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/patrickserrano/lacquer/ios-debugger-agentnpx skills add patrickserrano/lacquer --skill ios-debugger-agentgit clone --depth 1 https://github.com/patrickserrano/lacquerWrote 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/skills/patrickserrano/lacquer/ios-debugger-agent)<a href="https://agentmods.dev/skills/patrickserrano/lacquer/ios-debugger-agent"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/ios-debugger-agent.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 | $0.00042 | $0.01636 |
| Opus 5 | $0.00021 | $0.00818 |
| Sonnet 5 | $0.00008 | $0.00327 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
ios-debugger-agent 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Debugger Agent
Build and run iOS projects on a booted simulator, interact with the UI, and capture logs for debugging — via the flowdeck skill, which is this lacquer's canonical source of truth for exact FlowDeck syntax. This skill is a thin, scenario-specific wrapper around it, not a competing source of commands. If a command below errors or you're unsure of a flag, consult flowdeck's resources/ docs or run flowdeck <command> --help rather than guessing — never fall back to xcrun/simctl/xcodebuild.
Overview
FlowDeck ties build, install, and launch together (flowdeck run), and streams logs from the running app rather than querying the OS unified log. There is no need to discover DerivedData paths, hand-construct xcodebuild destinations, or spawn log stream predicates — FlowDeck's config-first workflow and app-tracking model replace all of that.
Prerequisites
- FlowDeck CLI installed (
flowdeck --version) - Project with
.xcodeprojor.xcworkspace - A saved FlowDeck config, or enough context to create one (
flowdeck context --json)
Core Workflow
1) Check for a saved config first
flowdeck config get --json
If a config exists, use bare commands (flowdeck build, flowdeck run, etc.) for the rest of this workflow. If not, discover and create one:
flowdeck context --json
flowdeck config set -w <workspace> -s <scheme> -S "<simulator>"
2) Discover the booted simulator (if you need a specific one)
flowdeck simulator list --json
Check each entry's state field for "Booted". If none are booted and you need a specific device, boot one by UDID (boot takes a UDID, not a name):
flowdeck simulator boot <udid>
3) Build the project
flowdeck build
Add -w <workspace> -s <scheme> -S "<simulator>" only if no config is saved and you're not overriding it.
4) Install and launch the app
flowdeck run
This builds, installs, and launches in one step, returning an App ID. To launch an existing build without rebuilding:
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 · 147 lines · 42 tokens per session scan A e4501dbe665e
ios-debugger-agent is a skill published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,636 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 2026-09-03.
Other skills, from other repositories
install-mimi-remote
安装、配置、配对、迁移、升级、诊断、回滚或卸载 Mimi Remote；在 macOS 上安装和维护 Mimi Remote Mac 菜单栏 App / DMG，或通过 Homebrew、Linux user-systemd 部署 agentd；从源码构建 iPhone/iPad App；配置 Codex 主通道和可选 Claude Code 实验 Runtime。用户提出“安装 Mimi Remote”“安装或修复 Mac 菜单栏 App”“在 iPad/iPhone 上使用 Codex 或 Claude Code”“部署、迁移或修复 agentd”“升级、回滚、卸载 Mimi Remote”“构建 MimiRemote iOS…
install-mimi-remote
安装、配置、配对、迁移、升级、诊断、回滚或卸载 Mimi Remote；在 macOS 上安装和维护 Mimi Remote Mac 菜单栏 App / DMG，或通过 Homebrew、Linux user-systemd 部署 agentd；从源码构建 iPhone/iPad App；配置 Codex 主通道和可选 Claude Code 实验 Runtime。用户提出“安装 Mimi Remote”“安装或修复 Mac 菜单栏 App”“在 iPad/iPhone 上使用 Codex 或 Claude Code”“部署、迁移或修复 agentd”“升级、回滚、卸载 Mimi Remote”“构建 MimiRemote iOS…
flutter-cherry-pick
How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel. Only use for flutter/flutter landed pull requests. Only use when the cherry pick request is into "stable", "beta" or a branch that has the format with flutter- . -candidate.0.
upgrade-browser
Upgrade browser versions (Chrome or Firefox) in the Flutter Web Engine and/or Framework tests. Use when asked to roll or upgrade Chrome or Firefox to a newer version.
run-devicelab-with-led
Run DeviceLab tests for Flutter PRs using LUCI's led CLI tool. Use when asked to run, launch, try, or deflake a post-submit or devicelab test against a PR using led.
natural-writing
Contains well-defined rules for creating natural, accurate, and readable writing. Use whenever authoring longer text, like analysis documents, PR or CL descriptions, or documentation.