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/projanvil/mindforge/swift-developmentnpx skills add ProjAnvil/MindForge --skill swift-developmentgit clone --depth 1 https://github.com/ProjAnvil/MindForgeWhat 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 | $0.00059 | $0.00686 |
| Opus 5 | $0.00030 | $0.00343 |
| Sonnet 5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00069 |
Grade A, and why
swift-development 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 yesterday.
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift 6 Development Skill
Instructions
Follow this guide when working on non-UI Swift code, business logic, algorithms, or the data layer. Your goal is to write high-performance, thread-safe, and expressive Swift code.
What This Skill Does
- Concurrent Programming: Write safe concurrent code using Actors, async/await, Task, and TaskGroup.
- Type Safety: Define Sendable types and use Typed Throws for precise error handling.
- Testing: Write modern unit tests using the Swift Testing framework.
- Data Processing: Write Codable models and encapsulate JSON parsing and network requests.
- Macros: Use or create macros to reduce boilerplate.
When to Use This Skill
- When writing ViewModel, Service, or Repository layer code.
- When defining data models (structs, enums).
- When implementing algorithms or utility functions.
- When writing unit tests.
- When fixing concurrency warnings or data races.
Examples
Example 1: Defining a Safe Actor Service
/// A thread-safe user data service
actor UserService {
private var cache: [String: User] = [:]
// Use typed throws to specify the error type explicitly
func fetchUser(id: String) async throws(NetworkError) -> User {
if let cached = cache[id] {
return cached
}
// Simulate network request
let user = try await NetworkClient.shared.get("/users/\(id)", as: User.self)
cache[id] = user
return user
}
}
Example 2: Testing with Swift Testing
import Testing
@testable import MyApp
@Test("User parsing should succeed")
func userParsing() async throws {
let json = """
{ "id": "1", "name": "Alice" }
""".data(using: .utf8)!
let user = try JSONDecoder().decode(User.self, from: json)
#expect(user.name == "Alice")
#expect(user.id == "1")
}
Best Practices
- Conform to Sendable: Any type passed between concurrency domains must conform to the
Sendableprotocol. - Avoid Global Mutable State: Avoid global variables unless protected by an Actor.
- Implicitly Unwrapped Optionals: Strictly forbidden (the force unwrap operator), except where unavoidable in initializers (very rare).
- Use
letovervar: Default to constants; use variables only when necessary. - Error Handling: Prefer
throwsanddo-catchover returningOptionalorResulttypes (throws is more natural in async contexts).
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.
- yesterday First seen · 82 lines · 59 tokens per session scan A e9ae75bd9429
swift-development is a skill published in the GitHub repository ProjAnvil/MindForge (3 stars, last pushed 5mo ago), licensed MIT. It adds 59 tokens to every session and 686 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 skills, from other repositories
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
debugging-mutations
Verify what changed on a ServiceNow instance after a tool call — sysaudit inspection, syslog/transaction logs, session context, Flow Designer execution logs, outbound HTTP traces.
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).