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 instructions/xopoko/build-swift-apps/agents-mdgit clone --depth 1 https://github.com/Xopoko/build-swift-appsWrote 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/instructions/xopoko/build-swift-apps/agents-md)<a href="https://agentmods.dev/instructions/xopoko/build-swift-apps/agents-md"><img src="https://agentmods.dev/badge/instructions/xopoko/build-swift-apps/agents-md.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 | $0.01023 | $0.01023 |
| Opus 5 | $0.00511 | $0.00511 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
build-swift-apps AGENTS.md 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 6d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidance
This repository is a multi-agent skill pack for Swift and Apple-platform development. It should stay generic, public-safe, and useful across Codex, Claude Code, Cursor, pi, and manual skill installs.
Project Shape
skills/contains installable Agent Skills. Each directory must contain oneSKILL.mdentrypoint and any local scripts or references that skill needs.shared/contains canonical support files used by multiple skills. Link to shared files instead of duplicating long guidance.references/contains plugin-level audits, ledgers, and routing notes that should not live in hot skill files.commands/contains short command entrypoints that delegate to canonical skills..codex-plugin/,.claude-plugin/,.cursor-plugin/,agents/, andpackage.jsonare packaging surfaces for different agents. Keep them in sync when skills are added or removed.docs/INSTALL.mdis the user-facing installation and dependency guide.scripts/doctor.sh,scripts/install-deps.sh, andscripts/validate-package.share the operational checks for new machines and release hygiene.
Scope
The plugin is for Swift application development across Apple platforms, with the deepest coverage for iOS and macOS. Do not add private/internal workflows, private service names, project names, or credentials. Keep examples generic and reusable.
Skill Catalog
| Area | Skills |
|---|---|
| Router | build-swift-apps |
| Build, run, debug, test | macos-runtime-debugger, macos-swiftpm-runner, macos-test-diagnoser, xcode-ui-test-stabilizer, macos-telemetry-probe |
| iOS simulator and runtime evidence | ios-simulator-browser, ios-simulator-debugger, ios-rocketsim-operator, ios-ettrace-profiler, ios-memgraph-inspector, swiftui-performance-inspector |
| SwiftUI, AppKit, and product UI | ios-swiftui-architect, macos-swiftui-architect, swiftui-view-architect, macos-view-architect, macos-appkit-bridge, macos-window-architect, ios-intents-architect, macos-liquid-glass-designer, ios-liquid-glass-designer |
| Xcode build performance | xcode-build-strategist, xcode-build-baseline, xcode-compile-profiler, xcode-project-auditor, swiftpm-build-inspector, xcode-build-tuner |
| Release and distribution | app-icon-studio, macos-signing-inspector, macos-notarization-packager, and the appstore-* App Store Connect skills |
| Tuist and generated projects | tuist-migration-planner, tuist-workspace-navigator, tuist-generation-doctor, tuist-flaky-test-stabilizer |
| Research and low-level Apple work | apple-dev-research, apple-firmware-inspector |
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.
- 6d ago First seen · 85 lines · 1,023 tokens per session scan A 6d507d6319cc
build-swift-apps AGENTS.md is an instructions file published in the GitHub repository Xopoko/build-swift-apps (45 stars, last pushed 8d ago), licensed MIT. It adds 1,023 tokens to every session, about $0.0051 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 instructions, from other repositories
ios-agent-skill CLAUDE.md
Instructions for Nagarjuna2997/ios-agent-skill, covering ios agent skill — claude ai expert ios/swift developer, when to load this skill, loading the right document, how these docs are structured and how you operate: delegation, loops, and verification.
ios-agent-skill GEMINI.md
Instructions for Nagarjuna2997/ios-agent-skill, covering ios agent skill — claude ai expert ios/swift developer, when to load this skill, loading the right document, how these docs are structured and how you operate: delegation, loops, and verification.
uikit-expert-skill CLAUDE.md
Claude Code instructions for zinxj/uikit-expert-skill, a project described as: Provide accurate, efficient, and modern UIKit Swift code using an AI agent skill focused on best practices and performance optimization.
MarkdownView AGENTS.md
Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.
compose-android-template CLAUDE.md
Claude Code instructions for ashtanko/compose-android-template, a project described as: 📱 A simple GitHub template to quickly set up an Android project using Kotlin and Jetpack Compose, getting you up and running in just seconds. Perfect for starting new apps with modern Android UI.
intentflow-ios AGENTS.md
Instructions for emrecanozturk/intentflow-ios, covering agent instructions, read first, architecture rules, commands and token budget.