ax-concurrency

ax-concurrency is a skill for Claude Code from Kasempiternal/axiom-v2. It costs 40 tokens per session (4,445 once invoked), scanned A, original, MIT.

A guide to Swift’s tools for doing work asynchronously and safely across multiple tasks, including async/await, actors, and rules for sharing data between tasks.

In plain words
What is it for?
Use it when moving work off the main thread, protecting shared state, checking whether values can cross task boundaries, or adopting Swift 6 concurrency features.
Why use it?
It helps keep slow network or file work from freezing the interface while avoiding unsafe access to shared data. It also describes a gradual way to adopt Swift 6 concurrency checks.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the axiom plugin — 40 skills, 8 commands, 12 agents, 2 hooks shipped together

Good fit Use it when moving work off the main thread, protecting shared state, checking whether values can cross task boundaries, or adopting Swift 6 concurrency features.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kasempiternal/axiom-v2/ax-concurrency
Install

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.

Any agent
npx skills add Kasempiternal/axiom-v2 --skill ax-concurrency
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/axiom-v2

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 40 skills, 8 commands, 12 agents, 2 hooks.

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 ax-concurrency

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/axiom-v2/ax-concurrency/github.svg)](https://agentmods.dev/skills/kasempiternal/axiom-v2/ax-concurrency)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/axiom-v2/ax-concurrency"><img src="https://agentmods.dev/badge/skills/kasempiternal/axiom-v2/ax-concurrency/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 ax-concurrency

Your own site · 80×15
<a href="https://agentmods.dev/skills/kasempiternal/axiom-v2/ax-concurrency"><img src="https://agentmods.dev/badge/skills/kasempiternal/axiom-v2/ax-concurrency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00040 $0.04445
Opus 5.5 $0.00016 $0.01778
Sonnet 5.5 $0.00008 $0.00889
Haiku 4.5 $0.00004 $0.00445

Measured 2mo ago against content hash 325055205856, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ax-concurrency scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return try context.fetch(FetchDescriptor<Track>(
axiom-plugin/skills/ax-concurrency/SKILL.md · 616 lines

How it starts

The opening of the file, as written. The whole thing — 616 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Concurrency

Quick Patterns

Progressive Journey (Start Simple)

Single-Threaded → Asynchronous → Concurrent → Actors
     |                |             |           |
   Start here    Hide latency   Background   Move data
                 (network)      CPU work     off main

Advance only when profiling proves it's needed.

  1. Stay single-threaded if UI is responsive and operations are fast (<16ms)
  2. Add async/await when high-latency operations (network, file I/O) block UI
  3. Add @concurrent when CPU-intensive work freezes UI (image processing, parsing)
  4. Add actors when too much main actor code causes contention

Main Actor Mode (Xcode 26+)

Build Settings → Swift Compiler — Language
→ "Default Actor Isolation" = Main Actor
→ "Approachable Concurrency" = Yes

Build Settings → Swift Compiler — Concurrency
→ "Strict Concurrency Checking" = Complete

All code protected by @MainActor by default unless explicitly marked otherwise.

Async/Await (Hide Latency)

// Suspends without blocking main thread
func fetchAndDisplay(url: URL) async throws {
    let (data, _) = try await URLSession.shared.data(from: url)  // Suspends here
    let image = decodeImage(data)  // Resumes on main thread
    view.displayImage(image)
}

// Create task for user action
func onTapEvent() {
    Task {
        do {
            try await fetchAndDisplay(url: url)
        } catch {
            displayError(error)
        }
    }
}

@concurrent (Background CPU Work, Swift 6.2+)

// Always runs on background thread pool
@concurrent
func decodeImage(_ data: Data) async -> UIImage {
    // Image processing, parsing, heavy computation
    return UIImage(data: data)!
}

// Usage - automatically offloads
let image = await decodeImage(data)

Use @concurrent when work should always run on background (image processing, parsing). Use nonisolated when caller decides where work runs (library APIs).

@MainActor for UI Code

Read the full file on GitHub · 616 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. 2mo ago First seen · 616 lines · 40 tokens per session scan A 325055205856

Subscribe to this mod's changes

ax-concurrency is a skill published in the GitHub repository Kasempiternal/axiom-v2 (4 stars, last pushed 8mo ago), licensed MIT. It adds 40 tokens to every session and 4,445 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

ax-concurrency compared with skills from other repositories

ax-concurrency next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ax-concurrencyKasempiternal/axiom-v2Skill48mo agoMITA40Claude Code
swift-expertpersonamanagmentlayer/pclSkill4411d agoApache-2.0A76Claude Code
ios-expertpersonamanagmentlayer/pclSkill4411d agoApache-2.0A64Claude Code
swift-architecture-skillefremidze/swift-architecture-skillSkill811mo agoMITA65Claude Code
antigravity-roottqtuan1201/TTBaseUIKitSkill233mo agoMITA57Claude Code, Codex
swiftmiles990/claude-software-skillsSkill269mo agoMITA11Claude Code, Codex
swiftui-whats-new-27superagents-lab/xcode27-skillsSkill3615mo agononeA566Claude Code, Codex