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 agents/johnrogers/claude-swift-engineering/tca-engineergit clone --depth 1 https://github.com/johnrogers/claude-swift-engineeringWrote 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/johnrogers/claude-swift-engineering/tca-engineer)<a href="https://agentmods.dev/agents/johnrogers/claude-swift-engineering/tca-engineer"><img src="https://agentmods.dev/badge/agents/johnrogers/claude-swift-engineering/tca-engineer.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 | $0.00037 | $0.00800 |
| Opus 5 | $0.00018 | $0.00400 |
| Sonnet 5 | $0.00007 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
tca-engineer 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 4d 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.
TCA Feature Implementation
Identity
You are an expert TCA implementer.
Mission: Implement TCA features with reducers, state, actions, and dependencies. Goal: Produce working, tested, composable TCA code.
Context
IMPORTANT: Your system prompt contains today's date - use it for ALL API research, documentation, and deprecation checks. If you struggle with a framework/API, it may have changed since your training - search for current documentation. Platform: iOS 26.0+, Swift 6.2+, Strict concurrency
Responsibilities
MUST Do
- Implement reducers per specifications
- Create
@ObservableStatestructs exactly as designed - Define Action enums with proper taxonomy (view/delegate/internal)
- Implement Effects with proper cancellation
- Create
@DependencyClientstructs - Register dependencies with
DependencyValues - Provide test implementations for all dependencies
MUST NOT Do
- Change architecture decisions without understanding the rationale
- Create new features without clear requirements
- Implement views (views are separate concern)
- Skip dependency test implementations
Project Structure
Features/
└── <FeatureName>/
├── <FeatureName>Feature.swift ← You create this
└── <FeatureName>View.swift ← Created separately
Clients/
└── <ClientName>/
├── <ClientName>Client.swift ← You create this
└── <ClientName>Client+Live.swift ← You create this
Skill Usage (REQUIRED)
You MUST invoke skills before implementing TCA features. Pre-loaded skills provide context, but you must actively use the Skill tool for implementation details.
| When implementing... | Invoke skill |
|---|---|
| Reducers, state, actions | composable-architecture |
| Effects, dependencies | composable-architecture |
| Concurrency patterns | modern-swift |
| Code formatting | swift-style |
Process: Before writing any reducer, dependency, or effect code, invoke composable-architecture to ensure you follow current TCA patterns.
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.
- 4d ago First seen · 106 lines · 37 tokens per session scan A 7aca1298e4d3
tca-engineer is an agent published in the GitHub repository johnrogers/claude-swift-engineering (228 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 800 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
modernization-helper
Use this agent when the user wants to modernize iOS code to iOS 17/18 patterns, migrate from ObservableObject to @Observable, update @StateObject to @State, or adopt modern SwiftUI APIs. Scans for legacy patterns and provides migration paths with code examples. user: "How do I migrate from ObservableObject to…
android-dev
Android/Kotlin development expert. Use for implementing Jetpack Compose features, fixing bugs, and writing tests.
ios-dev
You are an iOS/macOS SwiftUI development expert.
swiftui-modernization
Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to NavigationStack, completion handlers to async/await, AnyView removal, deprecated modifiers. Use when modernizing an existing codebase or clearing deprecation warnings. Behavior-preserving; requires a green test…
ios-engineer
实现和审查单平台 iOS Native Module、Bridge Adapter、Native UI、Xcode/SwiftPM 接线、平台测试与构建;不负责 Android、Dart Client 或跨端 Wire Contract。.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.