WeReply: Skill for Claude Code

.claude/skills/macos-agent-development/SKILL.md

macos-agent-development is a skill for Claude Code from cacr92/WeReply. It costs 39 tokens per session (3,483 once invoked), scanned A, original, MIT.

A development guide for building a macOS agent in Swift with Apple's Accessibility API, which lets apps inspect and control approved user-interface elements.

In plain words
What is it for?
Implementing WeChat monitoring, input writing, command receiving, logging, and inter-process communication on macOS.
Why use it?
It explains the project structure, required permissions, and components needed for a macOS agent to monitor and interact with WeChat.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is cacr92/WeReply's own configuration. It tells Claude Code how to work on WeReply itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything WeReply configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cacr92/WeReply. 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/cacr92/WeReply/main/.claude/skills/macos-agent-development/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cacr92/WeReply

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.

agentmods badge for macos-agent-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/cacr92/wereply/macos-agent-development.svg)](https://agentmods.dev/skills/cacr92/wereply/macos-agent-development)
Your own site
<a href="https://agentmods.dev/skills/cacr92/wereply/macos-agent-development"><img src="https://agentmods.dev/badge/skills/cacr92/wereply/macos-agent-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,483 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.03483
Opus 5 $0.00019 $0.01741
Sonnet 5 $0.00008 $0.00697
Haiku 4.5 $0.00004 $0.00348

Measured 7d ago against content hash 3d452d27ddb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

macos-agent-development 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 7d 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/skills/macos-agent-development/SKILL.md · 581 lines

How it starts

The opening of the file, as written. The whole thing — 581 lines — stays where its author put it; the contents beside it link to each section on GitHub.

macOS Agent Development Skill

Expert guidance for developing macOS Platform Agent using Swift + Accessibility API.

Project Structure

platform_agents/macos_agent/
├── main.swift              # 主入口
├── WeChatMonitor.swift     # 微信监听模块
├── InputWriter.swift       # 输入框控制模块
├── IPC/                    # IPC 通信模块
│   ├── MessageSender.swift
│   └── CommandReceiver.swift
├── Utils/                  # 工具模块
│   └── Logger.swift
├── Package.swift           # Swift Package Manager 配置
└── README.md

Accessibility API Setup

Requesting Permissions

import Cocoa
import ApplicationServices

func requestAccessibilityPermissions() -> Bool {
    let options = [kAXTrustedCheckOptionPrompt.takeUnretainedValue() as String: true]
    let accessEnabled = AXIsProcessTrustedWithOptions(options as CFDictionary)

    if !accessEnabled {
        print("请在系统偏好设置 -> 安全性与隐私 -> 辅助功能 中授权")
    }

    return accessEnabled
}

Main Entry Point

// main.swift
import Foundation

class MacOSAgent {
    let monitor: WeChatMonitor
    let inputWriter: InputWriter
    let commandReceiver: CommandReceiver

    init() {
        self.monitor = WeChatMonitor(intervalMs: 500)
        self.inputWriter = InputWriter()
        self.commandReceiver = CommandReceiver()
        setupCommandHandlers()
    }

    func setupCommandHandlers() {
        commandReceiver.registerHandler(commandType: "WriteInput") { command in
            guard let content = command["content"] as? String else {
                return false
            }
            return self.inputWriter.writeToInput(content: content)
        }

        commandReceiver.registerHandler(commandType: "ClearInput") { _ in
            return self.inputWriter.clearInput()
        }

        commandReceiver.registerHandler(commandType: "HealthCheck") { _ in
            MessageSender.sendHealthStatus(status: "ok", agentType: "macos_accessibility")
            return true
        }

        commandReceiver.registerHandler(commandType: "Stop") { _ in
            self.commandReceiver.stop()
            return true
        }
    }

    func run() {
        // 检查权限
        guard requestAccessibilityPermissions() else {
            MessageSender.sendError(message: "未授予辅助功能权限", code: "PERMISSION_DENIED")
            return
        }

        // 启动命令监听(后台线程)
        commandReceiver.startListeningAsync()

        // 启动微信监听(主线程)
        monitor.startMonitoring()

        // 运行 RunLoop
        RunLoop.main.run()
    }
}

// 启动 Agent
let agent = MacOSAgent()
agent.run()

Read the full file on GitHub · 581 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 7d ago First seen · 581 lines · 39 tokens per session scan A 3d452d27ddb6

Subscribe to this mod's changes

macos-agent-development is a skill published in the GitHub repository cacr92/WeReply (6 stars, last pushed 7mo ago), licensed MIT. It adds 39 tokens to every session and 3,483 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 2026-08-31.

Related

Other skills, from other repositories

orca-emulator-android

Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…

stablyai/orca · 102 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

dogfood

Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.

callstack/agent-device · 55 tokens

winapp-maui

Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.

microsoft/winappCli · 71 tokens

apple-search-ads

When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…

Eronred/aso-skills · 127 tokens

android-pentest

A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.

Netw0rkNoob/VulnClaw · 32 tokens