What is RunCue CLAUDE.md?

Repository instructions for RunCue, a tool that lets developers navigate and inspect an iOS app's interface using natural language after Xcode has built and launched it.

Use them when developing or maintaining RunCue, especially for building, testing, launching, clicking, scrolling, entering text, and checking screens on an iOS device.

They provide the project structure, development commands, and rules for dividing app building from interface control. This reduces confusion about which tool handles each part of iOS testing.

How lihei12345/RunCue configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lihei12345/RunCue. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lihei12345/RunCue/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lihei12345/RunCue

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lihei12345/runcue/claude-md/github.svg)](https://agentmods.dev/instructions/lihei12345/runcue/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lihei12345/runcue/claude-md"><img src="https://agentmods.dev/badge/instructions/lihei12345/runcue/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lihei12345/runcue/claude-md"><img src="https://agentmods.dev/badge/instructions/lihei12345/runcue/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 973 This file is loaded in full into every session.

When invoked 973 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00973	$0.00973
Opus 5.5	$0.00389	$0.00389
Sonnet 5.5	$0.00195	$0.00195
Haiku 4.5	$0.00097	$0.00097

Measured 2mo ago against content hash 3d9523a9d5ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

RunCue CLAUDE.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 2mo 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RunCue

RunCue 是开发者 UI 导航工具：在 XcodeBuildMCP 已经构建并启动 app 后，用自然语言完成 iOS UI 导航、输入和状态检查。

项目结构

src/core/agent-loop.ts — Agent Loop 核心（view tree -> VLM -> action -> repeat）
src/core/types.ts — 核心类型定义
src/vlm/cloud-api.ts — OpenAI-compatible VLM 适配器
src/vlm/prompt-templates/ — VLM prompt 模板
src/device/wda.ts — 唯一 iOS 设备 adapter，基于 WebDriverAgent
src/device/wda-manager.ts — WDA endpoint、启动、doctor
src/device/xcode-devices.ts — Xcode 设备枚举，基于 xcrun xctrace list devices
src/device/factory.ts — WDA-only adapter factory
src/mcp/server.ts — MCP Server
src/mcp/schemas.ts — MCP tool schema
src/cli.ts — CLI

开发命令

npm run build
npm run test
npm run dev

当前架构原则

WDA-only：不保留 simctl / legacy-simctl 设备路径，不暴露 backend 参数。
工具分工清晰：XcodeBuildMCP 负责 build/install/launch/logs；RunCue 只负责 UI 导航和检查。
输入走 WDA：type(text) 通过 WDA /keys，不走剪贴板、长按、粘贴菜单。
tree-first：普通场景只发 view tree；tree 不可用、稀疏或不变化时才发送当前截图。
通用性优先：不要针对某个 app、某段文案、某个业务页面写启发式逻辑。

RunCue + XcodeBuildMCP 协作规则

先用 XcodeBuildMCP build_run_sim 或等效流程启动 app。
把同一个设备的 UDID 或名称传给 RunCue 的 --device / deviceId。WDA path 下不要传 booted。
UI 导航、点击、滑动、输入文本统一通过 RunCue。
日志、截图、断点、构建结果仍通过 XcodeBuildMCP。
RunCue 完成后再截图，避免截到转场中间态。

MCP Tools

runcue_run(task, deviceId, platform?, bundleId?, maxSteps?, hints?, timeout?)
runcue_check(question, deviceId, platform?, bundleId?)
runcue_devices()
runcue_doctor(deviceId?, platform?)

CLI 示例

runcue devices
runcue doctor --device "iPhone 17 Pro Simulator" --platform ios-simulator
runcue run "登录并进入订单详情页" --device "iPhone 17 Pro Simulator" --platform ios-simulator --bundle-id com.example.MyApp
runcue check "当前是否在订单详情页？" --device "iPhone 17 Pro Simulator" --platform ios-simulator

输入模式

模式	发送内容	触发条件
`viewtree`	accessibility tree	tree 可用且信息足够
`hybrid`	tree + 当前截图	tree 稀疏，常见于 WebView/自绘 UI
`screenshot`	当前截图	tree 获取失败，或上一步操作后 tree 完全不变

Read the full file on GitHub · 78 lines

Changes

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.

2mo ago First seen · 78 lines · 973 tokens per session scan A 3d9523a9d5ee

Subscribe to this mod's changes

RunCue CLAUDE.md is an instructions file published in the GitHub repository lihei12345/RunCue (14 stars, last pushed 3mo ago), licensed MIT. It adds 973 tokens to every session, about $0.0039 per session on Opus 5.5. 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.

Mobile

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

RunCue: Instructions file for Claude Code