Borrowing it
Nothing to install: this file belongs to Uncle-Gao/Live-Translator-Hub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Uncle-Gao/Live-Translator-Hub/master/AGENTS.mdgit clone --depth 1 https://github.com/Uncle-Gao/Live-Translator-HubWrote 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/instructions/uncle-gao/live-translator-hub/agents-md)<a href="https://agentmods.dev/instructions/uncle-gao/live-translator-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/uncle-gao/live-translator-hub/agents-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.
<a href="https://agentmods.dev/instructions/uncle-gao/live-translator-hub/agents-md"><img src="https://agentmods.dev/badge/instructions/uncle-gao/live-translator-hub/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02672 | $0.02672 |
| Opus 5 | $0.01336 | $0.01336 |
| Sonnet 5 | $0.00534 | $0.00534 |
| Haiku 4.5 | $0.00267 | $0.00267 |
Grade A, and why
Live-Translator-Hub AGENTS.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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
Commands
# Install all workspace dependencies (run from repo root)
npm install
# Start the desktop app in dev mode (Electron + Vite HMR)
npm run dev
# Lint the desktop app
npm run lint -w desktop-app
# Build the desktop app (Electron distributable for all platforms)
npm run build -w desktop-app
# macOS only:
npm run build:mac -w desktop-app
# Build Vite frontend only (skip electron-builder)
npm run dist -w desktop-app
# Dict-generator: run tests (note: no test files currently exist)
npm test -w @live-translator/dict-generator
# i18n: extract new keys from t() and <Trans> calls into locale JSONs
npm run i18n:extract -w desktop-app
# i18n: translate all untranslated keys via Anthropic API
ANTHROPIC_API_KEY=sk-xxx npm run i18n:translate -w desktop-app
# Target specific languages:
ANTHROPIC_API_KEY=sk-xxx npm run i18n:translate -w desktop-app -- --lang ja-JP,ko-KR
# Translate README from zh-CN into 30+ languages (needs DEEPSEEK_API_KEY in .env)
node scripts/translate-readme.js
Important: The patcher packages (patcher-cursor, patcher-claude) have no CLI or build scripts. They are libraries called directly from electron/main.js via IPC handlers. The core package also has no scripts — it's a single-file runtime kernel injected raw into target apps.
Architecture
This is a npm workspaces monorepo with five packages under packages/. Pure JS throughout — no TypeScript. Electron 34, React 19, Tailwind CSS v4, Zustand, Framer Motion.
packages/desktop-app — Electron + React GUI
The main user-facing application. Built with Vite + vite-plugin-electron/simple.
electron/main.js— Electron main process. Handles 18 IPC channels acrossi18n:*,config:*,dict:*,cursor:*,claude:*,app:*, andupdate:*namespaces. Persists config to~/.live_translator_hub/config.json, encrypts API keys via ElectronsafeStorageto~/.live_translator_hub/api_keys.enc. On startup, migrates legacy config from~/.cursor_live_translator/and~/.claude_live_translator/into the unified Hub format, then deletes the old directories.electron/preload.js— Context bridge exposingwindow.liveTranslatorAPIwith invoke methods and event listeners (progress, sudo-prompt, update events). All renderer↔main communication goes through this interface.src/store/configStore.js— Single Zustand store. Top-levelconfighas keys:cursor,claude,apiKeys.saveConfigintentionally stripsapiKeysbefore writing to disk (keys saved separately viasaveApiKeys).src/App.jsx— Tab-based layout: Cursor Engine, Claude Engine, API Keys, Dict Generator.src/i18n.js— i18next init. Loads all JSON files fromsrc/locales/viaimport.meta.globat build time. Ships 34 languages.
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.
- 9d ago First seen · 194 lines · 2,672 tokens per session scan A aeaeabd724bd
Live-Translator-Hub AGENTS.md is an instructions file published in the GitHub repository Uncle-Gao/Live-Translator-Hub (32 stars, last pushed yesterday), licensed MIT. It adds 2,672 tokens to every session, about $0.0134 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.
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.
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.
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).
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).
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.
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.