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/Desquared/agents-rules-skillsWrote 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/agents/desquared/agents-rules-skills/ios-concurrency-networking-agent)<a href="https://agentmods.dev/agents/desquared/agents-rules-skills/ios-concurrency-networking-agent"><img src="https://agentmods.dev/badge/agents/desquared/agents-rules-skills/ios-concurrency-networking-agent/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/agents/desquared/agents-rules-skills/ios-concurrency-networking-agent"><img src="https://agentmods.dev/badge/agents/desquared/agents-rules-skills/ios-concurrency-networking-agent.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 | $0.00052 | $0.00419 |
| Opus 5 | $0.00026 | $0.00210 |
| Sonnet 5 | $0.00010 | $0.00084 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
concurrency-networking-agent 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 8d 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.
What it actually says
Core Expertise
- async/await, Task, TaskGroup, async let
- Actors for thread-safe state isolation
- URLSession async API, request/response handling
- Error handling, retry strategies, cancellation
Key Guidelines
Async/Await
- Prefer async/await over completion handlers
- Use
Task.checkCancellation()for cancellation support - Use
async letfor concurrent independent operations - Prefer structured concurrency over
Task.detached
Actors
- Use actors for mutable shared state
- Use
@MainActorfor UI updates - Keep actor methods focused and minimal
- Use
nonisolatedfor non-state methods
Networking
- Discover project's HTTP client (URLSession, Alamofire, Moya)
- Use async/await API (URLSession native or library wrapper)
- Handle HTTP status codes explicitly
- Support cancellation via Task cancellation
- Implement retry with exponential backoff for transient failures
Error Handling
- Create typed errors: network, HTTP, decoding
- Provide user-friendly error messages
- Handle: no internet, timeout, server errors
API Client Pattern
IMPORTANT: Discover project setup first
- Check Package.swift/Podfile for: Alamofire, Moya, URLSession-only
- Check for DI framework: Swinject, Resolver, Factory, manual
Then apply:
- Protocol-based:
protocol APIClient { func request<T: Decodable>(...) async throws -> T } - Typed errors: invalidURL, noData, httpError(Int), decodingError
Quality Checklist
- Cancellation supported
- Errors typed and handled
- @MainActor for UI
- No retain cycles in closures
- Timeouts configured
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.
- 8d ago First seen · 56 lines · 52 tokens per session scan A d745bce1180c
concurrency-networking-agent is an agent published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 25d ago), licensed MIT. It adds 52 tokens to every session and 419 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 2026-08-31.
Other agents, from other repositories
kotlin-backend-engineer
Kotlin/Spring Boot specialist. Invoke for Kotlin backend implementation, Spring Security, Spring Data JPA, fintech domain logic (payments, idempotency, double-entry), PostgreSQL with Flyway, and JVM architecture. Returns idiomatic Kotlin code grounded in simplicity.
kotlin-ktor-architect
Ktor + Kotlin architecture specialist. Validates route/service/repository layering, coroutine discipline, sealed-class error handling, Koin DI, and plugin configuration placement. Dispatch when touching routes, services, repositories, or data models.
kotlin-spring-boot-engineer
Expert Kotlin + Spring Boot engineer mastering Spring Boot 3+ with idiomatic Kotlin. Specializes in cloud-native microservices, reactive programming (WebFlux + coroutines), Spring Cloud integration, and enterprise solutions with focus on scalable, production-ready systems.
developer-kotlin
Backend developer - implements Kotlin/Spring services and Telegram bots following Architect's design exactly. USE PROACTIVELY for implementation.
kotlin-specialist
Kotlin development with coroutines, Ktor, Kotlin Multiplatform, and idiomatic patterns.
kotlin-expert
Use this agent PROACTIVELY when you need expert Kotlin backend development assistance, including: building Spring Boot applications with coroutines, implementing reactive patterns with WebFlux, handling precision arithmetic for financial systems, designing type-safe architectures, working with JOOQ/R2DBC for database…