agentmods.dev

push-2-talk CLAUDE.md

push-2-talk CLAUDE.md is an instructions file for Claude Code from yyyzl/push-2-talk. It costs 8,943 tokens per session, scanned A, original, MIT.

Repository instructions for a Windows-only desktop application. They describe the project's Windows design choices, development rules, and native system interfaces.

In plain words
What is it for?
Use them when changing features such as global hotkeys, startup behavior, keyboard input, audio muting, system-tray support, or the Windows installer.
Why use it?
They tell contributors which Windows-specific approaches to use and which cross-platform assumptions to avoid.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

not rated 183 3mo ago A scan 8,943 tokens original MIT
View the source file yyyzl/push-2-talk
Install

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.

agentmods
npx agentmods add instructions/yyyzl/push-2-talk/claude-md
Clone the repo
git clone --depth 1 https://github.com/yyyzl/push-2-talk

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 push-2-talk CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yyyzl/push-2-talk/claude-md.svg)](https://agentmods.dev/instructions/yyyzl/push-2-talk/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yyyzl/push-2-talk/claude-md"><img src="https://agentmods.dev/badge/instructions/yyyzl/push-2-talk/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,943 This file is loaded in full into every session.
When invoked 8,943 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.08943 $0.08943
Opus 5 $0.04471 $0.04471
Sonnet 5 $0.01789 $0.01789
Haiku 4.5 $0.00894 $0.00894

Measured 6d ago against content hash 7db2251eef6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

push-2-talk 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 6d 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 · 773 lines

How it starts

The opening of the file, as written. The whole thing — 773 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

⚠️ Windows 专属设计理念（重要）

本项目是专门为 Windows 用户设计的桌面应用，不考虑跨平台兼容性。

核心原则

  1. Windows Only — 所有设计决策优先考虑 Windows 平台的最佳实践
  2. 直接使用 Win32 API — 不需要跨平台抽象层，可直接调用 Windows 原生 API
  3. Windows 特有功能优先 — 充分利用 Windows 独有的系统特性（如 GetAsyncKeyState、注册表、NSIS 安装器等）
  4. 简化实现 — 不需要为 macOS/Linux 兼容性增加额外的条件编译或抽象

设计决策指南

场景 正确做法 错误做法
全局热键检测 直接用 Win32 GetAsyncKeyState 用跨平台库的通用抽象
配置文件路径 直接用 %APPDATA% 用 dirs crate 的跨平台路径
安装器 只构建 NSIS (.exe) 同时构建 MSI/DMG/DEB
系统托盘 使用 Windows 原生托盘 API 考虑 macOS 菜单栏兼容
键盘模拟 直接用 Win32 SendInput 用跨平台键盘模拟库
音频静音 直接用 Windows Audio Session API 考虑 PulseAudio/CoreAudio

已采用的 Windows 专属方案

  • Ghost Key Detection: 使用 GetAsyncKeyState Win32 API 检测按键真实状态
  • Auto-Start: 直接操作 Windows 注册表 HKEY_CURRENT_USER\...\Run
  • Installer: 仅使用 NSIS 安装器，已移除 MSI 支持
  • Admin Rights: 要求管理员权限运行（全局键盘钩子需要）

后续开发注意事项

  • 不要为了"以防万一"添加 #[cfg(target_os = "...")] 条件编译
  • 不要选择"跨平台兼容"的库而放弃更好的 Windows 原生方案
  • 不要在代码注释中提及"未来可能支持其他平台"
  • 可以直接使用 windows crate 调用 Win32 API
  • 可以假设用户环境是 Windows 10/11

版本兼容性原则

本项目是单机桌面应用，无需考虑版本向前/向后兼容。

  • 用户通过自动更新升级后，直接运行新版本代码
  • 不存在"旧版客户端访问新版服务器"等分布式兼容场景
  • 放心修改：数据结构、API 格式、配置字段等可直接调整，无需保留旧版兼容代码
  • 例外情况：仅在配置文件迁移时需要考虑（如 config.rs 中的自动迁移逻辑，确保旧配置能正常加载）

Project Overview

PushToTalk is a desktop application built with Tauri 2.0 that enables voice-to-text input and AI-powered assistance via global keyboard shortcuts. The architecture follows a clear separation between:

  • React frontend (TypeScript + Tailwind CSS) for UI
  • Rust backend (Tauri) for system-level operations

Core Workflows

1. Dictation Mode (按住/松手录音)

  • Press Ctrl+Win (or custom hotkey) → Records audio → Release key → Transcribes via ASR API → Optional LLM post-processing → Auto-inserts text into active window
  • Supports two recording modes:
    • Press Mode: Hold key to record, release to stop (traditional)
    • Toggle Mode: Press F2 to start, press F2 again to finish (prevents accidental stops)

Read the full file on GitHub · 773 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.

  1. 6d ago First seen · 773 lines · 8,943 tokens per session scan A 7db2251eef6d

Subscribe to this mod's changes

push-2-talk CLAUDE.md is an instructions file published in the GitHub repository yyyzl/push-2-talk (183 stars, last pushed 3mo ago), licensed MIT. It adds 8,943 tokens to every session, about $0.0447 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 2026-08-30.

Related

Other instructions, from other repositories

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 · 6,785 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens