humhum: Instructions file for Claude Code

CLAUDE.md

humhum CLAUDE.md is an instructions file for Claude Code from edible999999999-jpg/humhum. It costs 3,497 tokens per session, scanned A, original, MIT.

A set of instructions for working on HUMHUM, a Tauri desktop app with a small always-on-top character that reacts to coding-agent events with voice and commands.

In plain words
What is it for?
Use it to build, test, type-check, and understand the app's Rust backend, React interface, windows, and event flow.
Why use it?
It gives developers the project's structure, commands, event-testing method, and test procedures in one place.

Instructions file for Claude Code

Written for Claude Code: SessionEnd hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

This is edible999999999-jpg/humhum's own configuration. It tells Claude Code how to work on humhum 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 humhum configures →

Reuse

Borrowing it

Nothing to install: this file belongs to edible999999999-jpg/humhum. 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/edible999999999-jpg/humhum/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/edible999999999-jpg/humhum

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 humhum CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edible999999999-jpg/humhum/claude-md/github.svg)](https://agentmods.dev/instructions/edible999999999-jpg/humhum/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/edible999999999-jpg/humhum/claude-md"><img src="https://agentmods.dev/badge/instructions/edible999999999-jpg/humhum/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.

agentmods 80×15 button for humhum CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/edible999999999-jpg/humhum/claude-md"><img src="https://agentmods.dev/badge/instructions/edible999999999-jpg/humhum/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,497 This file is loaded in full into every session.
When invoked 3,497 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03497 $0.03497
Opus 5 $0.01749 $0.01749
Sonnet 5 $0.00699 $0.00699
Haiku 4.5 $0.00350 $0.00350

Measured 11d ago against content hash 2afc3ba8fc94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

humhum CLAUDE.md 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST http://localhost:31275/event \
CLAUDE.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 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.

项目简介

HumHum 是一个 Tauri v2 桌面宠物应用,监听多种 AI 编程助手事件(Claude Code、Codex、Qwen Code、Gemini CLI、Kimi K1 的 hooks 以及 QoderWork 日志),将其转化为语音播报,并支持语音指令和键盘快捷键交互。UI 是一个透明的、始终置顶的圆形小窗口,宠物形象是一只灯塔水母 "Hum"。

常用命令

npm install           # 安装依赖
npm run tauri dev     # 开发模式(同时启动 Vite 前端 + Rust 后端)
npm run tauri build   # 生产构建
npm run build         # 仅前端构建(tsc + vite)

Rust 后端在 src-tauri/ 目录下,支持标准 cargo 命令,但日常开发主要用 npm run tauri dev

手动模拟事件(用于测试):

curl -X POST http://localhost:31275/event \
  -H "Content-Type: application/json" \
  -d '{"hook_event_name":"TaskCompleted","session_id":"test-123","payload":{}}'

前端测试:npm test(vitest + node --test via scripts/run-tests.mjs)。完整测试套件:npm run test:all(含 relay 测试)。Rust 测试:cd src-tauri && cargo test --lib。类型检查:npx tsc --noEmitnpm run build。无 ESLint/Prettier 配置;类型安全依赖 tsc。

架构

双进程模型(Tauri v2)

  • Rust 后端src-tauri/src/):在端口 31275 运行 hyper HTTP 服务器(非 Axum/Actix),管理配置、会话存储、客户端注册表,通过 Tauri 事件系统向前端发送事件。
  • React 前端src/):渲染两个窗口 — "main"(280×210,透明桌宠浮层)和 "settings"(420×620,设置面板,默认隐藏)。App.tsx 通过 getCurrentWindow().label 判断窗口,在 PetWindow 挂载时调用 initBootstrap() 初始化全局单例。

语音管线(核心数据流)

事件到达 → VoicePipeline.processEvent()
    → 2 秒批量窗口(BATCH_WINDOW_MS)聚合快速连发事件
    → mergeEvents() 合并多事件为单次请求
    → OpenAISummarizer.summarize() (非流式调用,逐字符 yield)
    → SentenceSplitter.feed(char) (逐句切分,首句限60字加速TTFB)
    → TTS.synthesize(sentence) (Edge/OpenAI/ElevenLabs)
    → Rust play_audio IPC (base64 → /tmp/humhum-audio/*.mp3 → afplay)
    → 宠物状态: idle → processing → speaking → idle

注意:Summarizer 使用 stream: false 一次性获取完整响应,然后逐字符 yield 给 SentenceSplitter。音频播放使用 macOS 原生 afplay 命令,通过 Rust IPC(play_audio/stop_audio)调用,不使用 Web Audio API 播放。

初始化入口:src/lib/bootstrap.ts — 读取 Rust 配置,注册所有 provider,创建 VoicePipeline 等全局单例,通过 getAudioQueue() / getPipeline() / getSummarizer() / getSentenceSplitter() 导出访问。

Read the full file on GitHub · 179 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. 11d ago First seen · 179 lines · 3,497 tokens per session scan A 2afc3ba8fc94

Subscribe to this mod's changes

humhum CLAUDE.md is an instructions file published in the GitHub repository edible999999999-jpg/humhum (1 stars, last pushed 29d ago), licensed MIT. It adds 3,497 tokens to every session, about $0.0175 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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

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 · 5,153 tokens

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

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

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

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