config, GraphQL, testing…
craft-php-guidelines
Craft CMS 5 PHP coding standards and conventions. ALWAYS load when writing, editing, reviewing, or discussing any PHP in a Craft plugin or module — even small edits. Also when running ECS, PHPStan, or scaffolding with ddev craft make. Covers: PHPDoc blocks (@author, @since, @throws chains), section headers…