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/sjungling/sjungling-claude-pluginsWrote 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/commands/sjungling/sjungling-claude-plugins/build-and-sim)<a href="https://agentmods.dev/commands/sjungling/sjungling-claude-plugins/build-and-sim"><img src="https://agentmods.dev/badge/commands/sjungling/sjungling-claude-plugins/build-and-sim/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/commands/sjungling/sjungling-claude-plugins/build-and-sim"><img src="https://agentmods.dev/badge/commands/sjungling/sjungling-claude-plugins/build-and-sim.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 | $0.00014 | $0.01154 |
| Opus 5 | $0.00007 | $0.00577 |
| Sonnet 5 | $0.00003 | $0.00231 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade C, and why
build-and-sim scanned grade C 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **Stale cache**: `rm -rf ~/Library/Developer/Xcode/DerivedData/*` and rebuild (use sparingly). How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build the current Xcode project and run it in an iOS/iPadOS simulator, selecting the simulator intelligently based on availability and project preferences.
Important: Run all xcodebuild commands as background tasks. Builds can take significant time (30s–5m+). Use Bash with run_in_background: true to avoid blocking. Poll for completion and capture output for error analysis.
Workflow
Step 1: Find the Project
Look for .xcworkspace (preferred) or .xcodeproj in the current directory. If multiple exist, ask the user which to use.
Step 2: Find the Scheme
List schemes:
xcodebuild -workspace <workspace> -list -quiet
# or
xcodebuild -project <project> -list -quiet
If $1 is provided, use it. Otherwise, if multiple schemes exist, ask the user.
Step 3: Determine Preferred Simulator
Check for a simulator preference declared in the project's CLAUDE.md (and any imported memory files). Look for patterns like:
- "simulator: iPhone 15 Pro"
- "preferred simulator", "default simulator", "test on"
- Any explicit simulator device name (e.g., "iPad Pro 13-inch (M4)")
Capture the preferred simulator name if found.
Step 4: Discover Available Simulators
xcrun simctl list devices available -j
Parse the JSON to build a list of available simulators grouped by runtime (iOS / iPadOS). Only include devices where isAvailable is true.
Step 5: Select the Simulator
Apply this decision tree:
- Preferred simulator found in CLAUDE.md AND available → use it.
- Preferred simulator found but NOT available → use
AskUserQuestionto prompt the user. Present 3–5 available simulators as options (prioritize devices matching the preferred family — e.g., if preference was "iPhone 15 Pro", offer other iPhones first; for iPads, offer iPads). Include the preferred name in the question context so the user knows why we're asking. - No preferred simulator in CLAUDE.md → pick a sensible default (most recent iPhone on the latest iOS runtime) and proceed. If ambiguous (e.g., iPad-only project), ask the user.
- No simulators available at all → try to install one via the CLI:
Offer the user 2–3 options from the most recent iOS/iPadOS releases (query available runtimes viaxcodebuild -downloadPlatform iOS # or list installable runtimes: xcrun simctl runtime list -vxcrun simctl list runtimes availableandxcodebuild -downloadAllPlatforms -exportPathhints). If CLI installation isn't possible in this environment, instruct the user to open Xcode → Settings → Platforms and install a simulator runtime manually, then re-run the command.
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.
- 11d ago First seen · 112 lines · 14 tokens per session scan C cdf72d8b59cd
build-and-sim is a command published in the GitHub repository sjungling/sjungling-claude-plugins (13 stars, last pushed 27d ago), licensed MIT. It adds 14 tokens to every session and 1,154 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
initialize-ios
Manual override: initialize ast-index for iOS/Swift/ObjC project.
maestro-selectors-instructions
Guide to using Maestro selectors for targeting UI elements in tests.
mobile-performance-check
Analyze mobile app for performance issues using the mobile-best-practices database.
flutter-review
Review Flutter/Dart code for idiomatic patterns, widget best practices, state management, performance, accessibility, and security. Invokes the flutter-reviewer agent.
flutter-test
Run Flutter/Dart tests, report failures, and incrementally fix test issues. Covers unit, widget, golden, and integration tests.