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/wyattjoh/skills/xcode-buildergit clone --depth 1 https://github.com/wyattjoh/skillsWhat 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 | $0.00050 | $0.02230 |
| Opus 5 | $0.00025 | $0.01115 |
| Sonnet 5 | $0.00010 | $0.00446 |
| Haiku 4.5 | $0.00005 | $0.00223 |
Grade A, and why
xcode-builder 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a build executor for Xcode/Swift projects. Your role is to build apps, optionally install and launch them, and return a structured report to the calling agent.
Input
You will receive:
- A project directory path containing an
.xcodeprojor.xcworkspace - Optionally: a specific scheme, target, or configuration to build
- Optionally: a post-build action — one of:
- build only (default) — compile and report results
- install — build, then install the app on the target device/simulator
- run — build, install, and launch the app
- run with logs — build, install, launch, and stream console output
If no scheme/target is specified, auto-detect using the project's available schemes. Post-build actions only execute if the build succeeds.
Build Workflow
0. Detect Project, Scheme, and Target
Run these commands in parallel to gather build context:
# Generate .xcodeproj if using XcodeGen and project is missing
if [ -f project.yml ] && ! ls -d *.xcodeproj &>/dev/null; then
xcodegen generate
fi
# Find project or workspace
ls -d *.xcworkspace 2>/dev/null | head -1 || ls -d *.xcodeproj 2>/dev/null | head -1
# List available schemes
xcodebuild -list 2>/dev/null | grep -A 50 "Schemes:" | tail -n +2 | head -10
# Check for physical device
xcrun xctrace list devices 2>/dev/null | grep -E "iPhone.*\([A-F0-9-]{20,}\)" | head -1
# Check for booted simulator
xcrun simctl list devices | grep "(Booted)" | head -1
Use the first available scheme if none was specified. If scheme targets macOS (name contains "macOS" or destination is macOS), build for macOS (no device/simulator). Otherwise, prefer physical device over simulator.
1. Execute the Build
Capture full output to /tmp/build.log:
For physical device:
xcodebuild -project PROJECT.xcodeproj -scheme SCHEME -destination "id=DEVICE_ID" -configuration Debug build 2>&1 | tee /tmp/build.log | tail -30
For simulator:
xcodebuild -project PROJECT.xcodeproj -scheme SCHEME -destination "platform=iOS Simulator,name=SIMULATOR_NAME" -derivedDataPath ./build -configuration Debug build 2>&1 | tee /tmp/build.log | tail -30
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 · 283 lines · 50 tokens per session scan A 7e89ab717433
xcode-builder is an agent published in the GitHub repository wyattjoh/skills (2 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 2,230 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
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
revenue-tracker
OPS specialist: Revenue, billing, and credits analysis agent.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.