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/debugswift/xcodebazelmcp/simulator-workflownpx skills add DebugSwift/XcodeBazelMCP --skill simulator-workflowgit clone --depth 1 https://github.com/DebugSwift/XcodeBazelMCPWhat 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 | $0.00040 | $0.00699 |
| Opus 5 | $0.00020 | $0.00349 |
| Sonnet 5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
simulator-workflow scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
6. **Read bundle ID** — `plutil -convert json -o -` on `Info.plist` (sync `execSync`) How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simulator Workflow
Build + Run + Launch Chain
The bazel_ios_build_and_run tool chains these steps (each failure short-circuits):
- Build —
bazel build <target> - Find app — search
bazel-bin/using target label's package path - Resolve simulator — priority: explicit UDID > name match > first booted > first available iPhone > first available device
- Boot — lazy, only
simctl bootif state !=Booted - Install —
simctl install <udid> <app_path> - Read bundle ID —
plutil -convert json -o -onInfo.plist(syncexecSync) - Launch —
simctl launch <udid> <bundleId>
App Bundle Discovery
- After
bazel build, searchbazel-bin/using the target label's package path. - Target
//:Foo→bazel-bin/Foo.app,//Apps/Bar:Bar→bazel-bin/Apps/Bar/Bar.app. rules_appleplaces bundles inside<target>_archive-root/Payload/—findAppBundlesearches recursively.
Simulator Resolution
resolveSimulator returns { device: SimulatorDevice; warning?: string }:
warningis set when the resolved simulator is not the explicitly requested one (fallback).resolveSimulatorFromArgsinhelpers.tsis the convenience wrapper — returns{ sim, warning }.prependWarning(message, warning)prepends the warning to tool output.
Launch Environment Variables
Env vars are passed via SIMCTL_CHILD_* prefix convention — simctl forwards them to the launched process.
For Cursor DEBUG MODE (NDJSON hypothesis logs), use the swift-agent-debug-log skill and bazel_ios_agent_debug_* tools:
AGENT_DEBUG_LOG_PATH/AGENT_DEBUG_SESSION_IDvialaunchEnvonbuild_and_runoragent_debug_repro- Simulator fallback:
Documents/agent-debug.ndjson+bazel_ios_agent_debug_log_pull - Do not rely on the sim app writing directly to
.cursor/debug-*.logon the host
Platform CPU Flags
| Platform | Flag |
|---|---|
| iOS simulator | --ios_multi_cpus=sim_arm64 |
| iOS device | --ios_multi_cpus=arm64 |
| macOS | (none — host arch) |
| tvOS | --tvos_cpus=sim_arm64 |
| watchOS | --watchos_cpus=arm64 |
| visionOS | --visionos_cpus=sim_arm64 |
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 · 60 lines · 40 tokens per session scan A 618cbaadf51c
simulator-workflow is a skill published in the GitHub repository DebugSwift/XcodeBazelMCP (7 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 699 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
test
Run tests. Use after code changes to validate. Arguments: unit (default, no GPU), e2e (with models), filter name, or all.
boutique-store
Create and use Boutique Store for Swift data persistence, including initialization, @Stored controllers, CRUD operations, operation chaining, and granular event monitoring. Use when persisting arrays of items, building data controllers, or working with Boutique's Store type.
boutique-stored-values
Persist individual values with Boutique's @StoredValue (UserDefaults) and @SecurelyStoredValue (Keychain), including set, reset, toggle, bindings, keypath setters, array and dictionary helpers, and async observation. Use when storing preferences, settings, feature flags, or sensitive data like auth tokens.
boutique-swiftui
Integrate Boutique with SwiftUI views using onChange, onStoreDidLoad, bindings, and preview stores. Use when building SwiftUI views that display or react to Boutique-persisted data.
analyze-db-logs
Analyze Drift / SQLite slow-query and super-slow-query logs against this app's known stall patterns (read waves, N+1, transaction scoping, MultiExecutor contention, WAL/OS factors).
review-comments
Fetch PR review comments, address each one in code, and post resolution replies.